Cell analyzing apparatus and cell analyzing method

A cell analyzing apparatus includes: a histogram acquirer which is configured to perform measurement of a number of nuclear stained cells, and which, by using a result of the measurement, is configured to acquire a histogram indicating a fluorescence intensity; and an analysis controller which is configured to apply frequency analysis on data of the histogram acquired by the histogram acquirer, and which is configured to determine existence/nonexistence of cancer cells based on a result of the frequency analysis.

Robust Eye Tracking for Scanning Laser Ophthalmoscope

A system, apparatus, and method of obtaining an image of a fundus. Acquiring a reference image of the fundus at a first point in time. Acquiring a target image of the fundus at a second point in time. The target imaging area may overlap with the reference imaging area. An area of the target imaging area may be less than an area of the reference imaging area. Estimating movement of the fundus may be based upon at least the target image and the reference image. Acquiring a narrow field image of the fundus. An area of the narrow field imaging area may be less than the area of the target imaging area. A position of the narrow imaging area on the fundus may be adjusted based on the estimated movement of the fundus.

Optical detection apparatus and methods

An optical object detection apparatus and associated methods. The apparatus may comprise a lens (e.g., fixed-focal length wide aperture lens) and an image sensor. The fixed focal length of the lens may correspond to a depth of field area in front of the lens. When an object enters the depth of field area (e.g., sue to a relative motion between the object and the lens) the object representation on the image sensor plane may be in-focus. Objects outside the depth of field area may be out of focus. In-focus representations of objects may be characterized by a greater contrast parameter compared to out of focus representations. One or more images provided by the detection apparatus may be analyzed in order to determine useful information (e.g., an image contrast parameter) of a given image. Based on the image contrast meeting one or more criteria, a detection indication may be produced.

Biometrics authentication device and method

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.

Method for quantifying the morphological regularity degree of the pellucid zone in embryos and oocytes

The present invention refers to a method for calculating a shape factor indicative of the evenness of the pellucid zone thickness of a biological structure and to a method for evaluating the evenness of the pellucid zone thickness of a biological structure through said shape factor.

Component type automatic distinguishing method, component type automatic distinguishing system, image processing component data creation method, and image processing component data creation system

Characteristic data of a relevant component is extracted from a component image captured by camera, and the extracted characteristic data is compared with reference characteristic data of multiple types of component registered in a database to distinguish a type of component for which the two sets of data match most closely. As a result of this, a power spectrum image is created by applying an FFT for each scanning line to a lead presence candidate region corresponding to a candidate for a lead being present in a component image distinguished as an odd form component. Further, an HLAC characteristic is calculated from the power spectrum image in order to extract a periodic characteristic of the power spectrum image, and a connector component with leads is distinguished from an odd form component by learning a characteristic amount of the LAC characteristic using an SVM.

Virtualization of Tangible Interface Objects

An example system includes a stand configured to position a computing device proximate to a physical activity surface. The system further includes a video capture device, a detector, and an activity application. The video capture device is coupled for communication with the computing device and is adapted to capture a video stream that includes an activity scene of the physical activity surface and one or more interface objects physically interactable with by a user. The detector is executable to detect motion in the activity scene based on the processing and, responsive to detecting the motion, process the video stream to detect one or more interface objects included in the activity scene of the physical activity surface. The activity application is executable to present virtual information on a display of the computing device based on the one or more detected interface objects.

Method, apparatus, and terminal for obtaining vital sign data of target object

Embodiments of the present invention provide a method for obtaining vital sign data of a target object, including: obtaining a 3D depth image of a target object; obtaining, according to depth values of pixels in the 3D depth image of the target object, framework parameters of the target object and a graphic contour of the target object, where the depth value, is obtained according to the distance information, indicates a distance between a point on the target object and the imaging device; retrieving a 3D model matching the framework parameters of the target object and the graphic contour of the target object from a 3D model library, and obtaining a parameter ratio of the 3D model; obtaining at least one real size of the target object; and obtaining vital sign data of the target object according to the parameter ratio of the 3D model and the at least one real size.

