Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 493. Отображено 100.
26-12-2013 дата публикации

METHOD OF HOST-DIRECTED ILLUMINATION AND SYSTEM FOR CONDUCTING HOST-DIRECTED ILLUMINATION

Номер: US20130343617A1
Автор: Langley Richard Jay, Peirce Michael, SEZILLE Nicolas Jacques Jean
Принадлежит:

A method of host-directed illumination for verifying the validity of biometric data of a user is provided that includes capturing biometric data from a user with an authentication device during authentication and directing illumination of the biometric data from a host authentication system during the capturing operation. Moreover, the method includes comparing illumination characteristics of the captured biometric data against illumination characteristics expected to result from the directing operation, and determining that the user is a live user when the illumination characteristics of the captured biometric data match the illumination characteristics expected to result from the directing operation. 1. A method of host-directed illumination comprising:randomly selecting, by a host authentication system, illumination instructions from an illumination instruction listing; andexecuting the selected instructions while capturing biometric data from a user with an authentication device, the selected instructions received from the host authentication system.2. A method in accordance with claim 1 , further comprising comparing illumination characteristics included in the captured biometric data against corresponding illumination characteristics expected to result from capturing the biometric data.3. A method in accordance with claim 2 , further comprising determining the user is live when the captured biometric data illumination characteristics match the expected illumination characteristics.4. A method in accordance with claim 1 , further comprising:determining illumination characteristic differences between sequential images included in the captured biometric data;comparing the determined illumination characteristic differences against corresponding expected illumination characteristic differences; anddetermining the user is live when less than all of the determined illumination characteristic differences match the corresponding expected illumination characteristic ...

Подробнее
Номер записи: 1
03-04-2014 дата публикации

LIVENESS DETECTION

Номер: US20140093140A1
Автор: CAVALLINI Alessio, Juveneton Florian
Принадлежит: Accenture Global Services Limited

An image of a portion of a person's body is accessed, the image having been captured by an image capture device. Using the image, measurements of characteristics in the image are obtained, the characteristics in the image having been selected based on a statistical analysis of characteristics (i) in a plurality of first images taken directly of a person and (ii) in a plurality of second images taken of an image of a person. Based on a liveness function, a score for the image is determined using the obtained measurements of the characteristics in the image. A threshold value is accessed. The score of the image is compared to the accessed threshold value. Based on the comparison of the score of the image to the accessed threshold value, the image is determined to be have been taken by the image capture device imaging the portion of the person's body. 1. A biometric authentication system comprising: ["accessing an image of a portion of a person's body, the image having been captured by an image capture device;", 'obtaining, using the image, measurements of characteristics in the image, the characteristics in the image having been selected based on a statistical analysis of characteristics (i) in a plurality of first images taken directly of a person and (ii) in a plurality of second images taken of an image of a person;', 'determining, based on a liveness function, a score for the image using the obtained measurements of the characteristics in the image;', 'accessing, from the computer storage medium, a threshold value;', 'comparing the score of the image to the accessed threshold value; and', "based on the comparison of the score of the image to the accessed threshold value, determining that the image was taken by the image capture device imaging the portion of the person's body."], 'one or more processors configured to interact with a computer storage medium to perform operations comprising2. The biometric authentication system of claim 1 , further comprising: ...

Подробнее
Номер записи: 2
04-01-2018 дата публикации

BIOMETRIC IDENTIFICATION BY GARMENTS HAVING A PLURLITY OF SENSORS

Номер: US20180000367A1
Автор: LONGINOTTI-BUITONI Gianluigi
Принадлежит:

Biometric identification methods and apparatuses (including devices and systems) for uniquely identifying one an individual based on wearable garments including a plurality of sensors, including but not limited to sensors having multiple sensing modalities (e.g., movement, respiratory movements, heart rate, ECG, EEG, etc.). 1. A method of confirming a user's identity , the method comprising:wearing a garment comprising a plurality of integrated sensors at predetermined locations;synchronously recording sensor data from multiple predetermined locations on the garment;generating, in the garment, a biometric token from the recorded sensor data;transmitting the biometric token to a lodger in or on the garment; andtransmitting the biometric token to a third party having a biometric template against which the biometric token may be tested.2. The method of claim 1 , wherein generating a biometric token from the recorded sensor data comprises generating the biometric token in a scheduler on the garment.3. The method of claim 1 , wherein wearing comprises adjusting the position of the sensors based on haptic feedback from the garment.4. The method of claim 1 , wherein synchronously recording sensor data comprises synchronously recording sensor data from a plurality of motion sensors.5. The method of claim 1 , wherein synchronously recording sensor data comprises synchronously recording sensor data from a plurality of motion sensors claim 1 , one or more respiration sensors and one or more electrodes configured to contact the user's skin when the garment is worn.6. The method of claim 1 , wherein wearing the garment comprises wearing the garment over the user's torso.7. The method of claim 1 , wherein synchronously recording comprises synchronously recording sensor data from multiple sensor types on the garment.8. The method of claim 7 , wherein synchronously recording sensor data comprises recording data at a plurality of frequencies.9. The method of claim 1 , further ...

Подробнее
Номер записи: 3
07-01-2016 дата публикации

METHOD AND SYSTEM FOR AUTHENTICATING USER IDENTITY AND DETECTING FRAUDULENT CONTENT ASSOCIATED WITH ONLINE ACTIVITIES

Номер: US20160005050A1
Автор: Teman Ari
Принадлежит:

A method and system for authenticating a user's identity, studying user state and reaction, and detecting fraudulent user content associated with online activities. The method and system receives user content which may include video images, and processes the user content using facial recognition algorithms and analyzing various parameters to uniquely identify a user and a potentially fraudulent online posting, activity or profile. The method and system initiates a number of actions based on a determination that the user or posting, activity or profile is potentially fraudulent. 1. A method for determining fraudulent content online , the method comprising:receiving, by a computer system, user content;processing, by a processing device, the user content to determine a likelihood that the user content is presented fraudulently; andinitiating one or more actions based on a determination the user content is relatively likely to be presented fraudulently.2. The method of claim 1 , wherein the user content is a referenced image.3. The method of claim 2 , wherein the step of processing user content to determine a likelihood that the user content is presented fraudulently includes the steps of:searching an image database to identify incidences of a referenced image; andmatching incidences of a referenced image with identical or similar images within said image database.4. The method of wherein searching the image database includes searching embedded metadata associated with particular images stored within said image database.5. The method of claim 1 , further comprising the steps of:identifying one or more fields within said user content;employing the processing device to analyze and assign a first fraud score for each identified field within said user content;initiating one or more actions based on a determination that one or more first fraud scores exceeds a maximum allowable first fraud score;employing the processing device to determine an aggregate fraud score of the ...

Подробнее
Номер записи: 4
07-01-2021 дата публикации

FINGERPRINT MODULE, FINGERPRINT IDENTIFICATION SYSTEM, CONTROL METHOD, AND SMART LOCK

Номер: US20210004445A1
Автор: LI QINGBIN, Zhou Luming
Принадлежит: Shenzhen Goodix Technology Co., Ltd.

A fingerprint module, a fingerprint identification system, a control method and a smart lock. The fingerprint module includes: a fingerprint sensor, an MOC, and a key member, and the key member is connected to the fingerprint sensor. The key member is configured to generate an interrupt signal according to a touch operation of a user on the key member to wake up the main control unit, thereby reducing power consumption of the main control unit. 1. A fingerprint module , connected to a main control unit , the fingerprint module comprising: a fingerprint sensor , a match on chip (MOC) and a key member , and the key member is connected to the fingerprint sensor;the fingerprint sensor is configured to collect fingerprint information of a verification target, and output the fingerprint information to the MOC;the MOC is configured to authenticate the fingerprint information, and output an authentication result to the main control unit; andthe key member is configured to generate an interrupt signal according to a touch operation of a user on the key member, to wake up the main control unit.2. The fingerprint module according to claim 1 , wherein:at least one of the MOC or the fingerprint sensor is further configured to receive a first control instruction sent by the main control unit, and enter a power-up state according to the first control instruction.3. The fingerprint module according to claim 2 , wherein:the MOC is further configured to control the key member to be in a power-down state.4. The fingerprint module according to claim 3 , wherein the MOC is connected to the key member through a control switch; andthe MOC is configured to control the key member to be in the power-down state through the control switch when the MOC is in the power-up state.5. The fingerprint module according to claim 1 , wherein:at least one of the MOC or the fingerprint sensor is further configured to receive a second control instruction sent by the main control unit, and enter a power- ...

Подробнее
Номер записи: 5
07-01-2021 дата публикации

Fingerprint identification device and fingerprint identification method

Номер: US20210004562A1
Автор: Hung-Yu Yang, I-Hsiu Chen, Shao-Yang Chiang
Принадлежит: NOVATEK MICROELECTRONICS CORP

A fingerprint identification device and a fingerprint identification method are provided. The fingerprint identification device includes a self-emitting display panel, a fingerprint sensor and a processor. The self-emitting display panel displays at least one light pattern in a sensing region. The fingerprint sensor senses a finger object located above the sensing region of the self-emitting display panel to generate a first fingerprint image and a second fingerprint image corresponding to the at least one light pattern. The processor is coupled to the fingerprint sensor. The processor determines whether the first fingerprint image and the second fingerprint image have opposite tones to identify the finger object is a real finger or a fake finger.

Подробнее
Номер записи: 6
02-01-2020 дата публикации

LIVING BODY DETECTION METHOD AND SYSTEM, COMPUTER-READABLE STORAGE MEDIUM

Номер: US20200005061A1
Автор: Lu Jianghu, Sun Yahao, WANG Peng, YAO Cong
Принадлежит:

A living body detection method and system, and a computer-readable storage medium are disclosed. The living body detection method includes: acquiring a video including an object to be detected; extracting at least two images to be detected from the video, and determining optical flow information according to the at least two images to be detected; dividing each image to be detected into a foreground image and a background image according to the optical flow information; using a classifier to perform category judgment on the foreground image and the background image to obtain a category distribution of the foreground image and a category distribution of the background image; and obtaining a probability that the object to be detected is a living body according to the category distribution of the foreground image and the category distribution of the background image. 1. A living body detection method , comprising:acquiring a video including an object to be detected;extracting at least two images to be detected from the video, and determining optical flow information according to the at least two images to be detected;dividing each image to be detected into a foreground image and a background image according to the optical flow information;using a classifier to perform category judgment on the foreground image and the background image to obtain a category distribution of the foreground image and a category distribution of the background image; andobtaining a probability that the object to be detected is a living body according to the category distribution of the foreground image and the category distribution of the background image.2. The method according to claim 1 , wherein the classifier comprises a neural network model; andusing the classifier to perform category judgment on the foreground image and the background image to obtain the category distribution of the foreground image and the category distribution of the background image comprises:inputting the foreground ...

Подробнее
Номер записи: 7
07-01-2021 дата публикации

FACIAL DATA COLLECTION AND VERIFICATION

Номер: US20210006415A1
Автор: Luo Hongwei, Sun Xi
Принадлежит: Advanced New Technologies Co., Ltd.

The present application provides a facial data collection and verification solution. In this solution, after collecting a face sample, a collection device uses the face sample and check data including a random number as to-be-signed data, performs signature by using a device private key, to obtain a facial data signature, and then obtains trusted facial data based on the to-be-signed data, the facial data signature, and a digital certificate that includes a device public key. When performing verification on the trusted facial data, a facial recognition server sequentially performs verification on the digital certificate that includes the device public key, the facial data signature, and the check data. Because content used for the verification process is added for the face sample on the collection device, subsequent verification cannot succeed if a transmitted communication packet is replaced by an attacker. Therefore, a replay attack is prevented at the collection source. 1. A computer-implemented method comprising:obtaining, by a collection device, a random number that is generated by a facial recognition server responsive to a request initiated by a user, wherein the random number corresponds to current facial data collection and is stored on the facial recognition server;obtaining, by the collection device from a local service terminal, a collection invoking instruction corresponding to the current facial data collection, wherein the collection invoking instruction is generated by the local service terminal after the local service terminal obtains a facial recognition service request initiated by the user, and wherein the local service terminal performs facial verification and facial registration;collecting, by the collection device, a face sample of the user based on the collection invoking instruction;generating, based on the face sample of the user, a first set of data, wherein the first set of data comprises a device identifier corresponding to the ...

Подробнее
Номер записи: 8
27-01-2022 дата публикации

METHOD AND APPARATUS WITH LIVENESS DETECTION

Номер: US20220027649A1
Автор: CHOI JIHO, HAN Jaejoon, KWAK Youngjun, Lee Hana, LEE Solae, LEE Yong-Il, PARK Sungheon, YOO Byung In
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

A processor-implemented method with liveness detection includes: receiving a plurality of phase images of different phases; generating a plurality of preprocessed phase images by performing preprocessing, including edge enhancement processing, on the plurality of phase images of different phases; generating a plurality of differential images based on the preprocessed phase images; generating a plurality of low-resolution differential images having lower resolutions than the differential images, based on the differential images; generating a minimum map image based on the low-resolution differential images; and performing a liveness detection on an object in the phase images based on the minimum map image. 1. A processor-implemented method with liveness detection , comprising:receiving a plurality of phase images of different phases;generating a plurality of preprocessed phase images by performing preprocessing, including edge enhancement processing, on the plurality of phase images of different phases;generating a plurality of differential images based on the preprocessed phase images;generating a plurality of low-resolution differential images having lower resolutions than the differential images, based on the differential images;generating a minimum map image based on the low-resolution differential images; andperforming a liveness detection on an object in the phase images based on the minimum map image.2. The method of claim 1 , whereinthe performing of the preprocessing comprises removing noise from the phase images, andthe edge enhancement processing comprises enhancing an edge region of the object in each of the phase images.3. The method of claim 1 , wherein the performing of the edge enhancement processing comprises applying claim 1 , to each of the phase images claim 1 , any one or more of a Sobel filter claim 1 , an anisotropic filter claim 1 , a Laplacian filter claim 1 , a Canny edge filter claim 1 , and a neural network processing.4. The method of ...

Подробнее
Номер записи: 9
27-01-2022 дата публикации

METHODS, SYSTEMS AND COMPUTER PROGRAM PRODUCTS FOR EYE BASED SPOOF DETECTION

Номер: US20220027650A1
Автор: Gupta Arnav
Принадлежит:

The invention enables spoof detection in eye based person detection, person recognition, or person monitoring systems. The invention includes (i) illuminating an eye from a first source located at a first position, (ii) illuminating the eye from a second source located at a second position spaced from the first position, (iii) acquiring at the image sensor, a set of images of the eye which includes (a) a first set of image information representing a first specular reflection at a third position relative to the eye, (b) a second set of image information representing a second specular reflection at a fourth position relative to the eye, (iv) determining a difference value representing a difference between the third position and the fourth position, and (v) generating a data signal representing detection of a real eye in response to determining that the difference value is less than a threshold value. 1. A method for eye-based spoof detection , the method comprising:illuminating an eye positioned within a field of view of an image sensor, with illuminating radiation from a first source of illumination located at a first position;illuminating the eye with illuminating radiation from a second source of illumination located at a second position that is spaced apart from the first position; a first set of image information corresponding to a first image region representing a first specular reflection at a third position relative to the eye;', 'a second set of image information corresponding to a second image region representing a second specular reflection at a fourth position relative to the eye;, 'acquiring at the image sensor, a set of images of the eye, wherein the set of images includesdetermining based on image information corresponding to the acquired set of images, a difference value representing a difference between the third position and the fourth position; andgenerating a data signal representing detection of a real eye in response to determining that the ...

Подробнее
Номер записи: 10
11-01-2018 дата публикации

PROCESS AND SYSTEM FOR VIDEO SPOOF DETECTION BASED ON LIVENESS EVALUATION

Номер: US20180012059A1
Автор: BUSCH Christoph, BYLAPPA RAJA Kiran, GACON Pierre, RAGHAVENDRA Ramachandra
Принадлежит:

The invention presents a process for determining a video as being a spoof or a genuine recording of a live biometric characteristic, characterized in that it comprises the steps of: 1. A process for determining a video of a biometric characteristic as being a spoof or a genuine recording of a live biometric characteristic , wherein the video comprises a temporal sequence of frames (j) , the process being implemented in a system comprising a processing unit , characterized in that it comprises the steps of:preprocessing the video, said preprocessing comprising aligning the biometric characteristic on each frame of the video, computing a difference between a motion intensity of a current frame and a motion intensity of each frame of a set of preceding frames,', 'inferring, from said differences, a differential motion intensity of the current frame,', 'inferring from the differential motion intensities of the plurality of frames a motion intensity of the video,', 'comparing said motion intensity to a predetermined threshold, and assigning a liveness score to the video, depending on a the-comparison of the motion intensity of the video with the threshold, and, 'determining a liveness score of the video, said determination comprising, for each frame of a plurality of framesaccording to the liveness scores of the video, determining whether the video is a genuine recording of a biometric characteristic or a spoof.2. A process according to claim 1 , wherein the motion intensity of a frame comprises phase variation of the frame claim 1 , and motion intensity of the video comprises phase variation of the video.3. A process according to claim 1 , wherein motion intensity of the video is inferred from differential motion intensities of at least ten frames of the video.4. A process according to claim 1 , wherein the set of frames for computation of the motion intensity difference with the current frame comprises from three to eight frames claim 1 , and preferably five frames ...

Подробнее
Номер записи: 11
11-01-2018 дата публикации

SPOOFING ATTACK DETECTION DURING LIVE IMAGE CAPTURE

Номер: US20180012094A1
Автор: Martin Brian, Wu Yecheng
Принадлежит:

In general, one innovative aspect of the subject matter described in this specification can be embodied in a computer-implemented method. The method includes, detecting, by an imaging device, the presence of an object to be imaged. The method further includes, measuring, by the imaging device, a first characteristic of the object to be imaged, and measuring, by the imaging device, a second characteristic of the object to be imaged. The method further includes, determining, by a computing device, that at least one of the first characteristic of the object or the second characteristic of the object exceeds a threshold; and in response to determining, indicating, by the computing device, whether the object to be imaged is one of a spoofed object or an actual object. 1. A computer-implemented method , the method comprising:detecting, by an imaging device, the presence of an object to be imaged;measuring, by the imaging device, a distance between the imaging device and the object to be imaged;using, by a computing device, the measured distance and at least one feature of the imaging device to determine a characteristic of the object to be imaged;determining, by the computing device, whether the characteristic of the object exceeds a threshold; andindicating, by the computing device, whether the object to be imaged is one of a spoofed object and an actual object.2. The method of claim 1 , wherein the determined characteristic of the object to be imaged is the size of the object.3. The method of claim 1 , wherein the at least one feature of the imaging device includes one of:focal length of a lens of the imaging device,size of an imaging sensor of the imaging device,image pixel resolution of the imaging sensor, andobject size of the image in pixels.4. The method of claim 3 , wherein determining the characteristic of the object to be imaged includes using a width of an image detected by the imaging device and a width of the imaging sensor.5. The method of claim 4 , wherein ...