Video encoding method using offset adjustments according to pixel classification and apparatus therefor, video decoding method and apparatus therefor

A video encoding method and apparatus and video decoding method and apparatus generate a restored image having a minimum error with respect to an original image based on offset merge information indicating whether offset parameters of a current block and at least one neighboring block from among blocks of video are identical.

Method of reconstituting cellular spectra useful for detecting cellular disorders

Embodiments of the present disclosure provides improved methods for determining the presence of abnormalities in exfoliated cells. In one embodiment, the present disclosure provides methods for reconstructing cellular spectrum of a cell sample by creating a spectral map of the cellular sample, generating a binary mask of the spectral map, removing edge artifacts from each cell, and co-adding spectral data of each pixel corresponding to the cell to reconstruct the spectrum of each cell.

Video encoding method using offset adjustments according to pixel classification and apparatus therefor, video decoding method and apparatus therefor

A video encoding method and apparatus and video decoding method and apparatus generate a restored image having a minimum error with respect to an original image based on offset merge information indicating whether offset parameters of a current block and at least one neighboring block from among blocks of video are identical.

Object throughput using trained machine learning models

Disclosed are techniques for determining object throughput. A method may include obtaining first data representing a first image corresponding to a first time, identifying a first portion of the first data that depicts a first object at a first location, obtaining second data representing a second image corresponding to a second time, identifying a second portion of the second data that depicts the first object at a second location, obtaining third data indicating a counting threshold, determining based at least on the third data and the second location, that the first object satisfies the counting threshold, generating a value indicating a number of objects satisfying the counting threshold, the number of objects including the first object, generating a data value indicating a throughput of the number of objects based on the value indicating the number of objects satisfying the counting threshold and elapsed time between the first and second times.

Self-moving robot

The invention discloses a self-moving robot, comprising a light emitter, emitting light in a specific wavelength range to the ground; an image capturing device, matched with the light emitter to receive the light in a specific wavelength range to form an image based on the light in a specific wavelength range; and the controller comprises a ground type recognizing module, which extracts features in the image to recognize the ground type in the image. By disposing the light emitter and the image capturing device which are matched to emit and receive the light in a specific wavelength range, an influence of the ambient light on the image is reduced, such that the self-moving robot can accurately recognize the ground type at every moment and in every location, even at night when there is no light source.

Method and apparatus with fingerprint verification

A fingerprint verification method and apparatus is disclosed. The fingerprint verification method may include obtaining an input fingerprint image, determining a matching region between the input fingerprint image and a registered fingerprint image, determining a similarity corresponding to the matching region, representing a determined indication of similarities between the input fingerprint image and the registered fingerprint image, relating the determined similarity to the matching region as represented in a matching region-based similarity, determining a result of a verification of the input fingerprint image based on the matching region-based similarity, and indicating the result of the verification.

Method and system for visualizing a correlation mark using an electronic device

A mobile electronic device is used to decode a printed correlation mark. The device receives an image of a printed correlation mark, identifies a decoding template, applies the template to detect hidden content within the printed correlation mark, and outputs an image of the detected hidden content on the display. The device may enhance the image before presenting it on the display.

IMAGE PROCESSING APPARATUS AND METHOD FOR USE IN AN AUTOFOCUS SYSTEM

An image processing apparatus for determining a focused output image in a passive autofocus system is configured to retrieve a set of input images and compute a baseline estimate for at least one input image. The baseline estimate represents image structures in the input image. The image structures have a length scale larger than a predetermined image feature length scale. The image processing apparatus is further configured to compute a set of output images, wherein each output image of the set of output images is computed based on one of a different input image of the set of input images and the at least one baseline estimate for the different input image and the at least one baseline estimate for a respective different input image. The image processing apparatus is further configured to determine one output image of the set of output images as the focused output image. 1. An image processing apparatus for determining a focused output image a passive autofocus system , the image processing apparatus being configured to:retrieve a set of input images;compute at least one baseline estimate for at least one input image of the set of input images, the at least one baseline estimate representing image structures in the at least one input image, the image structures having a length scale larger than a predetermined image feature length scale;compute a set of output images;compute each output image of the set of output images based on one of a different input image of the set of input images and the at least one baseline estimate for the different input image and the at least one baseline estimate for a respective different input image; anddetermine one output image of the set of output images as the focused output image.2. The image processing apparatus according to claim 1 , wherein the image processing apparatus is configured to compute each output image of the set of output images based on a different input image and the at least one baseline estimate for the ...