Подробнее
Номер записи: 12
10-01-2019 дата публикации

METHOD FOR RECOGNISING A FALSE PAPILLARY PRINT BY STRUCTURED LIGHTING

Номер: US20190012513A1
Автор: BOUTET Jerome, FOURRE Joel Yann, Mainguet Jean-François
Принадлежит:

A method for determining if a papillary print is comprised of living human tissue or not, using a papillary print sensor comprising in superposition, a contact surface, an array optical sensor, and a plurality of illuminating devices parallel between them. The method comprises illumination of the papillary print by the illuminating devices forming together, on the contact surface, a light pattern which is uniform along an axis that extends from one side to the other of a detecting surface of the array optical sensor, and acquisition of an image by the array optical sensor, with these steps being implemented at least once; in each image, selection of the pixels corresponding to the valleys or ridges of the print; and using the pixels selected, extraction of an optical characteristic defining the response to illumination, of the material comprising the papillary print. 113-. (canceled)1410611021011221211121111102110. Method for determining if a papillary print is comprised of living human tissue or not , the print being in direct physical contact with a contact surface () of a papillary print sensor (; ) comprising , in superposition under the contact surface , an array optical sensor (; ) and illuminating means (; ) formed by a plurality of illuminating devices (; ) parallel between them , wherein it comprises the following steps:{'b': 1110', '2110', '1110', '1110', '106', '125', '111', '211, 'sub': i', '2', '3, 'illumination of the papillary print by the illuminating means, with the illuminating devices (; ; A, B) forming together, on the contact surface (), at least one light pattern which is uniform along an axis that extends from one side to the other of a detecting surface () of the array optical sensor, and acquisition of an image (I, I, I) by the array optical sensor, with these steps being implemented at least once, and at each step of illumination of the papillary print, the illuminating means (; ) together form at least one light pattern which is comprised ...

Подробнее
Номер записи: 13
14-01-2021 дата публикации

METHOD AND APPARATUS FOR IMAGE PROCESSING, ELECTRONIC DEVICE, AND STORAGE MEDIUM

Номер: US20210012091A1
Автор: LIU Tinghao, QIAN CHEN, Wang Quan
Принадлежит:

Embodiments of the present disclosure relate to a method and an apparatus for image processing, an electronic device and a storage medium. The method includes: obtaining a target region image in an image to be identified, the target region image comprising at least one target object; determining a state of each of the at least one target object based on the target region image, where the state includes an opened-eye state and a closed-eye state; and determining an identity authentication result based at least part on the state of each of the at least one target object. 1. A method for image processing , comprising:acquiring a target region image in an image to be recognized, the target region image comprising at least one target object;determining, based on the target region image, a state of each of the at least one target object, the state comprising eye-open and eye-closed; anddetermining, based at least part on the state of each of the at least one target object, an identity authentication result.2. The method of claim 1 , wherein the at least one target object comprises at least one eye.3. The method of claim 1 , wherein determining claim 1 , based at least part on the state of each of the at least one target object claim 1 , the identity authentication result comprises:responsive to the at least one target object comprising a target object of which the state is eye-open, determining that identity authentication succeeds.4. The method of claim 1 , before determining claim 1 , based on the target region image claim 1 , the state of each of the at least one target object claim 1 , further comprising: determining whether there is preset image information in a base database matched with the image to be recognized claim 1 , whereindetermining, based on the target region image, the state of each of the at least one target object comprises: responsive to there being the preset image information in the base database matched with the image to be recognized, determining ...

Подробнее
Номер записи: 14
14-01-2021 дата публикации

Dynamic lighting for image-based verification processing

Номер: US20210012092A1
Автор: Thomas Purves
Принадлежит: VISA INTERNATIONAL SERVICE ASSOCIATION

A facial recognition system may monitor a light source that causes a unique pattern of light to be projected on the subject during image capture. The lighting pattern may include intensity, color, source location, pattern, modulation, or combinations of these. The lighting pattern may also encode a signal used to further identify a location, time, or identity associated with the facial recognition process. In some embodiments the light source may be infrared or another frequency outside the visible spectrum but within the detection range of a sensor capturing the image.

Подробнее
Номер записи: 15
17-01-2019 дата публикации

3d mask face anti-spoofing with remote photoplethysmography

Номер: US20190014999A1
Автор: Guoying Zhao, Pong Chi YUEN, Shengping Zhang, Siqi LIU
Принадлежит: Hong Kong Baptist University HKBU

The present invention relates to 3D mask face anti-spoofing with remote photoplethysmography. More particularly, it relates to a local rPPG correlation model to extract discriminative and robust local rPPG signal patterns so that an imposter can better be detected regardless of the material and quality of the mask.

Подробнее
Номер записи: 16
21-01-2016 дата публикации

MULTISPECTRAL EYE ANALYSIS FOR IDENTITY AUTHENTICATION

Номер: US20160019420A1
Автор: Dos Remedios Alwyn, FENG CHEN, Shen Liang, SHENG Tao, Zhang Xiaopeng, Zhuo Shaojie
Принадлежит:

Certain aspects relate to systems and techniques for generating high resolution iris templates and for detecting spoofs, enabling more reliable and secure iris authentication. Pairs of RGB and NIR images can be captured by the iris authentication system for use in iris authentication, for example using an NIR LED flash and a four-channel image sensor. Multiple images of the user's iris can be captured by the system in a relatively short period of time and can be fused together to generate a high resolution iris image that can contain more detail of the iris structure and unique pattern than each individual images. The “liveness” of the iris, referring to whether the iris is a real human iris or an iris imitation, can be assessed via a liveness ratio based on comparison of known iris and sclera reflectance properties at various wavelengths to determined sensor responses at those same wavelengths.

Подробнее
Номер записи: 17
21-01-2016 дата публикации

MULTISPECTRAL EYE ANALYSIS FOR IDENTITY AUTHENTICATION

Номер: US20160019421A1
Автор: Dos Remedios Alwyn, FENG CHEN, Shen Liang, SHENG Tao, Zhang Xiaopeng, Zhuo Shaojie
Принадлежит:

Certain aspects relate to systems and techniques for generating high resolution iris templates and for detecting spoofs, enabling more reliable and secure iris authentication. Pairs of RGB and NIR images can be captured by the iris authentication system for use in iris authentication, for example using an NIR LED flash and a four-channel image sensor. Multiple images of the user's iris can be captured by the system in a relatively short period of time and can be fused together to generate a high resolution iris image that can contain more detail of the iris structure and unique pattern than each individual images. The “liveness” of the iris, referring to whether the iris is a real human iris or an iris imitation, can be assessed via a liveness ratio based on comparison of known iris and sclera reflectance properties at various wavelengths to determined sensor responses at those same wavelengths.

Подробнее
Номер записи: 18
17-01-2019 дата публикации

Method of Living Body Detection and Terminal Device

Номер: US20190019046A1
Автор: Tang Cheng, Zhang Xueyong, Zhou Haitao, Zhou Yibao
Принадлежит:

A method of living body detection performed with a terminal device includes the following operations. A first image for a target object is obtained via a camera at a first focal length, and a second image for the target object is obtained via the camera at a second focal length. A difference image of the first image and the second image is determined. Whether the target object is a living body is determined according to the difference image. 1. A method of living body detection , comprising:obtaining a first image for a target object via a camera at a first focal length;obtaining a second image for the target object via the camera at a second focal length;determining a difference image of the first image and the second image; anddetermining whether the target object is a living body according to the difference image.2. The method of claim 1 , wherein the determining whether the target object is the living body according to the difference image comprises:performing an image enhancement process on the difference image;performing a binarization process on the difference image subjected to the image enhancement process; anddetermining whether the target object is the living body according to the difference image subjected to the binarization process.3. The method of claim 1 , wherein the determining whether the target object is the living body according to the difference image comprises:acquiring a histogram of the difference image;converting the histogram into a curve diagram; anddetermining a similarity between the curve diagram and a preset curve diagram, and determining whether the target object is the living body according to the similarity.4. The method of claim 1 , wherein the determining whether the target object is the living body according to the difference image comprises:obtaining one or more features from the difference image; anddetermining whether the target object is the living body according to the one or more features.5. The method of claim 4 , wherein ...

Подробнее
Номер записи: 19
17-01-2019 дата публикации

IRIS-BASED LIVING-BODY DETECTION METHOD, MOBILE TERMINAL AND STORAGE MEDIUM

Номер: US20190019047A1
Автор: Tang Cheng, Zhang Xueyong, Zhou Haitao, Zhou Yibao
Принадлежит: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.

Disclosed are an iris-based living-body detection method, a mobile terminal and a storage medium. According to the method, in response to detection of the mobile terminal being lifted, the touch display screen is lighted, and the touch display screen is controlled to display preset guide content, the preset guide content is used to guide eyes watching the touch display screen to move; the iris recognition apparatus is notified to perform iris acquisition for a target object associated with the eyes, to obtain a plurality of iris images; and it is determined whether the target object is a living body with the plurality of iris images. 1. An iris-based living-body detection method , executed by a mobile terminal comprising a touch display screen and an iris recognition apparatus , the method comprising: in response to detection of the mobile terminal being lifted ,lighting the touch display screen, and controlling the touch display screen to display preset guide content, wherein the preset guide content is used to guide eyes watching the touch display screen to move;notifying the iris recognition apparatus to perform iris acquisition for a target object associated with the eyes, to obtain a plurality of iris images; anddetermining whether the target object is a living body with the plurality of iris images.2. The method according to claim 1 , wherein determining whether the target object is a living body with the plurality of iris images comprises:determining a constriction change rate of a pupil with the plurality of iris images, andconfirming that the target object is a living body, when the constriction change rate is within a preset range.3. The method according to claim 2 , wherein determining the constriction change rate of a pupil with the plurality of iris images comprises:determining an area of the pupil for each of the plurality of iris images successively in shooting time sequence, to obtain a plurality of area values; anddetermining change rates between ...

Подробнее
Номер записи: 20
16-01-2020 дата публикации

THREE-DIMENSIONAL LIVING-BODY FACE DETECTION METHOD, FACE AUTHENTICATION RECOGNITION METHOD, AND APPARATUSES

Номер: US20200019760A1
Автор: Li Liang, MA Chenguang
Принадлежит:

Embodiments of this specification relate to a three-dimensional living-body face detection method, a face authentication recognition method, and apparatuses. The three-dimensional living-body face detection method includes: acquiring multiple frames of depth images for a target detection object; pre-aligning the multiple frames of depth images to obtain pre-processed point cloud data; normalizing the point cloud data to obtain a grayscale depth image; and performing living-body detection based on the grayscale depth image and a living-body detection model. 1. A three-dimensional living-body face detection method , comprising:acquiring multiple frames of depth images for a target detection object;pre-aligning the multiple frames of depth images to obtain pre-processed point cloud data;normalizing the point cloud data to obtain a grayscale depth image; andperforming living-body detection based on the grayscale depth image and a living-body detection model.2. The method of claim 1 , wherein the pre-processed point cloud data is first pre-processed point cloud data claim 1 , the grayscale depth image a first grayscale depth image claim 1 , and the living-body detection model is obtained by:acquiring multiple frames of depth images for a target training object:pre-aligning the multiple frames of depth images for the target training object to obtain second pre-processed point cloud data;normalizing the second point cloud data to obtain a second grayscale depth image sample; andtraining based on the second grayscale depth image sample and label data of the second grayscale depth image sample to obtain the living-body detection model.3. The method of claim 1 , wherein the pre-aligning the multiple frames of depth images to obtain pre-processed point cloud data comprises:roughly aligning the multiple frames of depth images based on three-dimensional key facial points; andfinely aligning the roughly aligned depth images based on an iterative closest point (ICP) algorithm to ...

Подробнее
Номер записи: 21
21-01-2021 дата публикации

BIOMETRIC IMAGING SYSTEM AND METHOD OF DETERMINING PROPERTIES OF A BIOMETRIC OBJECT USING THE BIOMETRIC IMAGING SYSTEM

Номер: US20210019540A1
Автор: NILSSON René
Принадлежит: Fingerprint Cards AB

There is provided a biometric imaging system comprising a display panel. The display panel in turn comprises: a plurality of display pixels configured to emit visible light and controllable to form an image in the display; and a plurality of non-visible light emitting elements configured to emit linearly polarized non-visible light; a camera configured to receive polarized non-visible light having an orientation which is rotated with respect to the emitted linearly polarized light; and control circuitry configured to: activate the plurality of non-visible light emitting elements to emit linearly polarized light towards a biometric object; and control the camera to capture an image based on light reflected by the biometric object having a polarization which is rotated with respect to the emitted linearly polarized light. 1. A biometric imaging system comprising:a display panel comprising a plurality of display pixels configured to emit visible light and controllable to form an image in the display, and a plurality of non-visible light emitting elements configured to emit linearly polarized non-visible light;a camera configured to receive polarized non-visible light having an orientation which is rotated with respect to the emitted linearly polarized light; and activate the plurality of non-visible light emitting elements to emit linearly polarized light towards a biometric object, the biometric object being an eye; and', 'control the camera to capture an image based on light reflected by the biometric object having a polarization which is rotated with respect to the emitted linearly polarized light; and', 'determine if the biometric object belongs to a real person based on birefringent properties of the biometric object observed in the captured image., 'control circuitry configured to2. The biometric imaging system according to claim 1 , wherein the camera is configured to receive polarized non-visible light having a 90° rotation with respect to the emitted linearly ...

Подробнее
Номер записи: 22
26-01-2017 дата публикации

BIOMETRIC IDENTIFICATION APPARATUS

Номер: US20170024601A1
Автор: LIN PO-CHUAN
Принадлежит:

A biometric identification apparatus includes a control module, a fingerprint identification module including a fingerprint scan controller and a fingerprint receiver, a pulsatile blood flow detection module including one or multiple light sources and a photo detector, and a holder body defining a fingerprint identification zone and a pulsatile blood flow identification zone. In application, the user simply needs to press the fingertip of one single finger on the fingerprint identification zone and pulsatile blood flow identification zone of the holder body so that the biometric identification apparatus can detect user's fingerprint and pulsatile blood flow signals, fetch and convert characteristic data of detected signals, and then match fetched fingerprint and pulsatile blood flow characteristic data with respective reference data for security access control. The application of this dual-biometric identification technology greatly increases the cracking difficulty, achieving better anti-theft function. 1. A biometric identification apparatus , comprising a control module , a fingerprint identification module , a pulsatile blood flow detection module and a holder body , wherein;said control module is electrically connected to said fingerprint identification module and said pulsatile blood flow detection module and adapted for controlling said fingerprint identification module and said pulsatile blood flow detection module to start detection, receding detected feedback signals from said fingerprint identification module and said pulsatile blood flow detection module and using the data of said detected feedback signals for analysis and matching through a microprocessor thereof;said fingerprint identification module comprises a fingerprint scan controller controllable by said microprocessor of said control module to generate a scan control signal, and a fingerprint receiver adapted for receiving signals from said fingerprint scan controller and transmitting received ...

Подробнее
Номер записи: 23
28-01-2016 дата публикации

CONTROLLED ACCESS TO FUNCTIONALITY OF A WIRELESS DEVICE

Номер: US20160026884A1
Автор: Ferren Bran
Принадлежит:

Various embodiments of the invention may be used to verify that a person being authorized by biometric techniques to use a device is a living person and not some form of recording intended to spoof the system. Some embodiments may try to cause a change in a measured biometric feature, and compare images taken before and after the change to verify the change occurred. In some embodiments, multiple stages of verification may be used, either to increase the difficulty of spoofing the security system, or to provide different levels of security for different levels of access to the device's functionality. 1. An apparatus comprising:one or more processors;a touchscreen coupled to the one or more processors;a camera coupled to the one or more processors; and ["receive a request to access at least part of the apparatus's functionality;", 'perform face authentication based on a first input from the camera, to determine if a person attempting to access the at least part of the functionality has been approved to do so;', 'perform liveness verification, based on a second input from the camera, to determine whether the second input is from a living person corresponding to the person; and', 'grant access to the at least part of the functionality only if both the face authentication and the liveness verification are successful;, 'one or more non-transitory machine-readable media comprising instructions which, when executed by the one or more processors, cause the one or more processors to prompt the person to blink; and', 'use the camera to take a picture of at least a part of a face of the person., 'the liveness verification to2. The apparatus of claim 1 , wherein the one or more non-transitory machine readable media further comprise instructions which claim 1 , when executed by the one or more processors claim 1 , cause the one or more processors to prompt the person via text directions on the touchscreen.3. The apparatus of claim 1 , wherein the prompt is to request rotation of ...

Подробнее
Номер записи: 24
25-01-2018 дата публикации

SECURITY SYSTEM FOR FACILITY ACCESS CONTROL

Номер: US20180025242A1
Автор: Chandraker Manmohan, Lau Eric, Wong Elsa, YU Xiang
Принадлежит:

A facility access control system and corresponding method are provided. The facility access control system includes a camera configured to capture an input image of a subject attempting to enter or exit a restricted facility. The facility access control system further includes a memory storing a deep learning model configured to perform multi-task learning for a pair of tasks including a liveness detection task and a face recognition task. The facility access control system also includes a processor configured to apply the deep learning model to the input image to recognize an identity of the subject in the input image regarding being authorized for access to the facility and a liveness of the subject. The liveness detection task is configured to evaluate a plurality of different distracter modalities corresponding to different physical spoofing materials to prevent face spoofing for the face recognition task. 1. A facility access control system , comprising:a camera configured to capture an input image of a subject attempting to enter or exit a restricted facility;a memory storing a deep learning model configured to perform multi-task learning for a pair of tasks including a liveness detection task and a face recognition task; anda processor configured to apply the deep learning model to the input image to recognize an identity of the subject in the input image regarding being authorized for access to the facility and a liveness of the subject, and wherein the liveness detection task is configured to evaluate a plurality of different distracter modalities corresponding to different physical spoofing materials to prevent face spoofing for the face recognition task.2. The facility access control system of claim 1 , wherein the processor is configured to selectively permit or restrict access to the facility claim 1 , responsive to results of the liveness detection task and the face recognition task.3. The facility access control system of claim 1 , wherein the ...

Подробнее
Номер записи: 25
25-01-2018 дата публикации

LOGIN ACCESS CONTROL FOR SECURE/PRIVATE DATA

Номер: US20180025243A1
Автор: Chandraker Manmohan, Lau Eric, Wong Elsa, YU Xiang
Принадлежит:

A login access control system is provided. The login access control system includes a camera configured to capture an input image of a subject purported to be a person and attempting to login to a system to access secure data. The login access control system further includes a memory storing a deep learning model configured to perform multi-task learning for a pair of tasks including a liveness detection task and a face recognition task. The login access control system also includes a processor configured to apply the deep learning model to the input image to recognize an identity of the subject in the input image regarding being authorized for access to the secure data and a liveness of the subject. The liveness detection task is configured to evaluate a plurality of different distractor modalities corresponding to different physical spoofing materials to prevent face spoofing for the face recognition task. 1. A login access control system , comprising:a camera configured to capture an input image of a subject purported to be a person and attempting to login to a system to access secure data;a memory storing a deep learning model configured to perform multi-task learning for a pair of tasks including a liveness detection task and a face recognition task; anda processor configured to apply the deep learning model to the input image to recognize an identity of the subject in the input image regarding being authorized for access to the secure data and a liveness of the subject, and wherein the liveness detection task is configured to evaluate a plurality of different distractor modalities corresponding to different physical spoofing materials to prevent face spoofing for the face recognition task.2. The login access control system of claim 1 , wherein the processor is further configured to control access to the secure data claim 1 , responsive to results of the liveness detection task and the face recognition task.3. The login access control system of claim 1 , ...

Подробнее
Номер записи: 26
25-01-2018 дата публикации

Systems And Methods Of Biometric Analysis To Determine Lack Of Three-Dimensionality

Номер: US20180025244A1
Автор: Ackerman David Alan, Bohl Andrew James, Martin Christopher Robert
Принадлежит: Princeton Identity, Inc.

Exemplary embodiments are directed to biometric analysis systems generally including one or more illumination sources, a camera, and an analysis module. The illumination sources are configured to illuminate at least a portion of a face of a subject. The camera is configured to capture one or more images of the subject during illumination of the face of the subject. The analysis module is configured to analyze the one or more images captured by the camera to determine an indication of liveliness of the subject and prevent spoofing. 1. A biometric analysis system , comprising:an illumination source configured to illuminate an iris of a subject and at least a portion of a surrounding eye, ocular region and face of the subject;a camera configured to capture one or more images of the subject during illumination of the subject with the illumination source, the one or more images displaying reflected light from the iris and the portion of the surrounding ocular region and face of the subject; andan analysis module configured to receive as input the one or more images, analyze the reflected light in the one or more images, and determine a lack of three-dimensionality of the subject based on the reflected light in the one or more images of the portion of the surrounding ocular region and face of the subject.2. The biometric analysis system of claim 1 , wherein the illumination source is a near infrared illumination source.3. The biometric analysis system of claim 1 , wherein illumination of the portion of the surrounding ocular region and face of the subject creates a pattern of illumination.4. The biometric analysis system of claim 1 , wherein the analysis module is configured to determine the lack of three-dimensionality of the subject based on a detection of a uniform pattern of illumination distribution of the subject.5. The biometric analysis system of claim 1 , wherein the analysis module is configured to determine whether the lack of three-dimensionality is ...

Подробнее
Номер записи: 27
10-02-2022 дата публикации

BIOMETRIC AUTHENTICATION SYSTEM, BIOMETRIC AUTHENTICATION METHOD, AND PROGRAM

Номер: US20220043895A1
Автор: MATSUDA Yusuke, Miura Naoto, Miyatake Takafumi, Nagasaka Akio, NAKAZAKI Keiichiro, NONOMURA Yo
Принадлежит: Hitachi, Ltd.

A biometric authentication system, including an image input unit configured to obtain an image by imaging a living body, a storage unit configured to store registration information relating to a plurality of biological features obtained from a biological region of an image of each person, and an authentication processing unit configured to process the biological region of the image obtained by the image input unit to execute biometric authentication based on the registration information, wherein the plurality of biological features obtained from the biological region of the each person are a plurality of biological features having a low pattern correlation with one another, and wherein the authentication processing unit is configured to combine the plurality of biological features having a low pattern correlation with one another, which are obtained by processing the image, to execute the biometric authentication. 1. A biometric authentication system , comprising:an image input unit configured to obtain an image by imaging a living body;a storage unit configured to store registration information relating to a plurality of biological features obtained from a biological region of an image of each person; andan authentication processing unit configured to process the biological region of the image obtained by the image input unit to execute biometric authentication based on the registration information,wherein the plurality of biological features obtained from the biological region of the each person are a plurality of biological features having a low pattern correlation with one another, andwherein the authentication processing unit is configured to combine the plurality of biological features having a low pattern correlation with one another, which are obtained by processing the image, to execute the biometric authentication.2. The biometric authentication system according to claim 1 , wherein the living body to be imaged by the image input unit includes a finger.3. ...

Подробнее
Номер записи: 28
10-02-2022 дата публикации

METHOD FOR FINGERPRINT IDENTIFICATION, TERMINAL DEVICE AND STORAGE MEDIUM

Номер: US20220044002A1
Автор: SANG Weilin, ZHENG Jinzeng
Принадлежит: BEIJING XIAOMI MOBILE SOFTWARE CO., LTD.

A method for fingerprint identification. In the method, a radar wave is transmitted and a returned radar wave is received by using a radar sensor of the terminal device, when performing a fingerprint unlocking of the terminal device; a radar wave characteristic is acquired according to the transmitted radar wave and the received returned radar wave; in response to determining from the radar wave characteristic that the living finger is detected in the radar emission region of the radar sensor, the fingerprint sensor of the terminal device is awakened; and the fingerprint is acquired based on the awakened fingerprint sensor, and the acquired fingerprint is identified for unlocking of the terminal device. 1. A method for fingerprint identification , applied to a terminal device , comprising:transmitting a radar wave and receiving a returned radar wave by using a radar sensor of the terminal device;acquiring a radar wave characteristic according to the transmitted radar wave and the received returned radar wave; andin response to determining from the radar wave characteristic that a living finger is detected in a radar emission region of the radar sensor, acquiring a fingerprint based on the fingerprint sensor of the terminal device, and identifying the acquired fingerprint for unlocking of the terminal device.2. The method of claim 1 , wherein claim 1 , in response to determining from the radar wave characteristic that the living finger is detected in the radar emission region of the radar sensor claim 1 , acquiring the fingerprint based on the fingerprint sensor of the terminal device and identifying the acquired fingerprint for unlocking comprises:in response to determining from the radar wave characteristic that the living finger is detected in the radar emission region of the radar sensor, awakening the fingerprint sensor of the terminal device; andacquiring the fingerprint based on the awakened fingerprint sensor, and identifying the acquired fingerprint for ...

Подробнее
Номер записи: 29
10-02-2022 дата публикации

Living Body Detection Method and Device

Номер: US20220044039A1
Автор: Hua Congyi, Ren Zhihao
Принадлежит:

A living body detection method and device are disclosed. Wherein the method comprises the following steps: extracting valid depth data of a target detection object from depth map data containing the target detection object; generating a depth difference histogram based on the valid depth data; and inputting the depth difference histogram into a pre-trained machine learning classifier to obtain a determination result of whether the target detection object is a living body. By adopting this method, the detection accuracy can be improved. 1. A living body detection method , comprising:extracting valid depth data of a target detection object from depth map data containing the target detection object;generating a depth difference histogram based on the valid depth data; andinputting the depth difference histogram into a pre-trained machine learning classifier to obtain a determination result of whether the target detection object is a living body.2. The method of claim 1 , wherein the step of extracting valid depth data of a target detection object from depth map data containing the target detection object comprises:extracting depth data of the target detection object from the depth map data containing the target detection object in a manner of image segmentation according to a preset depth difference range;determining whether an angle of the extracted depth data on each coordinate plane of a three-dimensional coordinate system is within a preset angle range; if this angle is within the preset angle range, taking the extracted depth data as the valid depth data of the target detection object; otherwise, determining the extracted depth data as invalid depth data of the target detection object;wherein an xy plane of the three-dimensional coordinate system is parallel to a plane where a sensor of an image capturing device for acquiring the depth map data is located, and a z-axis of the three-dimensional coordinate system is a main optical axis of the image capturing device. ...

Подробнее
Номер записи: 30
10-02-2022 дата публикации

LIVENESS TEST METHOD AND APPARATUS

Номер: US20220044040A1
Автор: CHOI Chang Kyu, HAN Jaejoon, KIM Youngsung, KWAK Youngjun, YOO Byung In
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

A processor-implemented liveness test method includes detecting a face region in a query image, the query image including a test object for a liveness test, determining a liveness test condition to be applied to the test object among at least one liveness test condition for at least one registered user registered in a registration database, determining at least one test region in the query image based on the detected face region and the determined liveness test condition, obtaining feature data of the test object from image data of the determined at least one test region using a neural network-based feature extractor, and determining a result of the liveness test based on the obtained feature data and registered feature data registered in the registration database and corresponding to the determined liveness test condition. 1. A processor-implemented liveness data registration method comprising:detecting a face region in a registration image, the registration image comprising a registration object to be registered;determining at least one candidate registration region in the registration image based on the detected face region and a current liveness test condition;obtaining feature data of the registration object from image data of the determined at least candidate registration region using a neural network-based feature extractor;determining a liveness score based on the obtained feature data; anddetermining whether to register the current liveness test condition and the obtained feature data as liveness data of the registration object based on the determined liveness score.2. The processor-implemented liveness data registration method of claim 1 , wherein the determining of the at least one candidate registration region comprises determining either one or both of a first candidate registration region and a second candidate registration region based on the detected face region and the current liveness test condition.3. The processor-implemented liveness data ...

Подробнее
Номер записи: 31
23-01-2020 дата публикации

Biometrics authentication device and method

Номер: US20200026833A1
Автор: Gin-Chung Wang
Принадлежит: Individual

A biometrics authentication device has an object scanner, an object authentication device, a pulse waveform generation device, a pulse waveform authentication device and a determination device. The object scanner receives at least one of object images of a living being. The object authentication device performs an object authentication according to the at least one object image. The pulse waveform generation device receives the object images to generate a pulse waveform of the living being according to the object images and timestamps at which the object images are captured. The pulse waveform authentication device performs a pulse waveform authentication device according to the pulse waveform. The determination device determines a biometrics authentication result according to results of the object waveform authentication and the pulse waveform authentication.

Подробнее
Номер записи: 32
23-01-2020 дата публикации

User identity verification method, apparatus and system

Номер: US20200026940A1
Автор: Jidong Chen, Le He, Liang Li, Mian HUANG, Wenbo Yang, Yukun TUO
Принадлежит: Alibaba Group Holding Ltd

This specification discloses a user identity verification method, apparatus, and system, relating to the field of information technology. The method comprises: receiving a facial image and one or more eye-print pair images corresponding to an identity verification object from a client, wherein a number of the one or more eye-print pair images corresponds to a number of eye-print collection steps, comparing the facial image to a preset facial image and comparing the one or more eye-print pair images to preset eye-print templates, and sending successful identity verification information to a client when comparison results for the facial image and the one or more eye-print pair images meet preset conditions.

Подробнее
Номер записи: 33
28-01-2021 дата публикации

SPOOF DETECTION BY GENERATING 3D POINT CLOUDS FROM CAPTURED IMAGE FRAMES

Номер: US20210027080A1
Автор: Derakhshani Reza R., Storm Gregory Lee
Принадлежит: ALIBABA GROUP HOLDING LIMITED

A method includes receiving a first sequence of images of a first subject captured over a time period in which relative locations of the image acquisition device with respect to the first subject varies. A first image and a second image are selected as representing a first and second relative locations, respectively, of the image acquisition device with respect to the first subject. A first set of points and a second set of points are generated in a three-dimensional space, using the first image and the second image as a stereo pair, the first and second sets of points representing the first subject, and a background, respectively. It is determined that a difference between a first depth associated with the first set of points, and a second depth associated with the second set of points satisfies a threshold condition, and in response, access to a secure system is prevented. 1. A method comprising:receiving, at one or more processing devices, a first sequence of images of a first subject captured by an image acquisition device over a time period in which relative locations of the image acquisition device with respect to the first subject varies;selecting, by the one or more processing devices, a first image and a second image from the first sequence of images, wherein the first image represents a first relative location of the image acquisition device with respect to the first subject, and the second image represents a second relative location, different from the first relative location, of the image acquisition device with respect to the first subject;generating, by the one or more processing devices and using the first image and the second image as a stereo pair, (i) a first set of points in a three-dimensional space, the first set of points representing the first subject, and (ii) a second set of points in the three dimensional space, the second set of points representing a background depicted in the first and second images;determining that a first difference ...

Подробнее
Номер записи: 34
28-01-2021 дата публикации

METHOD AND DEVICE FOR LIVENESS DETECTION, AND STORAGE MEDIUM

Номер: US20210027081A1
Автор: GUO Xiaoyang, LIANG Mingyang, Wu Liwei, Yang Kai, YANG Wukui, Zhang Rui
Принадлежит:

The embodiments disclose a method and device for liveness detection and a computer-readable storage medium. The method includes that: a first image collected by a first image sensor of a binocular camera is acquired, and a second image collected by a second image sensor of the binocular camera is acquired; binocular matching processing is performed on the first image and the second image to obtain parallax information of the first image and the second image; and a liveness detection result is obtained according to the parallax information. 1. A method for liveness detection , comprising:acquiring a first image collected by a first image sensor of a binocular camera, and acquiring a second image collected by a second image sensor of the binocular camera;performing binocular matching processing on the first image and the second image to obtain disparity information between the first image and the second image; andobtaining a liveness detection result according to the disparity information.2. The method of claim 1 , wherein a modality of the first image is different from a modality of the second image.3. The method of claim 1 , wherein performing binocular matching processing on the first image and the second image to obtain the disparity information between the first image and the second image comprises:acquiring a first target region image of a target object from the first image, and acquiring a second target region image of the target object from the second image; andobtaining the disparity information between the first image and the second image based on the first target region image and the second target region image.4. (canceled)5. The method of claim 3 , wherein obtaining the disparity information between the first image and the second image based on the first target region image and the second target region image comprises:performing feature extraction processing on the first target region image to obtain first feature data, and performing feature extraction ...

Подробнее
Номер записи: 35
01-02-2018 дата публикации

Method And System For Acquiring And Analysing Fingerprints With Fraud Detection

Номер: US20180032827A1
Автор: BOUTET Jerome, Fourre Joel-Yann
Принадлежит:

A method and system for acquiring and analyzing fingerprints with fraud detection in which an image of a fingerprint of an object is formed and the object is irradiated by means of an energizing beam. A fluorescence emitted by the object in response to the energizing beam is analyzed and a validity criterion is established from the analysis of fluorescence and making it possible to discriminate biological tissue from other objects is verified. A region of interest, capable of characterizing the biological tissues is selected on the fingerprint image, where the region of interest defines a useful observation area on the object by correspondence, and the validity criterion is established from measurements of fluorescence intensity relative to the observation area only. 1. A method of acquiring and analyzing prints with spoof detection , the method comprising:forming a print image of an object facing a transparent reception surface, where the print image is representative of micro-structure of a visible surface of the object,irradiating the object through the transparent reception surface with an excitation beam according to an excitation spectral band,analyzing a fluorescence signal emitted by the object in response to the excitation beam, according to a fluorescence spectral band,verifying a validity criterion enabling biological tissues to be discriminated from other objects, where the validity criterion is established on the basis of the fluorescence analysis,wherein the analyzing the fluorescence signal comprises acquiring fluorescence intensity measurements over the whole visible surface of the object and forming a fluorescence image of the object, andwherein the method further comprises selecting in the print image a region of interest suitable for characterizing the biological tissues, which region of interest defines through correspondence, on the object, a corresponding useful observation zone, andthe validity criterion is established solely on the basis of ...

Подробнее
Номер записи: 36
01-02-2018 дата публикации

FACE LIVENESS DETECTION METHOD, TERMINAL, SERVER AND STORAGE MEDIUM

Номер: US20180032828A1
Автор: HUANG Feiyue, LI Jilin, WANG Chengjie, Wu Yongjian
Принадлежит:

A face liveness detection method includes outputting a prompt to complete one or more specified actions in sequence within a specified time period, obtaining a face video, detecting a reference face image frame in the face video using a face detection method, locating a facial keypoint in the reference face image frame, tracking the facial keypoint in one or more subsequent face image frames, determining a state parameter of one of the one or more specified actions using a continuity analysis method according to the facial keypoint, and determining whether the one of the one or more specified actions is completed according to a continuity of the state parameter. 1. A face liveness detection method comprising:outputting a prompt to complete one or more specified actions in sequence within a specified time period;obtaining a face video;detecting a reference face image frame in the face video using a face detection method;locating a facial keypoint in the reference face image frame;tracking the facial keypoint in one or more subsequent face image frames;determining a state parameter of one of the one or more specified actions using a continuity analysis method according to the facial keypoint; anddetermining, according to a continuity of the state parameter, whether the one of the one or more specified actions is completed.2. The method according to claim 1 , further comprising:determining that a live face exists if it is determined that the one or more specified actions is completed in sequence within the specified time period; ordetermining that no live face exists if it is determined that the one or more specified actions is not completed in sequence within the specified time period.3. The method according to claim 1 , wherein:detecting the reference face image frame using the face detection method includes detecting the reference face image frame using a face detection method based on deep convolutional neural network (CNN), andlocating the facial keypoint in the ...

Подробнее
Номер записи: 37
17-02-2022 дата публикации

FACE IMAGE QUALITY RECOGNITION METHODS AND APPARATUSES

Номер: US20220051010A1
Автор: Li Jianshu
Принадлежит: Alipay Labs (Singapore) Pte. Ltd.

Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for identity document face image quality recognition. One computer-implemented method includes pairing, for each user of a plurality of users and to form a pair of face images, an identity document (ID) face image and a live face image. For each pair of face images and based on a face similarity between the ID face image and the live face image, a similarity score for the ID face image is generated. Based on ID face images and similarity scores corresponding to the ID face images, a model for ID face image quality recognition is trained. 1. A computer-implemented method for identity document face image quality recognition , comprising:pairing, for each user of a plurality of users and to form a pair of face images, an identity document (ID) face image and a live face image;generating, for each pair of face images and based on a face similarity between the ID face image and the live face image, a similarity score for the ID face image; andtraining, based on ID face images and similarity scores corresponding to the ID face images, a model for ID face image quality recognition.2. The computer-implemented method of claim 1 , wherein training a model for ID face image quality recognition comprises training a multiclass classifier.3. The computer-implemented method of claim 2 , wherein training a multiclass classifier comprises:dividing the similarity scores into N labels of ID face image quality;assigning an ID face image with a corresponding label; andtraining a multiclass classifier of N classes based on the ID face images and corresponding labels of the ID face images.4. The computer-implemented method of claim 3 , wherein dividing the similarity scores into N labels is percentile-based.5. The computer-implemented method of claim 1 , wherein training a model for ID face image quality recognition comprises training a regression model.6. The computer-implemented method of ...

Подробнее
Номер записи: 38
01-02-2018 дата публикации

Systems and methods of illumination control for biometric capture and liveness detection

Номер: US20180034812A1
Автор: A. K. M. Mahbubur RAHMAN
Принадлежит: Eyelock LLC

The present disclosure describes illumination control for biometric capture with liveness detection. A first near infra-red (NIR) illuminator illuminates, during a first time slice, a right eye and/or a left eye, and may be located within a predetermined distance from a sensor. A second NIR illuminator may illuminate, during a second time slice, the right eye and/or left eye. The second NIR illuminator may be located at a second distance larger than the predetermined distance. A third NIR illuminator may illuminate, during a third time slice, the right eye and/or left eye, and may be located at a third distance that is larger than the predetermined distance. The sensor may be used to detect a red-eye effect during the first time slice, and capture an image of the right eye and/or left eye during the second time slice, and a second image during the third time slice.