System and method for biometric identification

The present invention relates to a method and system for generating and comparing a biometric singular signature of a person comprising the steps of a) obtaining a first image of a person; b) obtaining a hair portion image of the person; c) transforming the hair portion image into its frequency domain image and optionally saving said frequency domain image in a database. Additional applications associated to the method are disclosed.

Vehicle position estimation device, method and computer readable recording medium

Sensor information acquisition section acquires surrounding information including three dimensional information of respective surrounding positions of subject vehicle, and positional information of subject vehicle. Road surface information extraction section generates road surface image in which acquired surrounding information is projected onto road surface on which subject vehicle is travelling. Environment image generation section generates environment image in which three dimensional information of respective surrounding positions included in surrounding information has been appended to positions corresponding to surrounding positions in generated road surface image. Based on acquired positional information of subject vehicle, stored image acquisition section acquires stored image corresponding to positional information of subject vehicle from database. Image matching section matches generated environment image against acquired stored image. Estimation section estimates amount of displacement in positional information of subject vehicle based on obtained matching result.

Method, apparatus, and program for judging grid quality

An image obtaining section obtains a radiation image that includes a periodic pattern of a grid. A frequency analyzing section performs frequency analysis on the radiation image to obtain a frequency spectrum of the radiation image. A peak determining section determines a peak within the frequency spectrum to be a target of processing. A first judging section measures the width of the peak which is the target of processing, and judges the quality of the grid based on the measured width of the peak.

Spoof detection using multiple image acquisition devices

The technology described in this document can be embodied in a method that includes receiving from a sensor, information indicative of an environmental condition. The method also includes receiving first information indicative of whether or not a first image captured by a first image acquisition device corresponds to an alternative representation of a live person, and receiving second information indicative of whether or not a second image captured by a second image acquisition device corresponds to the alternative representation. The first information and the second information are combined in a weighted combination, the corresponding weights being assigned in accordance with the environmental condition. A determination is made, based on the weighted combination, that a subject in the first and second images is an alternative representation of a live person, and in response, access to the secure system is prevented.

Video encoding method using offset adjustments according to pixel classification and apparatus therefor, video decoding method and apparatus therefor

A video encoding method and apparatus and video decoding method and apparatus generate a restored image having a minimum error with respect to an original image based on offset merge information indicating whether offset parameters of a current block and at least one neighboring block from among blocks of video are identical.

Metrology method and apparatus for of determining a complex-valued field

Disclosed is a method of determining a complex-valued field relating to a sample measured using an imaging system. The method comprises obtaining image data relating to a series of images of the sample, imaged at an image plane of the imaging system, and for which at least two different modulation functions are imposed in a Fourier plane of the imaging system; and determining the complex-valued field from the imaging data based on the imposed modulation functions.

Image parameter calculating method, object tracking method, and image parameter calculating system

An image parameter calculating method comprising: (a) transforming a spatial domain target image to a frequency domain target image; (b) multiplying the frequency domain target image with a frequency domain reference image to acquire a frequency domain multiplying result; and (c) calculating at least one peak location of the spatial domain target image according to the frequency domain multiplying result.

Cell Contour Formation Apparatus and Method of the Same, and Non-Transitory Contour Readable Storage Medium Storing a Cell Contour Formation Program

An cell contour formation apparatus includes a cell image acquiring unit, a subband image creating unit, a features calculating unit, a correcting unit, a contour forming unit. The subband image creating unit creates subband images including a low frequency image and a high frequency image. The features calculating unit calculates a local texture features from the high frequency image. The correcting unit corrects the high frequency image on the basis of the pixel value of the low frequency image and the texture features. The contour forming unit forms contours of cells included in the cell group on the basis of the corrected high frequency image.