Подробнее
Номер записи: 39
31-01-2019 дата публикации

LIVENESS TEST METHOD AND APPARATUS

Номер: US20190034708A1
Автор: CHOI Chang Kyu, HAN Jaejoon, Kim Jungbae, KWAK Youngjun, Lee Changkyo, SON Jinwoo, YOO Byungin
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

A liveness test method and apparatus is disclosed. A processor implemented liveness test method includes extracting an interest region of an object from a portion of the object in an input image, performing a liveness test on the object using a neural network model-based liveness test model, the liveness test model using image information of the interest region as provided first input image information to the liveness test model and determining liveness based at least on extracted texture information from the information of the interest region by the liveness test model, and indicating a result of the liveness test. 1. A processor implemented liveness test method , the liveness test method comprising:extracting an interest region of an object from a portion of the object in an input image;performing a liveness test on the object using a neural network model-based liveness test model for each of one or more images of the object respectively input to the liveness test model,wherein image information of the interest region is provided, as first input image information, to a first input layer of the liveness test model,wherein image information of the input image or image information of the portion of the object is provided, as second input image information, to a second input layer of the liveness test model, andwherein the performing of the liveness test further includes determining, by the liveness test model, liveness of the object based at least on extracted texture information from the first input image information by the liveness test model and information extracted from the second input image information by the liveness test model; andindicating a result of the liveness test.2. The method of claim 1 , wherein the extracting of the interest region comprises:extracting a select portion including a pupil region as the interest region from the portion of the object in the input image.3. The method of claim 2 ,wherein the liveness test model uses the image ...

Подробнее
Номер записи: 40
31-01-2019 дата публикации

SYSTEM AND METHOD FOR IDENTIFYING RE-PHOTOGRAPHED IMAGES

Номер: US20190034746A1
Автор: Feng Xuetao, Wang Yan
Принадлежит: ALIBABA GROUP HOLDING LIMITED

One embodiment facilitates identification of re-photographed images. During operation, the system obtains a sequence of video frames of a target object. The system selects a frame with an acceptable level of quality. The system obtains, from the selected frame, a first image and a second image associated with the target object, wherein at least one of a zoom ratio property and a size property is different between the first image and the second image. The system inputs the first image and the second image to at least a first neural network to obtain scores for the first image and the second image, wherein a respective score indicates a probability that the corresponding image is re-photographed, wherein a re-photographed image is obtained by photographing or recording an image of the target object. The system indicates the selected frame as re-photographed based on the obtained probabilities. 1. A computer-implemented method for facilitating identification of re-photographed images , the method comprising:obtaining, by a computing device, a sequence of video frames of a target object;selecting a frame with an acceptable level of quality;obtaining, from the selected frame, a first image and a second image associated with the target object, wherein at least one of a zoom ratio property and a size property is different between the first image and the second image;inputting the first image and the second image to at least a first neural network to obtain scores for the first image and the second image, wherein a respective score indicates a probability that the corresponding image is re-photographed, wherein a re-photographed image is obtained by photographing or recording an image of the target object; andindicating the selected frame as re-photographed based on the obtained probabilities for the first image and the second image.2. The method of claim 1 , wherein the first image and the second image are one or more of:an image of a first size selected from a first area ...

Подробнее
Номер записи: 41
04-02-2021 дата публикации

IRIS LIVENESS DETECTION FOR MOBILE DEVICES

Номер: US20210034864A1
Автор: THAVALENGAL Shejin
Принадлежит: FotoNation Limited

An approach for an iris liveness detection is provided. A plurality of image pairs is acquired using one or more image sensors of a mobile device. A particular image pair is selected from the plurality of image pairs, and a hyperspectral image is generated for the particular image pair. Based on, at least in part, the hyperspectral image, a particular feature vector for the eye-iris region depicted in the particular image pair is generated, and one or more trained model feature vectors generated for facial features of a particular user of the device are retrieved. Based on, at least in part, the particular feature vector and the one or more trained model feature vectors, a distance metric is determined and compared with a threshold. If the distance metric exceeds the threshold, then a first message indicating that the plurality of image pairs fails to depict the particular user is generated. It is also determined whether at least one characteristic, of one or more characteristics determined for NIR images, changes from image-to-image by at least a second threshold. If so, then a second message is generated to indicate that the plurality of image pairs depicts the particular user of a mobile device. The second message may also indicate that an authentication of an owner to the mobile device was successful. Otherwise, a third message is generated to indicate that a presentation attack on the mobile device is in progress. 120-. (canceled)21. An electronic device comprising:a first image sensor;a second image sensor;one or more processors; and generating, at a first time and using the first image sensor, first image data representing an eye;', 'determining, based at least in part on the first image data, a first characteristic associated with the eye;', 'generating, at a second time and using the first image sensor, second image data representing the eye;', 'determining, based at least in part on the second image data, a second characteristic associated with the eye;', ...

Подробнее
Номер записи: 42
04-02-2021 дата публикации

MATCHER BASED ANTI-SPOOF SYSTEM

Номер: US20210034895A1
Автор: GORE Shounak Uday, Gu Jin, John Archibald Fitzgerald, Schneider John, STOIANOV Alexei
Принадлежит:

Techniques for improving the integrity and performance of biometric security processes on data processing devices are provided. An example of a method of determining a liveness of a biometric input according to the disclosure includes obtaining inquiry image information, obtaining enrollment image information, determining alignment information based on the inquiry image information and the enrollment image information, determining an overlap area based on the alignment information, determining anti-spoofing features based on the overlap area within the inquiry image information and the enrollment image information, and outputting a liveness score based on the anti-spoofing features. 1. A method of determining a liveness of a biometric input , comprising:obtaining inquiry image information;obtaining enrollment image information;determining alignment information based on the inquiry image information and the enrollment image information;determining an overlap area based on the alignment information;determining anti-spoofing features based on the overlap area within the inquiry image information and the enrollment image information; andoutputting a liveness score based on the anti-spoofing features.2. The method of wherein the inquiry image information and the enrollment image information are time-based signals.3. The method of wherein obtaining the inquiry image information includes obtaining feature vectors derived from an inquiry image.4. The method of wherein obtaining the enrollment image information includes obtaining a user identification and retrieving an enrollment template from an enrollment database based on the user identification.5. The method of further comprising determining a matching score based on the inquiry image information and the enrollment image information.6. The method of wherein the anti-spoofing features are obtained from features in the overlap area of both the inquiry image information and the enrollment image information claim 5 , wherein ...

Подробнее
Номер записи: 43
04-02-2021 дата публикации

LIVING BODY DETECTION METHOD, APPARATUS AND DEVICE

Номер: US20210034896A1
Автор: Wang Hai, Wu Peng, ZHAO Hongwei, Zhu Zhu
Принадлежит:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for liveness detection are provided. One of methods includes: displaying an image to a user, and capturing a face image of the user while displaying the image to the user; determining an eye image of an eye of the user based on the face image; extracting a to-be-verified image from the eye image of the user, wherein the to-be-verified image is reflection of the displayed image in the eye of the user; comparing the displayed image with the to-be-verified image to determine whether the to-be-verified image matches the displayed image; and performing liveness detection on the user based on a result of comparison. 1. A liveness detection method , comprising:sequentially displaying a plurality of images to a user; capturing a plurality of face images of the user while displaying the plurality of images to the user; determining an eye image of an eye of the user based on the face image;', 'extracting a to-be-verified image from the eye image of the user, wherein the to-be-verified image is a reflection of a corresponding one of the displayed images in the eye of the user, and', 'comparing the corresponding displayed image with the to-be-verified image to determine whether the to-be-verified image matches the corresponding displayed image;, 'for each of the captured face imagesdetermining a quantity of matches between the to-be-verified images and the corresponding displayed images; andperforming liveness detection on the user based on the quantity of matches.2. The method according to claim 1 , wherein determining the eye image of the user based on the face image comprises:determining whether the face image contains the user's face or reaches a clarity; andin response to determining that the face image contains the user's face or reaches the clarity, extracting the eye image of the user from the face image.3. The method according to claim 1 , wherein each displayed image ...

Подробнее
Номер записи: 44
09-02-2017 дата публикации

VISUAL LIVENESS DETECTION

Номер: US20170039440A1
Автор: Li Min, Liu Wen, Qin Yong, Su Zhong, Zhang Shi Lei, Zhao Shiwan
Принадлежит:

In an approach for visual liveness detection, a video-audio signal related to a speaker speaking a text is obtained. The video-audio signal is split into a video signal which records images of the speaker and an audio signal which records a speech spoken by the speaker. Then a first sequence indicating visual mouth openness is obtained from the video signal, and a second sequence indicating acoustic mouth openness is obtained based on the text and the audio signal. Synchrony between the first and second sequences is measured, and the liveness of the speaker is determined based on the synchrony. 1. A method for visual liveness detection , the method comprising:obtaining, by one or more computer processors, a video-audio signal related to a speaker speaking a text;splitting, by one or more computer processors, the video-audio signal into a video signal which records images of the speaker and an audio signal which records a speech spoken by the speaker;obtaining, by one or more computer processors, a first sequence indicating visual mouth openness from the video signal;obtaining, by one or more computer processors, a second sequence indicating acoustic mouth openness based on the text and the audio signal;measuring, by one or more computer processors, synchrony between the first sequence and the second sequence; anddetermining, by one or more computer processors, liveness of the speaker based on the synchrony.2. The method of claim 1 , wherein obtaining a first sequence comprises:sampling, by one or more computer processors, the video signal to obtain video frames;determining, by one or more computer processors, a mouth-open-status of the speaker for a video frame of the video signal; andsequencing, by one or more computer processors, the mouth-open-statuses of the video frames of the video signal in time order to generate the first sequence.3. The method of claim 1 , wherein obtaining a second sequence comprises:segmenting, by one or more computer processors, the text ...

Подробнее
Номер записи: 45
08-02-2018 дата публикации

METHOD AND APPARATUS TO IDENTIFY A LIVE FACE IMAGE USING A THERMAL RADIATION SENSOR AND A VISUAL RADIATION SENSOR

Номер: US20180039845A1
Автор: Chen Chia-Yu, CHUANG Pierce I-Jen, Hung Li-Wen, Lai Jui-Hsin
Принадлежит:

A method, system and computer program product are disclosed that comprise capturing first image data of a person's face using at least one sensor responsive in a band of infrared wavelengths and capturing second image data of the person's face using the at least one sensor responsive in a band of visible wavelengths; extracting image features in the image data and detecting face regions; applying a similarity analysis to image feature edge maps extracted from the first and the second image data; and recognizing a presence of a live face image after regions found in the first image data pass a facial features classifier. Upon recognizing the presence of the live face image, additional operations can include verifying the identity of the person as an authorized person and granting the person access to a resource. 1. A method , comprising:capturing first image data of a person's face using at least one sensor responsive in a band of infrared wavelengths and capturing second image data of the person's face using the at least one sensor responsive in a band of visible wavelengths;extracting image features in the image data and detecting face regions;applying a similarity analysis to image feature edge maps extracted from the first and the second image data; andrecognizing a presence of a live face image after regions found in the first image data pass a facial features classifier that identifies a presence of an image of a human face in the first image data.2. The method as in claim 1 , further comprising claim 1 , upon recognizing the presence of the live face image claim 1 , verifying the identity of the person as an authorized person claim 1 , and granting the person access to a resource.3. The method as in claim 1 , where the at least one sensor is comprised of a first sensor and a second sensor that are co-located in one device claim 1 , or where the at least one sensor is comprised of a first sensor that comprises part of a device and a second sensor that comprises ...

Подробнее
Номер записи: 46
11-02-2016 дата публикации

Method of host-directed illumination and system for conducting host-directed illumination

Номер: US20160044029A1
Автор: Michael Peirce, Nicolas Jacques Jean Sezille, Richard Jay Langley
Принадлежит: Daon Holdings Ltd

A method of host-directed illumination for verifying the validity of biometric data of a user is provided that includes capturing biometric data from a user with an authentication device during authentication and directing illumination of the biometric data from a host authentication system during the capturing operation. Moreover, the method includes comparing illumination characteristics of the captured biometric data against illumination characteristics expected to result from the directing operation, and determining that the user is a live user when the illumination characteristics of the captured biometric data match the illumination characteristics expected to result from the directing operation.

Подробнее
Номер записи: 47
24-02-2022 дата публикации

METHOD FOR TRANSMITTING FACE IMAGE DATA, TRANSFERRING VALUE, APPARATUS, AND ELECTRONIC DEVICE

Номер: US20220058376A1
Автор: Geng Zhijun, GUO Runzeng, WANG Shaoming, Zhou Jun
Принадлежит:

This application provides a method for transmitting face image data and transferring value, apparatuses, an electronic device, and a storage medium, which belongs to the field of network technologies. The method for transmitting face image data includes acquiring a face data stream through the sensor, and transmitting the face data stream to the first processor; performing image screening on a face image in the face data stream by the first processor to obtain at least a target face image, the target face image meeting a target condition; retrieving a target web address from the memory by the first processor; and transmitting the target face image to the target web address by the first processor. 1. A method for transmitting face image data , applicable to a camera component of a terminal , the camera component comprising a sensor , a first processor , and a memory , the memory including one of a trusted execution environment (TEE) element or a secure element (SE) , the method comprising:acquiring a face data stream through the sensor, and transmitting the face data stream to the first processor;performing image screening on a face image in the face data stream by the first processor to obtain at least a target face image, the target face image meeting a target condition;retrieving a target web address from the memory by the first processor; andtransmitting the target face image to the target web address by the first processor.2. The method according to claim 1 , wherein the performing image screening on the face image in the face data stream to obtain the target face image comprises:performing liveness detection on the face image, and determining each face image with a detection result being a living body as the target face image.3. The method according to claim 1 , wherein the performing image screening on the face image in the face data stream to obtain the target face image comprises:performing quality assessment on the face image to obtain a quality score of ...

Подробнее
Номер записи: 48
06-02-2020 дата публикации

SYSTEM AND METHOD FOR USING IMAGES TO AUTHENTICATE A USER

Номер: US20200042682A1
Автор: Douglas Lawrence, JOHNSON Clayton, Liu Yolanda
Принадлежит: Capital One Services, LLC

Systems and methods for authenticating a user, the method including receiving an image of a user of a device, identifying a first facial descriptor of the user from the received image and from previously captured images of the user, and determining a difference between the first facial descriptor from the received image and that from the previously captured images. The method further includes identifying a second facial descriptor of a non-user from the previously captured images of the user, and applying facial recognition to images stored in a plurality of second social networking profiles associated with a first social networking profile of the user to identify the second facial descriptor from the images stored in the second social networking profiles. Based on the difference and the second facial descriptor, the user may be authenticated. 120.-. (canceled)21. A computer-implemented method of authenticating a user , the method comprising:receiving an image of a user of a device;identifying at least one facial descriptor of the user from the received image;identifying at least one facial descriptor of the user from a plurality of previously captured images of the user stored in the device;determining a difference between the at least one facial descriptor from the received image and the at least one facial descriptor from the previously captured images;cross-verifying the received image against a plurality of images of the user stored in a social networking profile of the user;cross-verifying the received image against a plurality of images of the user stored in a social networking profile of a non-user, the social networking profile of the non-user being associated with the social networking profile of the user; andgenerating, based on at least the determined difference and the cross-verifications, a notification indicative of whether the user in the received image is an authorized user.22. The computer-implemented method of claim 21 , further comprising ...

Подробнее
Номер записи: 49
06-02-2020 дата публикации

SYSTEM FOR VERIFYING THE IDENTITY OF A USER

Номер: US20200042773A1
Автор: "Benkreira Abdelkader MHamed", EDWARDS Joshua, MOSSOBA Michael
Принадлежит:

A system receives an image including a live facial image of the user and an identity document including a photograph of the user. Moreover, the system calculates a facial match score by comparing facial features in the live facial image to facial features in the photograph. The system recognizes data objects and characters in the identity document using optical character recognition (OCR) and computer vision, and then identifies, based on the recognized data objects and characters, a type of the identity document. Further, the system calculates a document validity score by comparing the recognized characters and data objects to character strings and data objects known to be present in the identified type of the identity document. Additionally, the system determines and outputs the user's identity verification status based on comparing the facial match score to a facial match threshold and comparing the document validity score to a document validity threshold. 1. A method , implemented using a computer , for verifying an identity of a user , the method comprising:receiving an image from a camera of an automated teller machine (ATM), the image including a live facial image of the user holding an identity document that includes a photograph of the user; calculating a facial match score by comparing facial features in the live facial image to facial features in the photograph;', 'recognizing data objects and characters in the identity document by performing optical character recognition (OCR) and computer vision tasks;', 'identifying, based on the recognized data objects and parsing the recognized characters, a type of the identity document;', 'calculating a document validity score by comparing the recognized characters and recognized data objects to character strings and data objects known to be present in the identified type of the identity document; and', 'determining, based on comparing the facial match score to a predetermined facial match threshold and comparing ...

Подробнее
Номер записи: 50
18-02-2021 дата публикации

SYSTEMS AND METHODS FOR FACIAL LIVENESS DETECTION

Номер: US20210049391A1
Автор: Bi Ning, CHENG Ke-Li, FISCHLER Matthew, Qi Yingyong, Sarkis Michel Adib, Zou Xuan
Принадлежит:

A method performed by an electronic device is described. The method includes receiving an image. The image depicts a face. The method also includes detecting at least one facial landmark of the face in the image. The method further includes receiving a depth image of the face and determining at least one landmark depth by mapping the at least one facial landmark to the depth image. The method also includes determining a plurality of scales of depth image pixels based on the at least one landmark depth and determining a scale smoothness measure for each of the plurality of scales of depth image pixels. The method additionally includes determining facial liveness based on at least two of the scale smoothness measures. Determining the facial liveness may be based on a depth-adaptive smoothness threshold and/or may be based on a natural face size criterion. 1. A method performed by an electronic device , comprising:receiving an image, wherein the image depicts a face;detecting at least one facial landmark of the face in the image;receiving a depth image of the face;determining at least one landmark depth by mapping the at least one facial landmark to the depth image;determining a plurality of scales of depth image pixels based on the at least one landmark depth;determining a scale smoothness measure for each of the plurality of scales of depth image pixels; anddetermining facial liveness based on at least two of the scale smoothness measures.2. The method of claim 1 , wherein determining the plurality of scales is based on an inverse relationship between the at least one landmark depth and the plurality of scales.3. The method of claim 1 , wherein determining the scale smoothness measures comprises applying Laplacian filtering for each of the plurality of scales of the depth image pixels.4. The method of claim 1 , further comprising determining a smoothness measure based on at least two of the scale smoothness measures claim 1 , wherein determining the facial liveness ...

Подробнее
Номер записи: 51
16-02-2017 дата публикации

LIVENESS DETECTION

Номер: US20170046583A1
Автор: Khan Usman Mahmood, LOUGHLIN-MCHUGH Eleanor Simone Frederika, Paraskevas Georgios, Rodriguez Francisco Angel Garcia, Tremoulheac Benjamin Robert
Принадлежит:

A liveness detection system comprises a controller, a video input, a feature recognition module, and a liveness detection module. The controller is configured to control an output device to provide randomized outputs to an entity over an interval of time. The video input is configured to receive a moving image of the entity captured by a camera over the interval of time. The feature recognition module is configured to process the moving image to detect at least one human feature of the entity. The liveness detection module is configured to compare with the randomized outputs a behaviour exhibited by the detected human feature over the interval of time to determine whether the behaviour is an expected reaction to the randomized outputs, thereby determining whether the entity is a living being. 1. A liveness detection system comprising:a controller configured to control an output device to provide randomized outputs to an entity over an interval of time;a video input configured to receive a moving image of the entity captured by a camera over the interval of time;a feature recognition module configured to process the moving image to detect at least one human feature of the entity; anda liveness detection module configured to compare with the randomized outputs a behaviour exhibited by the detected human feature over the interval of time to determine whether the behaviour is an expected reaction to the randomized outputs, thereby determining whether the entity is a living being.2. A liveness detection system according to claim 1 , wherein the human feature that the feature recognition module is configured to detect is an eye of the entity.3. A liveness detection system according to claim 2 , wherein providing the randomized outputs comprises controlling the output device to emit at least one light pulse having a randomized timing within the moving image claim 2 , and the expected reaction is an expected pupillary response to the at least one light pulses.4. A liveness ...

Подробнее
Номер записи: 52
15-02-2018 дата публикации

METHODS AND SYSTEMS FOR ENHANCING USER LIVENESS DETECTION

Номер: US20180046852A1
Автор: Ionita Mircea
Принадлежит:

A method for enhancing user liveness detection is provided that includes calculating, by a computing device, parameters for each frame in a video of captured face biometric data. Each parameter results from movement of at least one of the computing device and the biometric data during capture of the biometric data. The method also includes creating a signal for each parameter and calculating a similarity score. The similarity score indicates the similarity between the signals. Moreover, the method includes determining the user is live when the similarity score is at least equal to a threshold score. 1. A method for enhancing user liveness detection comprising:calculating, by a computing device, parameters for frames included in a video of captured face biometric data, each parameter resulting from movement of at least one of the computing device and the biometric data during capture of the biometric data;creating a signal for each parameter;calculating a similarity score, the similarity score indicating the similarity between the signals; anddetermining the user is live when the similarity score is at least equal to a threshold score.2. A method for enhancing user liveness detection in accordance with claim 1 , said calculating parameters step further comprising calculating claim 1 , for each frame claim 1 , an angle of light illuminating the biometric data.3. A method for enhancing user liveness detection in accordance with claim 2 , said calculating parameters step further comprising calculating a second angle for each frame claim 2 , the second angle being between a plane defined by a front face of the computing device and a vertical axis.4. A method for enhancing user liveness detection in accordance with claim 1 , said calculating parameters step further comprising:calculating a perpendicular distance for each point of interest within a field of view of the computing device; andcalculating an angle for each frame, the angle being between a plane defined by a ...

Подробнее
Номер записи: 53
15-02-2018 дата публикации

METHODS AND SYSTEMS FOR DETERMINING USER LIVENESS AND VERIFYING USER IDENTITIES

Номер: US20180046853A1
Автор: Ionita Mircea
Принадлежит:

A method for verifying the identity of a user is provided that includes generating, by a computing device, a parameter for each processed frame in a video of biometric data captured from a user. The parameter results from movement of the computing device during capture of the biometric data. Moreover, the method includes generating a signal for the parameter and calculating a confidence score based on the generated signal and a classification model specific to the user. The classification model is generated from other signals generated for the parameter. Furthermore, the method includes verifying the identity of the user as true when the confidence score is at least equal to a threshold score. 1. A method for verifying the identity of a user comprising:processing frames extracted from a video of biometric data captured from a user;generating, by a computing device, a parameter for each processed frame, the parameter resulting from movement of the computing device during capture of the biometric data;identifying processed frames captured at different values of the parameter, the different values being based on incremental changes in the parameter;generating a biometric template for each identified frame;comparing each biometric template against a corresponding user record biometric template and calculating a matching score for each comparison, the user record biometric templates being generated from biometric data captured at the different parameter values; andverifying the identity of the user as true based on the matching scores.2. A method for verifying the identity of a user in accordance with claim 1 , said verifying step comprising:comparing each matching score against a threshold score; andverifying the identity of the user as true when each matching score is at least equal to the threshold score.3. A method for verifying the identity of a user in accordance with claim 1 , said verifying step comprising:fusing the matching scores into a final matching score; ...

Подробнее
Номер записи: 54
15-02-2018 дата публикации

Methods and systems for enhancing user liveness detection

Номер: US20180046871A1
Автор: Mircea Ionita
Принадлежит: Individual

A method for enhancing user liveness detection is provided that includes calculating, by a computing device, a first angle and a second angle for each frame in a video of captured face biometric data. The first angle is between a plane defined by a front face of the terminal device and a vertical axis, and the second angle is between the plane defined by the front face of the terminal device and a plane defined by the face of the user. Moreover, the method includes creating a first signal from the first angles and a second signal from the second angles, calculating a similarity score between the first and second signals, and determining the user is live when the similarity score is at least equal to a threshold score.

Подробнее
Номер записи: 55
06-02-2020 дата публикации

Information Processing Method, Information Processing Device, and Computer-Readable Non-Transitory Storage Medium Storing Program

Номер: US20200045226A1
Автор: Arisada Hiroaki, Lertsumruaypun Kanwipa
Принадлежит:

Provided is a technique capable of guaranteeing that an image submitted online during identity verification is an image photographed on the site. An information processing method executed by an information processing device including a display unit includes displaying, on the display unit, an image of a photographing region output by a photographing device, displaying, in the photographing region displayed on the display unit, a photographing guide indicating a position of an identity verification document in the photographing region and a holding method of the identity verification document, the photographing guide being selected based on a predetermined selection logic, and causing the photographing device to photograph the image of the photographing region. 1. An information processing method executed by an information processing device including a display device , a processor of the information processing device configured to:display, on the display device, an image of a photographing region output by a photographing device;display, in the photographing region displayed on the display device, a photographing guide indicating a position of an identity verification document in the photographing region and a holding method of the identity verification document, the photographing guide being selected based on a predetermined selection logic; andcause the photographing device to photograph the image of the photographing region.2. The information processing method according to claim 1 , wherein the photographing guide includes a photographing guide indicating a position where a finger of a user and the identity verification document are in contact or a photographing guide indicating a direction of a hand of the user and a position of the identity verification document in the hand.3. The information processing method according to claim 1 , wherein claim 1 , in the displaying the photographing guide claim 1 , the photographing guide is selected according to an ...

Подробнее
Номер записи: 56
03-03-2022 дата публикации

Method and System for Authenticating an Occupant Within an Interior of a Vehicle

Номер: US20220067135A1
Автор: BARTH Alexander, Welk Douglas L.
Принадлежит:

A method is provided for authenticating an occupant within an interior of a vehicle. The vehicle includes a camera which is configured to monitor the interior of the vehicle, and a processing device being configured to process image or video data provided by the camera. Characteristic features are determined being visible via the camera, and authenticating image or video data are captured via the camera while an occupant is present within the interior of the vehicle. Via the processing device, face recognition and liveliness check are performed for the occupant based on the authenticating image or video data, and an identification degree of the characteristic features is determined within the authenticating image or video data. Based on the face recognition, the liveliness check and the identification degree it is determined whether an authentication of the occupant is to be accepted. 1. A method , comprising:generating, with a camera, image or video data of an interior of a vehicle;determining characteristic features that are visible via the camera; and capturing, from the image or video data generated by the camera, an authenticating image or video data that indicates a presence of the occupant within the interior of the vehicle;', 'performing, by a processing unit, based on the authenticating image or video data, a face recognition and a liveliness check for the occupant;', 'determining, within the authenticating image or video data, an identification degree of the characteristic features; and', 'determining whether to authenticate the occupant based on the face recognition, the liveliness check, and the identification degree of the characteristic features., 'authenticating an occupant in the interior of the vehicle by2. The method of claim 1 , wherein determining the characteristic features comprises:capturing, via the camera, background image or video data without any occupants present within the interior of the vehicle; andselecting, from the background image ...

Подробнее
Номер записи: 57
03-03-2022 дата публикации

FACE RECOGNITION METHOD AND EDGE DEVICE

Номер: US20220067349A1
Автор: Kuan Yu-Kai, Tsai Yu-Che
Принадлежит:

A face recognition method for an edge device is provided. Firstly, a recognition data is received from a computing device through a wireless network. Then, a trained model is retrieved from the recognition data. Then, the trained model is stored. Then, a face detection operation is performed to acquire a face image and a face temperature of a detected face. When the face temperature is within a human body temperature range and the face image complies with the trained model, the edge device confirms that the detected face is a face of a real person and the real person is a known user. 1. A face recognition method for an edge device , the face recognition method comprising steps of:receiving a recognition data from a computing device through a wireless network;retrieving a trained model from the recognition data;storing the trained model;performing a face detection operation to acquire a face image and a face temperature of a detected face; andwhen the face temperature is within a human body temperature range and the face image complies with the trained model, confirming that the detected face is a face of a real person and the real person is a known user.2. The face recognition method according to claim 1 , wherein the human body temperature range is between 35 degrees Celsius and 42 degrees Celsius.3. The face recognition method according to claim 1 , wherein the computing device previously performs a trained model establishing process claim 1 , and the trained model establishing process comprises steps of:inputting a trained image into the computing device;performing a deep learning process on the trained image;extracting at least one facial feature of the face image; andperforming a face recognition operation on the facial feature of the face image, so that the trained model is established.4. The face recognition method according to claim 3 , wherein the trained model is encrypted as an encrypted recognition data by the computing device claim 3 , and the encrypted ...

Подробнее
Номер записи: 58
03-03-2022 дата публикации

METHODS AND DEVICES FOR FACE ANTI-SPOOFING

Номер: US20220067413A1
Автор: Xu Yan
Принадлежит: Alipay Labs (Singapore) Pte. Ltd.

Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for face anti-spoofing. One computer-implemented method includes receiving, by a server and from a user device, a plurality of images of a user face, each of the plurality of images corresponding to a facial expression performed by a user in response to each interaction challenge of a plurality of interaction challenges. The plurality of images are concatenated into a concatenated image. A convolutional neural network (CNN) classifier is used to obtain a confidence score for the concatenated image. A liveness of the user face is determined based on a comparison of the confidence score and a threshold value. 1. A computer-implemented method for face anti-spoofing , comprising:receiving, by a server and from a user device, a plurality of images of a user face, each of the plurality of images corresponding to a facial expression performed by a user in response to each interaction challenge of a plurality of interaction challenges;concatenating the plurality of images into a concatenated image;using a convolutional neural network (CNN) classifier to obtain a confidence score for the concatenated image; anddetermining liveness of the user face based on a comparison of the confidence score and a threshold value.2. The computer-implemented method of claim 1 , wherein each interaction challenge of the plurality of interaction challenges is randomly selected from an interaction challenge library.3. The computer-implemented method of claim 1 , wherein each interaction challenge of the plurality of interaction challenges requires at least a start expression and an end expression of the user face claim 1 , and wherein the facial expression is the end expression of the user face.4. The computer-implemented method of claim 2 , further comprising:building up the interaction challenge library.5. The computer-implemented method of claim 2 , wherein the interaction challenge library ...

Подробнее
Номер записи: 59
25-02-2016 дата публикации

METHODS FOR PERFORMING BIOMETRIC RECOGNITION OF A HUMAN EYE AND CORROBORATION OF SAME

Номер: US20160055387A1
Автор: Hanna Keith J., Hoyos Hector T.
Принадлежит:

A method of biometric recognition is provided. Multiple images of the face or other non-iris image and iris of an individual are acquired. If the multiple images are determined to form an expected sequence of images, the face and iris images are associated together. A single camera preferably acquires both the iris and face images by changing at least one of the zoom, position, or dynamic range of the camera. The dynamic range can be adjusted by at least one of adjusting the gain settings of the camera, adjusting the exposure time, and/or adjusting the illuminator brightness. The expected sequence determination can be made by determining if the accumulated motion vectors of the multiple images is consistent with an expected set of motion vectors and/or ensuring that the iris remains in the field of view of all of the multiple images. 120-. (canceled)21. A method of biometric acquisition , comprising:acquiring, by a first sensor, an image of a face;acquiring, by a second sensor, an image of a corresponding iris suitable for computer recognition at the same time as or within a specified period of time from acquiring the image of the face to ensure that the image of the face and the image of the corresponding iris are from a same live person;associating the image of the face and the image of the corresponding iris together for biometric identification of the same live person; anddetermining if motion vectors from comparing the image of the corresponding iris with the image of the face are consistent with an expected sequence of images acquired from the same live person. This is a continuation of, and claims priority to U.S. application Ser. No. 13/567,901, filed Aug. 6, 2012 and entitled “Methods for Performing Biometric Recognition of a Human Eye and Corroboration of the Same”, which in turn is a continuation of, and claims the benefits of priority to:U.S. application Ser. No. 12/887,106 filed Sep. 21, 2010 and entitled “Methods for Performing Biometric Recognition of ...

Подробнее
Номер записи: 60
14-02-2019 дата публикации

IMAGE ANALYSIS FOR USER AUTHENTICATION

Номер: US20190050866A1
Автор: WANG Yicong, Xu Haizhi
Принадлежит:

A user can be authenticated to a mobile computing device using an authentication process that recognizes the user and verifies that an actual human being is attempting to be authenticated, in order to minimize the ability of another person to spoof the authentication process. A model of a user can be generated and stored in the cloud, enabling that model to be synchronized across various devices. A user accessing one of these devices can have infrared image information captured, which can be used with a facial recognition process, to recognize the user, and with a human verification process, to verify that the facial information corresponds to a human user. Various approaches such as visual analysis and thermal imaging can be used to verify that the human user being recognized is interactive with the device. 1. A mobile device , comprising:a processor; and obtain a request to authorize a transaction;', 'illuminate, with an infrared light emitting diode, a user that is interacting with the mobile device;', 'use a camera on the mobile device to capture an infrared image of a portion of a face of the user;', 'analyze the infrared image to identify eyes of the user;', 'determine that the infrared image corresponds to a living being by analyzing a thermal characteristic of the eyes of the user;', 'identify the user based at least in part on the infrared image;', 'authenticate the user as a result of the identity of the user being recognized as an authorized user and as a result of the infrared image corresponding to a living being; and', 'allow the transaction to be performed as a result of the user being authenticated., 'memory storing instructions that, as a result of being executed by the processor, cause the mobile device to2. The mobile device of claim 1 , wherein the infrared image captures a reflection of infrared light emitted from the infrared light emitting diode.3. The mobile device of claim 1 , wherein the instructions further cause the mobile device to: ...

Подробнее
Номер записи: 61
25-02-2021 дата публикации

OBJECT RECOGNITION METHOD AND APPARATUS

Номер: US20210056332A1
Автор: CHOI Chang Kyu, HAN Jaejoon, HAN Seungju, Kim JiHye, Ko Minsu, PARK Sungun, SON Changyong, SON Jinwoo
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

An object recognition apparatus and method are provided. The apparatus includes a processor configured to verify a target image using an object model and based on reference intermediate data extracted by a partial layer of the object model as used in an object recognition of an input image, in response to a failure of a verification of the input image after a success of the object recognition of the input image, and perform an additional verification of the target image in response to the target image being verified in the verifying of the target image. 1. A processor-implemented object recognition method , the method comprising:verifying a target image using an object model and based on reference intermediate data previously extracted by a partial layer of the object model as used in an object recognition of an input image, in response to a failure of a verification of the input image after a success of the object recognition of the input image; andperforming an additional verification, of the target image, in response to the target image being verified in the verifying of the target image.2. The method of claim 1 , wherein the verification of the input image and the additional verification are respective liveness verification operations performed using a liveness model.3. The method of claim 1 ,wherein the object recognition of the input image is a registration based recognition,wherein, upon the target image being verified in the verifying of the target image, identification of the target image is performed without performing registration based recognition of the target image, andwherein, upon failure of the verifying of the target image, registration based recognition of the target image is performed.4. The method of claim 1 ,wherein the object recognition of the input image is registration based recognition, andwherein, upon the target image being verified in the verifying of the target image, the additional verification of the target image is performed without ...

Подробнее
Номер записи: 62
22-02-2018 дата публикации

METHODS FOR PERFORMING BIOMETRIC RECOGNITION OF A HUMAN EYE AND CORROBORATION OF SAME

Номер: US20180053052A1
Автор: Hanna Keith J., Hoyos Hector T.
Принадлежит:

A method of biometric recognition is provided. Multiple images of the face or other non-iris image and iris of an individual are acquired. If the multiple images are determined to form an expected sequence of images, the face and iris images are associated together. A single camera preferably acquires both the iris and face images by changing at least one of the zoom, position, or dynamic range of the camera. The dynamic range can be adjusted by at least one of adjusting the gain settings of the camera, adjusting the exposure time, and/or adjusting the illuminator brightness. The expected sequence determination can be made by determining if the accumulated motion vectors of the multiple images is consistent with an expected set of motion vectors and/or ensuring that the iris remains in the field of view of all of the multiple images. 120-. (canceled)21. A method for biometric acquisition , comprising:acquiring, by a sensor, an image of the iris comprising a reflection of a predefined geometrical shape;determining a value of deformation or magnification of the geometrical shape in the reflection;comparing the determined value to a value of deformation or magnification expected for a reflection occurring off a live eye; anddetermining that the image of the iris is acquired from a live eye if the determined value is consistent with the expected value.22. The method of claim 21 , wherein determining the value of deformation or magnification comprises determining if the determined value is within a magnification range that is approximately 3 to 6 millimeters divided by a distance of the predefined geometrical shape from the iris.23. The method of claim 21 , comprising determining if a dimension of the reflection is at least ten times smaller than a corresponding dimension of the predefined geometrical shape claim 21 , if the iris is at least 100 millimeters from the predefined geometrical shape.24. The method of claim 21 , comprising determining if a dimension of the ...

Подробнее
Номер записи: 63
13-02-2020 дата публикации

SECURITY CONTROL METHOD AND DEVICE OF APPLICATION, AND ELECTRONIC DEVICE

Номер: US20200050748A1
Автор: GUO Ziqing, HUI Fangfang, TAN Xiao, Zhou Haitao
Принадлежит:

The present disclosure provides a security control method and device of an application, and an electronic device. The method includes: determining whether running information of the application meets a preset security control condition; calling a preset service if the running information of the application meets the preset security control condition, the preset service being configured to enable the application to run in a trusted execution environment; and executing an authentication service corresponding to the running information of the application in the trusted execution environment. 1. A security control method of an application , the security control method comprising:determining whether running information of the application meets a preset security control condition;calling a preset service based on a determination that the running information of the application meets the preset security control condition, the preset service being configured to enable the application to run in a trusted execution environment; andexecuting an authentication service corresponding to the running information of the application in the trusted execution environment.2. The security control method according to claim 1 , whereindetermining whether the running information of the application meets the preset security control condition comprises: determining whether the application is a preset application; ordetermining an operation type of a current operation of the application, and determining whether the operation type is a preset operation type;calling the preset service based on the determination that the running information of the application meets the preset security control condition, comprises: calling the preset service based on a determination that the application is the preset application, or based on a determination that the operation type is the preset operation type; andexecuting the authentication service corresponding to the running information of the application in the ...

Подробнее
Номер записи: 64
13-02-2020 дата публикации

IDENTIFICATION METHOD AND APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM

Номер: US20200050877A1
Автор: Li Liang
Принадлежит:

An identification method includes: controlling at least one camera to acquire a face image and an eye image of a target object, wherein the eye image includes at least one of an iris feature or an eye-print feature; and identifying the target object based on the face image and the eye image. 1. An identification method , comprising:controlling at least one camera to acquire a face image and an eye image of a target object, wherein the eye image comprises at least one of an iris feature or an eye-print feature; andidentifying the target object based on the face image and the eye image.2. The method of claim 1 , wherein the identifying the target object based on the face image and the eye image comprises:determining whether the target object is a living body based on the eye image and the face image; andidentifying the target object if the target object is a living body.3. The method of claim 1 , wherein the controlling at least one camera to acquire a face image and an eye image of a target object comprises:adjusting the at least one camera to acquire the face image of the target object; andadjusting the at least one camera based on a position of a facial rectangular frame of the face image to acquire the eye image of the target object.4. The method of claim 3 , wherein the at least one camera is one camera claim 3 ,the adjusting the at least one camera to acquire the face image of the target object comprises: adjusting the camera to obtain the position of the facial rectangular frame of the target object; and acquiring the face image of the target object based on the position of the facial rectangular frame; andthe adjusting the at least one camera based on a position of a facial rectangular frame of the face image to acquire the eye image of the target object comprises: adjusting the camera based on the position of the facial rectangular frame of the face image to obtain a position of a two-eye rectangular frame of the target object; and acquiring the eye image of ...

Подробнее
Номер записи: 65
23-02-2017 дата публикации

LIVENESS DETECTION APPARATUS AND LIVENESS DETECTION METHOD

Номер: US20170053174A1
Автор: FAN Haoqiang, JIA Kai, Yin Qi
Принадлежит:

A liveness detection apparatus and a liveness detection method are provided. The liveness detection apparatus may comprise: a specific exhibiting device, for exhibiting a specific identification content; an image acquiring device, for acquiring image data of a target object to be recognized during the exhibition of the identification content; a processor, for determining whether there is a reflective region corresponding to the identification content in the acquired image data, determining a regional feature of the reflective region when there is the reflective region, to obtain a determination result, and recognizing whether the target object is a living body based on the determination result. 1. A liveness detection apparatus , comprising:a specific exhibiting device, for exhibiting a specific identification content;an image acquiring device, for acquiring image data of a target object to be recognized during the exhibition of the identification content;a processor, for determining whether there is a reflective region corresponding to the identification content in the acquired image data, determining a regional feature of the reflective region when there is the reflective region, to obtain a determination result, and recognizing whether the target object is a living body based on the determination result.2. The liveness detection apparatus according to claim 1 , wherein claim 1 , the specific exhibiting device is used for exhibiting at least one of a title bar claim 1 , a tool bar and a background region of the liveness detection apparatus as the identification content.3. The liveness detection apparatus according to claim 1 , wherein claim 1 , the specific exhibiting device includes:a sequence generator, for randomly generating a reference sequence; anda display, for applying the reference sequence to the identification content, to adjust a display effect of the identification content.4. The liveness detection apparatus according to claim 3 , wherein claim 3 , ...

Подробнее
Номер записи: 66
23-02-2017 дата публикации

SYSTEM AND METHOD FOR VALIDATING THREE-DIMENSIONAL OBJECTS

Номер: US20170053175A1
Автор: Tussy Kevin Alan
Принадлежит:

A system for verifying the presence of a three-dimensional object. The system has a plurality of two-dimensional cameras. Each camera is oriented to face a different direction. Cameras adjacent to each other are set to have overlapping field of a views. An image processor conducts image recognition on images received from the cameras. The three dimensions of the object are verified by comparing the image recognition in the overlapping field of views. 1. A system for verifying the presence of a three-dimensional object , the system comprising:a plurality of two-dimensional cameras, each camera being oriented in a different direction and adjacent cameras having overlapping field of a views, andan image processor conducting image recognition on images received from the cameras,whereinthe three dimensions of the object are verified by comparing the image recognition in the overlapping field of views.2. The system of claim 1 , wherein the image recognition is facial recognition.3. The system of claim 2 , wherein the facial recognition generates biometric measurements between facial features detected in the images received from cameras claim 2 , and the biometric measurements generated from the images received from the cameras are compared to expected differences.4. The system of claim 3 , further comprising an authentication processor wherein when the biometric measurements meet the expected differences within a predetermined threshold claim 3 , a person being imaged is authenticated as a real person.5. The system of claim 1 , wherein the adjacent cameras are angled away from one another.6. The system of claim 1 , wherein the adjacent cameras are angled towards one another.7. A system for verifying the presence of a three-dimensional object claim 1 , the system comprising:a plurality of two-dimensional cameras disposed such that fields of the plurality of two-dimensional cameras are overlapping, adjacent cameras of the plurality of two-dimensional cameras being angled ...

Подробнее
Номер записи: 67
23-02-2017 дата публикации

SYSTEMS AND METHODS FOR LIVENESS ANALYSIS

Номер: US20170053406A1
Автор: Hirvonen David
Принадлежит:

In a system for determining liveness of an image presented for authentication, a reference signal is rendered on a display, and a reflection of the rendered signal from a target is analyzed to determine liveness thereof. The analysis includes spatially and/or temporally band pass filtering the reflected signal, and determining RGB values for each frame in the reflected signal and/or each pixel in one or more frames of the reflected signal. Frame level and/or pixel-by-pixel correlations between the determined RGB values and the rendered signal are computed, and a determination of whether an image presented is live or fake is made using either or both correlations. 1. A computer-implemented method comprising:rendering on a display device a time-varying first signal comprising a plurality of different respective signals that are separated in phase from each other;during the rendering, capturing a plurality of images of a target that is illuminated by the rendered first signal;applying a band pass filter temporally to the images to generate a plurality of filtered images;extracting a second signal from the filtered images;generating a first measure based on, at least, a temporal correlation of the first signal and the second signal;for each pixel location in a plurality of pixel locations, extracting a respective signal for the pixel location based on changes to a respective value of the pixel location over time in a plurality of the filtered images;calculating a respective pixel location correlation score for each of the pixel locations based on a correlation of the respective extracted signal of the pixel location to the first signal;generating a second measure based on, at least, a plurality of the pixel location correlation scores; andaccepting or rejecting the target based on, at least, the first and second measures.2. The method of wherein each respective signal of the first signal is a different color.3. The method of wherein each of the colors is rendered using ...

Подробнее
Номер записи: 68
01-03-2018 дата публикации

ELECTRONIC DEVICE AND METHOD FOR MEASURING HEART RATE BASED ON INFRARED RAYS SENSOR USING THE SAME

Номер: US20180055392A1
Автор: CHOI Jongmin, KIM DongWook, KIM Taeho, Lee Donghyun, Lee Jaesung, LEE Seungeun, PARK JeongMin, WON Jinhee
Принадлежит:

A method for determining a heart rate (HR) using an infrared rays (IR) sensor and an electronic device is provided. An image is received using an IR sensor, at least one region of interest (ROI) for measuring the HR is determined in the received image, and the HR is determined based on the at least one determined ROI. 1. An electronic device comprising:an infrared rays (IR) sensor;a memory; anda processor electrically connected to the IR sensor and the memory, receive an image using the IR sensor,', 'determine at least one region of interest (ROI) for measuring a heart rate (HR) in the received image, and', 'determine the HR based on the at least one determined ROI., 'wherein the memory stores instructions which, when executed, cause the processor to2. The electronic device of claim 1 , wherein the instructions cause the processor to:detect an object from the received image,extract features of the detected object, anddetermine the at least one ROI based on the extracted features of the object.3. The electronic device of claim 2 , wherein the instructions cause the processor to extract locations of eyes claim 2 , a nose claim 2 , a mouth claim 2 , and a forehead of a user as the features if a user's face is included in the received image.4. The electronic device of claim 1 , wherein the instructions cause the processor to:receive a request for user authentication, recognize an iris of a user using the IR sensor,determine whether measurement of the HR is possible in the ROI, andcomplete the user authentication if the HR is measured.5. The electronic device of claim 4 , wherein the instructions cause the processor to:determine the HR of the user based on the determined ROI if the ROI is determined to correspond to the authenticated user, andstore the at least one determined ROI in the memory to correspond to the authenticated user if the ROI is not determined to correspond to the authenticated user.6. The electronic device of claim 1 , wherein the instructions cause ...

Подробнее
Номер записи: 69
20-02-2020 дата публикации

PULSE WAVE DETECTION DEVICE, IMAGE ANALYSIS DEVICE, AND BIOMETRIC INFORMATION GENERATION SYSTEM

Номер: US20200054222A1
Автор: ADACHI Yoshihisa, NUNOKAWA Takashi, OGAWA Rieko, OKUMURA Tetsuya, ONISHI Junya
Принадлежит:

Pulse waves of a living body are detected with high accuracy. A pulse wave detection device includes a camera configured to capture an image of the living body a plurality of times through a first green filter and an infrared light filter having light transmission characteristics in a near-infrared light wavelength range within a wavelength range where a light absorption coefficient of oxidized hemoglobin is greater than a light absorption coefficient of reduced hemoglobin, and an image analysis unit configured to analyze a plurality of images of the living body captured by the camera and to detect the pulse waves of the living body. The image analysis unit is configured to detect the pulse waves by detecting a change in intensity of light in the near-infrared light wavelength range indicated by the plurality of images. 116-. (canceled)17. A pulse wave detection device configured to detect a pulse wave of a living body by analyzing an image obtained by capturing the living body , the pulse wave detection device comprising:an imaging unit configured to capture an image of the living body a plurality of times through a first filter having light transmission characteristics in a near-infrared light wavelength range within a wavelength range where a light absorption coefficient of oxidized hemoglobin is greater than a light absorption coefficient of reduced hemoglobin, or having light transmission characteristics in a visible light wavelength range and a near-infrared light wavelength range within a wavelength range where a light absorption coefficient of oxidized hemoglobin is greater than a light absorption coefficient of reduced hemoglobin, and through a second filter having light transmission characteristics in a visible light wavelength range and a near-infrared light wavelength range within a wavelength range where a light absorption coefficient of oxidized hemoglobin is greater than a light absorption coefficient of reduced hemoglobin; andan image analysis unit ...

Подробнее
Номер записи: 70
05-03-2015 дата публикации

AUTHENTICATION APPARATUS, PRISM MEMBER FOR AUTHENTICATION AND AUTHENTICATION METHOD

Номер: US20150062319A1
Автор: Higuchi Teruyuki
Принадлежит:

An authentication apparatus includes a prism, an imaging unit, a visible light source and an infrared light source. The prism comprises: a contact surface contacted with the living body; a reflection surface contacted with the contact surface, and totally reflect light by the visible light source from a concave portion of the living body and a convex portion of the living body, and light by the infrared light source from an inside of the living body; and an imaging surface configured to be opposed to the contact surface, in contact with the reflection surface, and provided at an angle such that the light from the concave portion of the living body cannot be reached, and the light totally reflected by the reflection surface and the light from the convex portion of the living body can be transmitted. The imaging unit images the light which is transmitted through the imaging surface. 1. An authentication apparatus including a prism body , an imaging unit , a visible light source configured to radiate a visible light to a living body and an infrared light source configured to radiate an infrared light to the living body , a living body contact surface configured to be in contact with the living body;', 'a reflection surface configured to be in contact with the living body contact surface, and totally reflect light by the visible light source from a concave portion of the living body and a convex portion of the living body, and light by the infrared light source from an inside of the living body; and', 'an imaging surface configured to be opposed to the living body contact surface, in contact with the reflection surface, and provided at an angle such that the light from the concave portion of the living body cannot be reached, and the light totally reflected by the reflection surface and the light from the convex portion of the living body can be transmitted,, 'wherein the prism body compriseswherein the imaging unit is configured to image the light, which is transmitted ...

Подробнее
Номер записи: 71
10-03-2022 дата публикации

Method and device for determining operation based on facial expression groups, and electronic device

Номер: US20220075996A1
Автор: Aiping PI, Feiying HUANG, Huagui LIANG, Qiurong Chen, Weiming JIAN
Принадлежит: Xunteng Guangdong Technology Co Ltd

This application provides an operation determination method based on expression groups, apparatus and electronic device therefor, and relates to the technical field of image processing. The method is executed by an electronic device. The method comprises: obtaining a current human face image of a target object; performing a live body human face identification on the target object based on the current human face image, determining whether an identity of the target object is legal according to an identification result; the live body human face identification comprises a live body identification and a human face identification; if legal, obtaining a current expression group of the current human face image; determining an instruction to be executed corresponding to the current expression group; performing an operation corresponding to the instruction to be executed. This application uses human face identification technology, and while continuing the identity authentication function of human face identification, with addition of user-defined facial expressions, it may ensure that a user will not display these actions in unconscious states such as work, sleep or coma etc., which greatly protects the safety of the user's face, to improve the safety and reliability of the electronic device to determine the operation.

Подробнее
Номер записи: 72
10-03-2022 дата публикации

METHOD AND DEVICE FOR AUTHENTICATING NEAR-FIELD INFORMATION, ELECTRONIC APPARATUS, AND COMPUTER STORAGE MEDIUM

Номер: US20220076268A1
Автор: Chen Qiuangzhou, Huang Feiying, Jian Weiming, Liang Huagui, Pi Aiping
Принадлежит:

This application provides a method for near-field information authentication, device, electronic device and computer storage medium therefor, comprising: obtaining a current location information of the object to be authenticated, determining a target grid area where the object to be authenticated is located; receiving the identity authentication request sent by the target service terminal; determining effective users of the target service terminal according to the information of the target service terminal, determining biological characteristic information of each valid user; performing identity authentication based on the live body biological characteristic information of the object to be authenticated and the biological characteristic information of each valid user. When information authentication is performed on the object to be authenticated, this application is realized through the live body biological characteristic information of the object to be authenticated. The user does not need to provide a physical identification card, which simplifies the information authentication process and improves the user experience of the user when performing information authentication; Only when the object to be authenticated is within the preset range of its authorized merchant, the current location information of the object to be authenticated is sent to the server, which ensures the user's location privacy. 1. A method for a near-field information authentication , characterized in that , the method is applied to a server and comprising:obtaining a current location information of an object to be authenticated, then determining a target grid area where the object to be authenticated is located, wherein when the object to be authenticated is within a preset range of its authorized merchants, a user terminal of the object to be authenticated periodically sends the current location information of the object to be authenticated to the server;receiving an information ...

Подробнее
Номер записи: 73
03-03-2016 дата публикации

METHOD AND APPARATUS FOR LIVE USER RECOGNITION

Номер: US20160062456A1
Автор: Wang Kongqiao, Wang Wendong, ZHANG BO
Принадлежит:

Embodiments of the present invention relate to a method and apparatus for live user recognition. There is disclosed a method for live user recognition. The method comprises: obtaining an image containing a face; while recognizing the face based on the image, detecting whether gaze of the face moves into proximity of a random position on a display screen every time an object is displayed at the random position; and determining whether the image is obtained from the live user based on the detection. The corresponding apparatus is disclosed as well. 117-. (canceled)18. A method for live user recognition , the method comprising:obtaining an image containing a face;while recognizing the face based on the image, detecting whether gaze of the face moves into a proximity of a random position on a display screen every time an object is displayed at the random position; anddetermining whether the image is obtained from the live user based on the detection.19. The method of claim 18 , wherein detecting whether gaze of the face moves into a proximity of a random position on a display screen every time an object is displayed at the random position comprises:detecting whether the gaze of the face moves into the proximity of the random position in a predetermined time period after the object is displayed.20. The method of claim 18 , whereina first object is displayed at a first random position on the display screen at a first instant;a second object is displayed at a second random position on the display screen at a subsequent second instant, a distance between the first and second random positions being greater than a predetermined threshold distance.21. The method of claim 20 , wherein the first object is removed from the display screen prior to the second instant.22. The method of claim 18 , wherein the object is displayed on the display screen for a time duration that is less than a predetermined threshold time.23. The method of claim 18 , further comprising:detecting stay ...

Подробнее
Номер записи: 74
03-03-2016 дата публикации

IMAGE PROCESSING APPARATUS FOR FACIAL RECOGNITION

Номер: US20160063314A1
Автор: Samet Shai
Принадлежит: SAMET PRIVACY, LLC

An apparatus including an image capture device including a lens, a shutter, an image sensor, and an aperture is provided. The image capture device receives, via the lens, a plurality of images. The apparatus further includes a display, a memory, a receiver, a transmitter, and a processor. The receiver receives facial recognition data. The transmitter transmits an instruction to capture a series of images via the image capture device. The series of images may include a randomly generated pose. The apparatus further includes a processor to analyze the facial recognition data to determine an estimated age of a user. 1. An information processing apparatus comprising:an image capture device for capturing a plurality of images of a user;a memory storing at least one data array including pupil distance in correspondence with age information;a processor configured to generate a random facial pose;a transmitter configured to transmit instructions to a user, including an instruction to pose for the image capture device in a first facial configuration for capturing a first image and to pose in a second facial configuration for capturing a second image, wherein the first facial configuration is different than the second facial configuration, and one of the first and second facial configurations corresponds to the randomly generated facial pose;a receiver configured to receive facial image information based on the plurality of images captured by the image capture apparatus, said facial image information comprising:the first image of the user;the second image of the user; andone or more feature inputs corresponding to one or more facial features, wherein at least one of the one or more of the feature inputs corresponds to an age-indicator;wherein the processor determines, based on the facial image information, one or more of:a positive detection of a full image of the user's face in the first and second images;whether the pose of the user in first image corresponds to the first ...

Подробнее
Номер записи: 75
01-03-2018 дата публикации

DEVICE TO PROVIDE A SPOOFING OR NO SPOOFING INDICATION

Номер: US20180060680A1
Автор: Alon Ofir
Принадлежит:

Aspects may relate to a device to provide a spoofing or no spoofing indication. The device may comprise a processor and a sensor. The sensor may receive multiple facial frames of a face of a user. The processor coupled to the sensor may be configured to: perform a function based upon components of the face of the user relative to one another to determine measured facial features for two adjacent frames of the multiple facial frames; and determine whether the measured facial features for the two adjacent frames are sufficiently different to indicate liveness of the user and no spoofing attempt. 1. A device comprising:a sensor to receive multiple frames of a face of a user; and perform a function based upon components of the face of the user relative to one another to determine measured facial features for two adjacent frames of the multiple frames; and', 'determine whether the measured facial features for the two adjacent frames indicate that the two adjacent frames are sufficiently different to indicate a liveness of the user., 'a processor coupled to the sensor, the processor configured to2. The device of claim 1 , wherein claim 1 , if none of the adjacent frames of the multiple facial frames are determined to be similar claim 1 , the processor is configured to command a no spoofing indication.3. The device of claim 1 , wherein the components of the user's face relative to one another to perform the function to determine measured facial features are related to at least one of raising an eyebrow claim 1 , moving a lip claim 1 , moving a cheek claim 1 , moving a head side to side claim 1 , or moving a nose.4. The device of claim 1 , wherein the components of the user's face relative to one another to perform the function to determine measured facial features are related to an eye blink.5. The device of claim 4 , wherein the components of the user's face relative to one another to perform the function to determine measured facial features related to the eye blink ...

Подробнее
Номер записи: 76
01-03-2018 дата публикации

Online Pseudonym Verification and Identity Validation

Номер: US20180060681A1
Автор: Bud Andrew
Принадлежит: iProov Ltd.

Methods, systems, and computer program products for authenticating an online user. Authentication involves sending a code from a server to a user device equipped with a source of illumination and a camera capable of capturing video imagery of the online user. The user device receives the code, modulates the source of illumination in accordance with the code, and captures video imagery of the user while the source of illumination is being modulated according to the code. The captured video imagery of the online user is sent to the server where it is analyzed to detect evidence of changes in illumination that correspond to the code. If good correspondence is found, the user may be authenticated. Similar methods may be applied to other biometric data. Applications of the authentication include identify validation, pseudonym verification, and distinguishing human from non human access attempts. 1. A method of authenticating a presence of an online user seeking to use a device to effect an action which is contingent on authenticating the presence of the online user , wherein the device includes a source of illumination and a camera , the method comprising:modulating the source of illumination; andusing the camera to capture video imagery of the online user while modulating the source of illumination;in a first analyzing step, analyzing the captured video imagery to detect frames that show changes in reflected illumination in temporal correspondence with the modulation of the source of illumination;in a second analyzing step, determining a spatial arrangement of the brightness changes in reflected illumination in the detected frames and determining a degree of consistency of the spatial arrangement of the brightness changes in reflected illumination with a spatial arrangement of brightness changes that would be expected from a three-dimensional shape comprising a plurality of features of a human present during authentication;using results of the first analyzing step to ...

Подробнее
Номер записи: 77
04-03-2021 дата публикации

Method of Liveness Detection and Related Device

Номер: US20210064898A1
Автор: CHEN Kuan-Hung, Chen Wen-Chung, Shiue Tsuey-Huey, Wu Bing-Jhang
Принадлежит:

A method of liveness detection for a computing device comprises acquiring at least one full cycle of a remote photoplethysmography, rPPG, signal from a skin image, extracting at least one rPPG waveform characteristic from the full cycle of the rPPG signal, and determining whether the skin image includes a life according to the extracted rPPG waveform characteristic. 1. A method of liveness detection for a computing device , the method comprising:acquiring at least one full cycle of a remote photoplethysmography, rPPG, signal from a skin image;extracting at least one rPPG waveform characteristic from the full cycle of the rPPG signal; anddetermining whether the skin image includes a life according to the extracted rPPG waveform characteristic.2. The method of claim 1 , wherein the step of determining whether the skin image includes the life according to the extracted rPPG waveform characteristic comprises:determining that the skin image includes the life when the extracted rPPG waveform characteristic includes at least one of a dicrotic notch wave, a systolic wave, a diastolic wave, a systolic-diastolic wave, a first order differential feature of the rPPG signal, and a second order differential feature of the rPPG signal.3. The method of claim 2 , wherein the second order differential feature of the rPPG signal includes at least one of an early systolic positive wave claim 2 , an early systolic negative wave claim 2 , a late systolic reincreasing wave claim 2 , a late systolic redecreasing wave claim 2 , and an early diastolic positive wave.4. A computing device for liveness detection claim 2 , the computing device comprising:a processing unit, for executing a program code; and acquiring at least one full cycle of a remote photoplethysmography, rPPG, signal from a skin image;', 'extracting at least one rPPG waveform characteristic from the full cycle of the rPPG signal; and', 'determining whether the skin image includes a life according to the extracted rPPG waveform ...

Подробнее
Номер записи: 78
04-03-2021 дата публикации

METHOD AND APPARATUS FOR DETERMINING LIVENESS

Номер: US20210064899A1
Автор: HEO Jingu, KIM Joohyeon, LEE Younkyu, Nam Dong Kyung
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

A liveness determining method and apparatus are provided. The liveness determining apparatus includes an optical sensor including at least one optical source; a memory configured to store registered color information; and at least one processor configured to: obtain, from the optical sensor, an input fingerprint image of an object corresponding to the at least one optical source, obtain input color information from the input fingerprint image, compare the input color information and the registered color information, and determine liveness of the object based on a result of the comparing. 1. A liveness determining method comprising:obtaining, by an optical sensor, an input fingerprint image of an object corresponding to at least one optical source of the optical sensor;obtaining, by a processor, input color information from the input fingerprint image;comparing, by the processor, the input color information and registered color information; anddetermining, by the processor, liveness of the object based on a result of the comparing.2. The liveness determining method of claim 1 , wherein the obtaining of the input fingerprint image comprises obtaining a plurality of input fingerprint images at a preset frame rate for a preset time period claim 1 , for each optical source of a plurality of optical sources having different frequencies.3. The liveness determining method of claim 1 , wherein the comparing comprises comparing an input intensity obtained from the input fingerprint image and a registered intensity from the registered color information claim 1 , for each optical source of a plurality of optical sources having different frequencies.4. The liveness determining method of claim 3 , wherein the comparing comprises:(i) determining whether a difference between the input intensity and the registered intensity for a plurality of pixels is less than a first threshold value; or(ii) determining whether an average of the difference between the input intensity and the ...

Подробнее
Номер записи: 79
04-03-2021 дата публикации

ID VERIFICATION WITH A MOBILE DEVICE

Номер: US20210064900A1
Автор: Fankhauser Benjamin, Georgoulis Stamatios, Goettlicher Michael, Hudritsch Marcus, Polac Magdalena, Saha Suman, Shamoska Nevena, van Goo Luc, Vorobiev Mikhail
Принадлежит:

A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document and using automated verification of identification documents. Identification documents may be authenticated by validating security features. The system may determine features expected in a valid identification document and determine whether those features are present, employing techniques, such as determining whether direction-sensitive features are present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks. 1. At least one non-transitory computer-readable medium comprising computer-executable instructions which , when executed by a computing device , cause the computing device to carry out a method , the method comprising:capturing a plurality of images using a camera; and recognizing images of the plurality of images as images of an identification document;', 'computing the angle of the camera relative to the identification document for the recognized images of the plurality of images;', 'identifying at least one security feature of the identification document based on the recognized images taken at multiple angles; and', 'verifying validity of the at least one security feature based on the recognized images taken at multiple angles., 'analyzing the captured images by2. The at least one non-transitory computer-readable medium of claim 1 , wherein capturing a plurality of images using a camera comprises:providing instructions to a user indicating at what angles the camera of the computing device should be held relative to the identification document.3. The at least one non-transitory computer-readable medium of claim 1 , wherein recognizing images of the plurality of images as images of an identification document comprises:processing images of the captured plurality of images captured by identifying regions of the ...

Подробнее
Номер записи: 80
04-03-2021 дата публикации

FACIAL LIVENESS DETECTION WITH A MOBILE DEVICE

Номер: US20210064901A1
Автор: Fankhauser Benjamin, Georgoulis Stamatios, Goettlicher Michael, Hudritsch Marcus, Polac Magdalena, Saha Suman, Shamoska Nevena, Van Gool Luc, Vorobiev Mikhail
Принадлежит:

A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document, using automated verification of identification documents and detection that a live person identified by the document is present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks. The deep learning model may be trained using training data extracted from facial feature locations of training images. 1. A non-transitory computer-readable medium comprising computer-executable instructions which , when executed by a computing device , cause the computing device to carry out a method , the method comprising: accessing a plurality of images comprising a face obtained by a camera;', 'providing the plurality of images to a trained deep learning model to obtain output indicating one or more likelihoods that the plurality of images comprise images of a live user and one or more likelihoods that the plurality of images comprise images of a spoof attack; and', 'identifying the plurality of images as comprising at least one of a live user and a spoof attack based on the output obtained from the trained deep learning model;, 'using at least one processor to performwherein the trained deep learning model comprises at least one convolutional neural network and at least one feedback network configured to prevent overtraining of the at least one convolutional neural network.2. The non-transitory computer readable medium of claim 1 , wherein the trained deep learning model is trained based on any one of:training data comprising facial feature locations extracted from training images; andfeedback from the at least one feedback network.3. The non-transitory computer-readable medium of claim 1 , wherein the trained deep learning model is configured to identify spoof attacks including pre-recorded videos comprising a face claim 1 , still ...

Подробнее
Номер записи: 81
02-03-2017 дата публикации

Portable Biometric-based Identity Device

Номер: US20170063549A1
Автор: Antequera Rodriguez Nicolas, Zwart Klaas
Принадлежит: HANSCAN IP B.V.

A portable biometric device and system for secure communication and method for operating said system. The invention describes a portable biometric device () designed for improving security during internet transactions by means of a gateway device (). Also described is a secure actuation device () which, together with the portable biometric device (), allows the opening or closing of a set of access control elements in facilities to be controlled in order to block the entry of unauthorised persons. Also described are two systems for secure communication, which respectively comprise a portable biometric device () and a secure actuation device () combined with a portable biometric device (), and methods for operating said systems. 115-. (canceled)16. A portable biometric device for secure operations , comprising:a biometric acquisition sensor for acquiring biometric data of a user;a life detection sensor for determining that the user whose data are being acquired is alive;a physical security component formed by a plurality of microswitches that detect possible deformations in an outer shell of the portable biometric device as a result of tampering;a processor which is in communication with the biometric acquisition sensor, the life detection sensor and the physical security detector, and which is designed to encrypt operating data relating to the biometric data of the user, before sending this externally, and to decrypt incoming external information;a secure memory unit in communication with the processor;a wireless communication unit to allow for communication between the processor and the outside;wherein the encryption operation carried out by the processor comprises generating path sequences, which are variable in time, for a table of keys that are generated in a random manner to determine a key selected by means of a path descriptor, generating a random seed for defining an initial state of the path descriptor, and executing an encryption/decryption algorithm on ...

Подробнее
Номер записи: 82
17-03-2022 дата публикации

FACE LIVING BODY DETECTION METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM

Номер: US20220083795A1
Автор: DING Shouhong, LI Jilin, MENG Jia, TAI Ying, YAO Taiping, Zhang Jian
Принадлежит:

This application provides a face living body detection method performed by a computing device, the method including: obtaining a first face image of a target detection object in a first illumination condition and a second face image of the target detection object in a second illumination condition, determining a difference image according to the two images, decoupling an object reflectivity and an object normal vector corresponding to the target detection object from a feature map extracted from the difference image, and determining whether the target detection object is a living body according to the object reflectivity and the object normal vector. This method decouples texture information and depth information of a face, and performs living body detection by using decoupled information, which increases the defense capability against D attacks, thereby effectively defending against planar attacks and D attacks. 1. A face living body detection method performed by a computing device , the method comprising:obtaining a first face image of a target detection object in a first illumination condition and a second face image of the target detection object in a second illumination condition;determining a difference image according to the first face image and the second face image;extracting a feature map from the difference image, and decoupling an object reflectivity corresponding to the target detection object and an object normal vector corresponding to the target detection object from the feature map, the object reflectivity being used for representing texture information, and the object normal vector being used for representing depth information; anddetermining whether the target detection object is a living body according to the object reflectivity and the object normal vector.2. The method according to claim 1 , wherein the determining a difference image according to the first face image and the second face image comprises:identifying a face central region of the ...

Подробнее
Номер записи: 83
28-02-2019 дата публикации

BLUE LIGHT ADJUSTMENT FOR BIOMETRIC SECURITY

Номер: US20190065722A1
Автор: Kaehler Adrian
Принадлежит:

Systems and methods for blue light adjustment with a wearable display system are provided. Embodiments of the systems and methods for blue light adjustment can include receiving an eye image of an eye exposed to an adjusted level of blue light; detecting a change in a pupillary response by comparison of the received eye image to a first image; determining that the pupillary response corresponds to a biometric characteristic of a human individual; and allowing access to a biometric application based on the pupillary response determination. 1. A head mounted display system configured to project variable levels of blue light to an eye of a user , the display system comprising:a frame configured to be wearable on the head of the user;a display configured to project at least blue light into the eye of the user and to modify an intensity of the blue light relative to an intensity of non-blue light;a camera configured to capture images of the eye while the display projects light into the eye; and instruct the camera to capture a first image of the eye while the display projects light at a first ratio of intensity of blue light to non-blue light into the eye;', 'instruct the display to change the first ratio to a second ratio of the intensity of blue light to non-blue light;', 'instruct the camera to capture a second image of the eye while the display projects the second ratio of intensity of blue light to non-blue light;', 'determine that a change in the pupil parameter between the second image and the first image matches a biometric characteristic of a human individual; and', 'based on the determination that the change in the pupil parameter between the second image and the first image matches the biometric characteristic of a human individual, determine an identity of the human individual., 'a hardware processor programmed to2. The head mounted display system of claim 1 , wherein the display comprises a scanning fiber projector.3. The head mounted display system of claim ...

Подробнее
Номер записи: 84
28-02-2019 дата публикации

BIOMETRIC COMPOSITE IMAGING SYSTEM AND METHOD REUSABLE WITH VISIBLE LIGHT

Номер: US20190065845A1
Автор: Xu Hefei
Принадлежит:

An object of the present invention is to provide a biological feature composite imaging technology that multiplexing of the imaging functions and a mobile terminal comprising said composite imaging system. The composite imaging system comprises: a lens assembly (); an optical filter assembly () including at least a visible light bandpass region and an infrared light bandpass region; an image sensor () that includes a visible light imaging region, an infrared light imaging region, and a transition region between said two regions, said image sensor () operating under one of the visible light imaging mode and the infrared light imaging mode. Under the infrared light imaging mode, specific physical properties of the biological features are used as the image quality information to realize auto-focus of the biological features in the region of interest. 1. A biological feature composite imaging system with multiplexing of imaging functions , comprising:a lens assembly for receiving light from a region of interest;an optical filter assembly for filtering the received light so as to image light with a waveband for which passage is allowed, the optical filter assembly including at least a visible light bandpass region that allows only the visible light to pass through the optical filter assembly and an infrared light bandpass region that allows only the infrared light to pass through the optical filter assembly;an image sensor that includes a visible light imaging region, an infrared light imaging region, and a transition region between said two regions, said image sensor operating under one of the visible light imaging mode and the infrared light imaging mode, wherein the visible light imaging region images the visible light passing through the visible light bandpass region under the visible light imaging mode, and the infrared light imaging region images the infrared light passing through the infrared bandpass region under the infrared light imaging mode, wherein the ...

Подробнее
Номер записи: 85
28-02-2019 дата публикации

System and method of authentication using image of a user

Номер: US20190065874A1
Автор: Jean-Pierre Gerard, Jeremy Pastore, Michael L. Zhao, Ramamohan Reddy Sangasani, Roopa A. Vaidya, Steven Klocinski
Принадлежит: Mastercard International Inc

A fraud prevention system, method and medium analyzes a fraud prevention image, or a sequence of fraud prevention images, including a facial region of the user and a card associated with the user. The systems, methods and mediums may enable an image parser, a facial recognizer, a communication manager and an authenticator. The image parser may be adapted to parse the fraud prevention image into a facial image and a device image. The facial recognizer may be adapted to analyze the facial image to generate a current facial signature of the user. The authenticator may be adapted to authenticate the user based at least on comparison to the current facial signature and an enrolled facial signature. The communication manager may request a device verification based on a device signature and the authentication of the user. A liveness detector may verify liveness of the user within the fraud prevention image.

Подробнее
Номер записи: 86
28-02-2019 дата публикации

VERIFICATION METHOD AND SYSTEM

Номер: US20190065875A1
Автор: BEN ARBIA Mohamed, SHEIKH FARIDUL Hasan
Принадлежит:

The present invention relates to a method of verifying that (or determining whether) a biometric feature of a live human is present. More particularly, the present invention relates to a method of verifying that (or determining whether) a biometric feature of a live human is present for use as part of a biometric recognition system and/or method. In particular, the invention relates to a method of determining whether a biometric feature of a live human is present, comprising: using a camera , capturing visual data of a presented biometric feature; transmitting a signal towards the biometric feature; using a sensor , capturing data related to a reflected signal from the presented biometric feature; and determining whether the visual data and the reflected signal data relate to a biometric feature having realistic dimensions thereby to determine that a live biometric feature is present. 1. A method for determining whether a biometric feature of a live human is present , comprising:using a camera, capturing visual data of a presented biometric feature;transmitting a signal towards the biometric feature;using a sensor, capturing data related to a reflected signal from the presented biometric feature; anddetermining whether the visual data and the reflected signal data relate to a biometric feature having realistic dimensions thereby to determine that a live biometric feature is present.2. A method according to claim 1 , wherein determining whether the visual data and the reflected signal data relate to a biometric feature having realistic dimensions comprises determining whether the visual data and the reflected signal data in combination relate to a biometric feature having realistic dimensions.3. A method according to claim 1 , wherein the visual data relates to an angular size of the presented biometric feature.4. A method according to claim 1 , wherein the reflected signal data relates to a distance of the presented biometric feature from the sensor.5. A method ...

Подробнее
Номер записи: 87
10-03-2016 дата публикации

Multi-Stage Liveness Determination

Номер: US20160070967A1
Автор: Bandyopadhyay Saurav, BURNS David William, Chan Kwokleung, Chen Ming Yu, Du Eliza Yingzi, Ganti SuryaPrakash, Gu Jin, Schneider John Keith, Vural Esra
Принадлежит:

A method of determining whether a biometric object is part of a live individual is described. In one such method, image information is acquired from the biometric object by using a sensor, such as an ultrasonic sensor. The image information may be analyzed in at least two analysis stages. One of the analysis stages may be a temporal analysis stage that analyzes changes in the image information obtained during a time period throughout which the biometric object was continuously available to the sensor. For example, a dead/alive stage may analyze differences between image information taken at two different times in order to identify changes from one time to the next. Other stages may focus on aspects of a particular image information set, rather than seeking to assess changes over time. These other stages seek to determine whether an image information set exhibits characteristics similar to those of a live biometric object. 1. A method of determining whether a biometric object is part of a live individual , comprising:acquiring image information from the biometric object using a sensor; andanalyzing the image information in at least two analysis stages, wherein one of the analysis stages is a temporal analysis stage that analyzes changes in the image information obtained during a time period throughout which the biometric object was continuously available to the sensor.2. The method of claim 1 , wherein the temporal analysis stage determines whether changes in the image information are similar to changes consistent with a live object.3. The method of claim 2 , wherein the temporal analysis stage determines whether a feature of the biometric object changed during the time period.4. The method of claim 3 , wherein the feature is selected from the group consisting of a pore opening size claim 3 , a pore depth claim 3 , a ridge pattern claim 3 , and a texture.5. The method of claim 1 , wherein:(a) the temporal analysis stage determines whether changes in the image ...

Подробнее
Номер записи: 88
10-03-2016 дата публикации

IMAGE-BASED LIVENESS DETECTION FOR ULTRASONIC FINGERPRINTS

Номер: US20160070968A1
Автор: Bandyopadhyay Saurav, Chan Kwokleung, Chen Ming Yu, Du Eliza Yingzi, Gu Jin, Vural Esra
Принадлежит:

A liveness-detection method and/or system is disclosed. A method of detecting liveness can comprise obtaining a single ultrasonic image of a biometric object. The single ultrasonic image can be subdivided into a plurality of overlapping sample blocks. Feature vectors can be extracted in a spatial domain and a frequency domain from each of the plurality of sample blocks. The feature vectors can be compared from each of the plurality of sample blocks to a classification model. 1. A method of detecting liveness , comprising:obtaining a single ultrasonic image of a biometric object;subdividing the single ultrasonic image into a plurality of overlapping sample blocks;extracting feature vectors in a spatial domain and a frequency domain from each of the plurality of sample blocks; andcomparing the feature vectors from each of the plurality of sample blocks to a classification model.2. The method of claim 1 , wherein the feature vectors include a histogram feature.3. The method of claim 2 , wherein the histogram feature includes ultrasonic impedance characteristics of ridges and valleys of the biometric object.4. The method of claim 2 , wherein the histogram feature includes one or more of the following: ridge energy claim 2 , ridge entropy claim 2 , ridge variance claim 2 , ridge skewness claim 2 , ridge kurtosis claim 2 , ridge variance coefficient claim 2 , valley energy claim 2 , valley entropy claim 2 , valley variance claim 2 , valley skewness valley kurtosis claim 2 , and valley variance coefficient.5. The method of claim 1 , wherein the feature vectors include ratio-based features.6. The method of claim 5 , wherein the ratio-based features include a ratio of individual features between ridge and valley of the biometric object.7. The method of claim 5 , wherein the ratio-based features include one or more of the following: ratio of mean of ridge and valley claim 5 , ratio of median of ridge and valley claim 5 , ratio of energy of ridge and valley claim 5 , ratio of ...

Подробнее
Номер записи: 89
27-02-2020 дата публикации

SYSTEM AND METHOD FOR LOCATING AND DETERMINING SUBSTANCE USE

Номер: US20200065568A1
Автор: Nienhouse Robert Frank
Принадлежит:

In devices that determine levels of substance use, a substance level in a test sample provided to the testing device by a test subject is determined. A sequence of images are captured to include a portion of the face of the test subject providing the test sample and a display of the testing device. A value indicative of the substance level detected within the test sample is determined. A validity indicator indicating validity of the value indicative of the substance level is determined. A current location is determined. The value indicative of the substance level, the validity indicator, and the current location are sent to a remote server. 1. A mouthpiece for coupling with a testing device of the type that measures a substance level contained in a breath sample provided by a test subject through the mouthpiece , the mouthpiece comprising:a flange having a substantially oval outer shape and forming a substantially round inner passage through the flange having a first inner surface; anda first plurality of first protrusions formed on the first inner surface such that the first inner surface is irregularly shaped and not smooth;the plurality of first protrusions preventing a tube from sealing with the first inner surfaces.2. The mouthpiece of claim 1 , wherein the plurality of first protrusions prevent pressure of a sample provided through the tube from reaching sufficient pressure to trigger the testing device.3. The mouthpiece of claim 1 , further comprising:an oval shaped lip ring positioned on, and smaller than, the flange, the lip ring having an outer surface for sealing with lips of the test subject and a second inner surface; anda plurality of second protrusions formed on the second inner surface such that the second inner surface is irregularly shaped and not smooth;the plurality of second protrusions preventing a tube from sealing with the second inner surfaces.4. The mouthpiece of claim 3 , the plurality of second protrusions prevent pressure of a sample ...

Подробнее
Номер записи: 90
09-03-2017 дата публикации

METHOD FOR CHARACTERIZING MATERIAL BY ANALYSIS OF SPECKLES

Номер: US20170068865A1
Автор: CHIU Remy, GUILLEMOT Florence, MAALOUF Aldo
Принадлежит:

The invention proposes a method for characterizing material in which a surface is formed, comprising the steps of: 1. A method for characterizing material in which a surface is formed , comprising the steps of:projecting a coherent light beam onto the surface to generate on said surface speckles resulting from interferences of the light beams diffused by said surface,acquiring an image of said surface on which the speckles appear,processing said image to compute at least one characterization criterion of the material, andfrom criteria, determining the material constituting the surface,in which the processing step of the image comprises: setting up an autocorrelation matrix of the light intensity of the image,', 'computation of the discrete cosine transform of said matrix, and', 'computation of the value of a characterization criterion such as the average on the image of the matrix trace obtained by the discrete cosine transform of the autocorrelation matrix, and, 'computation of an autocorrelation function of the light intensity on the image and computation of the value of at least one criterion set up from said function, said computation comprising average of the phases of the wavelet coefficients on the image, or', 'standard deviation of the phases of the wavelet coefficients on the image., 'computation of the value of at least one representative criterion of a phase shift distribution of the light beams diffused by the surface, said computation comprising computation of a wavelet transform of the image, and computation of the value of at least one criterion from the following group2. The characterization method according to claim 1 , wherein computation of the value of at least one characterization criterion from the autocorrelation function of the light intensity comprises:computation of the value of at least one criterion set up from the Fourier transform of the autocorrelation function, andcomputation of the value of at least one criterion set up from the ...

Подробнее
Номер записи: 91
11-03-2021 дата публикации

FACIAL LIVENESS DETECTION

Номер: US20210073518A1
Автор: Bharadwaj Shivang, Kumar Anant, Niranjan Bhupendra
Принадлежит:

Approaches for processing captured image to detect facial portion of a user within the captured image are described. In an example, a facial image from the processed captured image may be derived. Based on the derived facial image, determining a set of specular features and texture-based feature vector. Based on the specular features and the texture-based feature vector, whether the facial image is of a facial substitute or not may be ascertained. 1. A system comprising:a processor; processing captured image to detect facial portion of a user within the captured image;', 'deriving a facial image from the processed captured image;', 'for the derived facial image, determining a set of specular features and texture-based feature vector; and', 'based on the specular features and the texture-based feature vector, ascertaining whether the facial image is of a facial substitute., 'an image analysis module coupled to the processor, wherein the image analysis module is to2. The system as claimed in claim 1 , wherein the image analysis module to detect the facial portion of the user based on one of edge detection techniques and a support vector machine classifier.3. The system as claimed in claim 1 , wherein to derive the facial image from the processed captured image claim 1 , the image analysis module is tocropping a portion of the captured image bearing the facial portion to obtain the facial image;detecting pair of eyes within the facial image;aligning the facial image with respect to a notional axis; andresizing the facial image to a predefined size.4. The system as claimed in claim 1 , wherein for determining the set of specular features claim 1 , the image analysis module is to:converting the facial image to a YUV color space to obtain a converted facial image; andprocessing the Y-channel of converted facial image to obtain the specular features.5. The system as claimed in claim 4 , wherein the processing the Y-channel of the converted facial image further comprises: ...

Подробнее
Номер записи: 92
16-03-2017 дата публикации

Device and Method for the Direct Optical Recording of Live Skin Areas

Номер: US20170076133A1
Автор: HILLMANN Juergen, MORGENEIER Dirk, REINHOLD Joerg
Принадлежит:

A device and method for direct optical recording of live skin areas, particularly of fingerprints or handprints, is disclosed. A novel possibility for direct optical recording of human skin prints with forensic quality where interference through ambient light is excluded is achieved in that, from a skin area to be recorded, image data of a calibration image generated under homogeneous illumination from an areal source and ambient light that may be present are read out from the sensor array, an adapted illumination pattern is calculated by means of the stored calibration image such that, through application of the adapted illumination pattern, a two-dimensionally structured illumination pattern is generated to minimize the influence of the ambient light and to homogenize the illumination at least of the deposited skin print, wherein an illumination array is controlled in individual light-emitting elements or in groups of light-emitting elements with the calculated illumination pattern. 1. A method for optical recording of skin prints by a direct optical scanner , the method comprising:placing a skin area to be recorded on a placement surface of the scanner;reading out and storing image data of a calibration image from a sensor array, the calibration image being generated under homogeneous illumination from an areal source and ambient light that may be present;calculating an adapted illumination pattern by applying image processing to a stored calibration image, and applying the adapted illumination pattern to generate a two-dimensionally structured illumination pattern to minimize influence of the ambient light and to homogenize the illumination of the deposited skin print;controlling an illumination array with the calculated adapted illumination pattern, the illumination array being controllable in individual light-emitting elements or in groups of light-emitting elements; andreading out and storing image data of an image of the deposited skin area generated with ...

Подробнее
Номер записи: 93
05-03-2020 дата публикации

METHOD, APPARATUS, AND SYSTEM FOR RESOURCE TRANSFER

Номер: US20200074148A1
Автор: Chen Jidong, XU WEI
Принадлежит:

A method for resource transfer, includes: acquiring a front face image, and a side face image from at least one side, of a target user; performing a liveness detection and an identity recognition on the target user based on the front face image and the side face image; and executing, if a liveness detection result is that the target user is a live user and an identity recognition result is that the target user is an authorized user of a target electronic account, resource transfer on the target electronic account. 1. A method for resource transfer , comprising:acquiring a front face image, and a side face image from at least one side, of a target user;performing a liveness detection and an identity recognition on the target user based on the front face image and the side face image; andexecuting, if a liveness detection result is that the target user is a live user and an identity recognition result is that the target user is an authorized user of a target electronic account, resource transfer on the target electronic account.2. The method according to claim 1 , wherein the performing the liveness detection and the identity recognition on the target user based on the front face image and the side face image comprises:performing the liveness detection on the target user based on the front face image and the side face image; andperforming the identity recognition on the target user based on the front face image and the side face image if the liveness detection result is that the target user is a live user.3. The method according to claim 2 , wherein the performing the liveness detection on the target user based on the front face image and the side face image comprises:inputting the front face image into a pre-trained first liveness detection model for processing to acquire a first probability outputted from the first liveness detection model;inputting the side face image into a pre-trained second liveness detection model for processing to acquire a second probability ...

Подробнее
Номер записи: 94
18-03-2021 дата публикации

FINGERPRINT AUTHENTICATION METHOD AND SYSTEM FOR REJECTING SPOOFING ATTEMPTS

Номер: US20210081641A1
Автор: Setterberg Eric
Принадлежит: Fingerprint Cards AB

A method of authenticating a user by means of a fingerprint authentication system, comprising the steps of receiving a touch by a candidate finger probe; acquiring a first candidate fingerprint image of the candidate finger probe; determining a first authentication representation based on the first candidate fingerprint image; retrieving a stored enrollment representation of an enrolled fingerprint of the user; comparing the first authentication representation with the enrolment representation; determining a liveness score for the candidate finger probe; and when the first authentication representation matches with the stored enrolment representation, and the liveness score indicates a likely spoof: providing a signal indicating a failed authentication; determining a first anti-spoofing representation based on the first candidate fingerprint image; and storing the first anti-spoofing representation. 1. A method of authenticating a user by means of a fingerprint authentication system , said method comprising the steps of:receiving a touch by a candidate finger probe;acquiring a first candidate fingerprint image indicating a surface topography of said candidate finger probe;determining a first authentication representation based on said first candidate fingerprint image;retrieving a stored enrollment representation of an enrolled fingerprint of said user;comparing said first authentication representation with said enrolment representation;determining a liveness score for said candidate finger probe; and providing a signal indicating a failed authentication;', 'determining a first anti-spoofing representation based on said first candidate fingerprint image; and', 'storing said first anti-spoofing representation., 'when said liveness score indicates a likely spoof2. The method according to claim 1 , further comprising the steps of:acquiring a second candidate fingerprint image indicating a surface topography of said candidate finger probe;determining a second ...

Подробнее
Номер записи: 95
14-03-2019 дата публикации

FACIAL RECOGNITION METHOD AND RELATED PRODUCT

Номер: US20190080188A1
Автор: HUI Fangfang, Wang Lizhong, Zhou Haitao
Принадлежит:

Embodiments of the present disclosure relate to mobile terminal technologies, a facial recognition method and related products are provided. The method includes: acquiring a face image by a mobile terminal; extracting face feature information from the face image and matching the face feature information with a predetermined face feature template by a central processing unit (CPU) of the mobile terminal; performing liveness detection according to the face image by a graphics processing unit of the mobile terminal when the CPU extracts the face feature information from the face image and matches the face feature information with the predetermined face feature template. 1. A facial recognition method , comprising:acquiring a face image by a mobile terminal;extracting face feature information from the face image and matching the face feature information with a predetermined face feature template by a central processing unit of the mobile terminal;performing liveness detection according to the face image by a graphics processing unit of the mobile terminal, when the central processing unit extracts the face feature information from the face image and matches the face feature information with the predetermined face feature template.2. The method according to claim 1 , wherein the liveness detection comprises blink detection and depth of field detection claim 1 , and performing the liveness detection according to the face image comprises:performing the blink detection and the depth of field detection in parallel.3. The method according to claim 1 , wherein acquiring the face image comprises:acquiring more than one face image at different collection angles.4. The method according to claim 3 , wherein acquiring more than one face image at different collection angles comprises:acquiring more than one face image at different collection angles by enabling the mobile terminal to be oriented to a face of a user at the different collection angles.5. The method according to claim 3 ...

Подробнее
Номер записи: 96
31-03-2022 дата публикации

ENHANCED TRAINING METHOD AND APPARATUS FOR IMAGE RECOGNITION MODEL

Номер: US20220101049A1
Автор: Xu Wenhao
Принадлежит: ALIPAY (HANGZHOU) INFORMATION TECHNOLOGY CO., LTD.

Implementations of the present specification provide an enhanced training method for an image recognition model. A predetermined quantity or predetermined proportion of samples are randomly selected from a first sample set as a seed sample for extension to obtain several extended samples. The extended sample is obtained by adding disturbance to an original image without changing an annotation result. In a sample extension process, disturbance values are arranged towards neighborhood in predetermined distribution with a reference pixel as a reference, so that real disturbance can be well simulated. Because the annotation result of the extended sample remains unchanged after the disturbance is added, an image recognition model trained by using the extended sample can well recognize a target recognition result of an original image, thereby improving robustness of the image recognition model. 1. A computer-implemented method , comprising:randomly selecting a predetermined quantity of samples from a first sample set as seed samples, wherein a seed sample of the seed samples corresponds to a seed image and an annotation result for the seed image; separately merging, on at least one image channel, pixels of the seed image of the seed sample with disturbance values to obtain a disturbance image, wherein the disturbance values are arranged in a predetermined distribution with a reference pixel as a center, and the predetermined distribution is related to a distance from each of the pixels to the reference pixel; and', 'constructing an extended sample based on the disturbance image and the annotation result for the seed image, wherein the reference pixel is determined based on a predetermined rule; and, 'obtaining, for each of the seed samples, at least one extended sample based on an extension operation for the seed sample, wherein the extension operation comprisesperforming an enhanced training in an image recognition model using the at least one extended sample as input.2. ...

Подробнее
Номер записи: 97
12-03-2020 дата публикации

LIVENESS DETECTION METHOD, APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM

Номер: US20200082192A1
Автор: Ding Jingting, Li Liang
Принадлежит:

A liveness detection method includes: controlling a display screen to display a color according to a predetermined color display sequence, the color display sequence including at least two different colors; capturing an image of a target object in a color display process of the display screen; acquiring a color change sequence of a face of the target object in the image over time; and determining whether the target object is live based on a matching relationship between the color display sequence and the color change sequence. 1. A liveness detection method , comprising:controlling a display screen to display a color according to a predetermined color display sequence, the color display sequence including at least two different colors;capturing an image of a target object in a color display process of the display screen;acquiring a color change sequence of a face of the target object in the image over time; anddetermining whether the target object is live based on a matching relationship between the color display sequence and the color change sequence.2. The method according to claim 1 , wherein determining whether the target object is live based on a matching relationship between the color display sequence and the color change sequence comprises:if the color display sequence matches the color change sequence, determining that the target object is live; andif the color display sequence does not match the color change sequence, determining that the target object is not live.3. The method according to claim 2 , wherein if the color display sequence matches the color change sequence claim 2 , determining that the target object is live comprises:if the color display sequence matches the color change sequence, determining whether the face of the target object in the image conforms to a three-dimensional color reflection characteristic; andif it is determined that the face of the target object in the image conforms to the three-dimensional color reflection characteristic, ...

Подробнее
Номер записи: 98
25-03-2021 дата публикации

FACE VERIFICATION METHOD AND APPARATUS

Номер: US20210089754A1
Автор: Chang Wonsuk, CHOI Chang Kyu, HAN Jaejoon, HAN Seungju, KIM Deoksang, Shin Dae-Kyu, SON Changyong, SON Jinwoo, YOO Byungin
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold. 1. A mobile device comprising: obtain an image for a user;', 'ascertain whether eyes of the user are closed;', 'select to not perform a user verification when the eyes of the user are ascertained to be closed; and', 'unlock the mobile device, to permit the user to access functions of the mobile device, when the user verification verifies the user., 'one or more processors configured to23-. (canceled)4. The mobile device of claim 9 , wherein the one or more processors are further configured to determine a result of the performed user verification through consideration of a similarity claim 9 , with respect to registered verification information and a result of the implementation of the machine learning verification model.58-. (canceled)9. The mobile device of claim 1 , comprising at least one processor and a memory storing instructions that configure the at least one processor to perform the user verification claim 1 , including implementation of a machine learning verification model with respect to the image.10. The mobile device of claim 9 , wherein the machine learning verification model includes a neural network.1115-. (canceled)16. The mobile device of claim 9 , wherein the at least one processor is a processor of the one or more processors.17 ...

Подробнее
Номер записи: 99
25-03-2021 дата публикации

FACE VERIFICATION METHOD AND APPARATUS

Номер: US20210089755A1
Автор: Chang Wonsuk, CHOI Chang Kyu, HAN Jaejoon, HAN Seungju, KIM Deoksang, Shin Dae-Kyu, SON Changyong, SON Jinwoo, YOO Byungin
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold. 1. A mobile device , comprising: ["obtain an image for a user's face;", 'ascertain whether a user distance from the user to the mobile device is within a threshold range of distances;', 'select to not perform a user verification when the user distance is ascertained to not be within of the threshold range of distances; and', 'when the user verification verifies the user, dependent on the image, unlock the mobile device to permit the user to access functions of the mobile device., 'one or more processors configured to23-. (canceled)4. The mobile device of claim 9 , wherein the one or more processors are further configured to determine a result of the performed user verification through consideration of a similarity claim 9 , with respect to registered verification information and a result of the implementation of the machine learning verification model.58-. (canceled)9. The mobile device of claim 1 , comprising at least one processor and a memory storing instructions that configure the at least one processor to perform the user verification claim 1 , including implementation of a machine learning verification model with respect to the image.10. The mobile device of claim 9 , wherein the machine learning verification model includes a neural network. ...

Подробнее
Номер записи: 100