Temporal fusion of multimodal data from multiple data acquisition systems to automatically recognize and classify an action

A multimodal sensing system includes various devices that work together to automatically classify an action. A video camera captures a sequence of digital images. At least one other sensor device captures other sensed data (e.g., motion data). The system will extract video features from the digital images so that each extracted image feature is associated with a time period. It will extract other features from the other sensed data so that each extracted other feature is associated with a time period. The system will fuse a group of the extracted video features and a group of the extracted other features to create a fused feature representation for a time period. It will then analyze the fused feature representation to identify a class, access a data store of classes and actions to identify an action that is associated with the class, and save the identified action to a memory device.

Optical coin discrimination systems and methods for use with consumer-operated kiosks and the like

Systems and associated methods for optical coin discrimination are disclosed herein. In one embodiment, a method for discriminating coins includes obtaining a digital image of a coin, identifying the outline of the coin using a suitable algorithm, and determining the diameter of the coin using the outline of the coin. The method of this embodiment further includes generating a rectangular image of the coin using, for example, a log-polar transform, generating a series of, for example, Fourier transforms from the rectangular image, and identifying spectral peak locations and intensities in the Fourier transform results. The diameter of the coin, spectral peak location, spectral peak intensity of the coin and/or other aspects of the coin can then be compared to known values for different coins to discriminate the coin.

Target Detection, Tracking, and Classification in Compressive Measurement Domain

The present invention is to provide a method and system using compressed data directly for target tracking and target classification in videos. The present invention uses a video imager to generate compressive measurements, and a random subsampling operator to compress the video data. It uses a Gaussian Mixture Model (GMM) for target detection and manual location of the target and putting a bounding box around the targets in the first frame is not required. It further applies a saliency-based algorithm to re-center the captured target. This re-centering process can be repeated multiple times and each application of re-centering will improve over the previous one. A pixel completion algorithm is used to fill in the missing pixels for the captured target area. A Sparse Representation Classification (SRC) for target classification. Both the target templates in a dictionary and captured targets are transformed to the frequency domain using Fast Fourier Transform (FFT).

Imaging-Type Heart Rate Monitoring Device and Method Thereof

The present invention provides an imaging-type heart rate monitoring device and method thereof. It acquires the human image information tracks the target area in the human image information, and extracts the target image in the target area. It transforms the human image information through the first frequency domain transform. It filters the residual noise of the continuous wavelet transform information. It rebuilds the residual noise filtered information by the continuous wavelet transform. It transforms the continuous wavelet transform rebuilt information by the Fourier transform. It obtains a heart rate value through the second frequency domain transformed information.

Methods and a computing device for determining whether a mark is genuine

Methods for determining whether a mark is genuine are described. According to various implementations, a computing device (or logic circuitry thereof) receives (e.g., via a camera or via a communication network) an image of a candidate mark (e.g., a one-dimensional or two-dimensional barcode), uses the image to make measurements of a characteristic of a feature of the candidate mark, resulting in a profile for that feature. The computing device filters out, from the feature profile, all spatial frequency components that are indicated to be sibling frequency components. In some embodiments, the computing device carries out the reverse procedure, and filters out all spatial frequency components except for those indicated to be sibling frequency components.

Machine vision-based method and system for aircraft docking guidance and aircraft type identification

A machine vision-based method and system for aircraft docking guidance and aircraft type identification, comprising: S1, a monitoring scenario is divided into different information processing function areas; S2 a captured image is pre-processed; S3 the engine and the front wheel of an aircraft are identified in the image, so as to confirm that the aircraft has appeared in the image; S4 continuous tracking and real-time updating are performed on the image of the engine and the front wheel of the aircraft captured in step S3; S5 real-time positioning of the aircraft is implemented and the degree of deviation of the aircraft with respect to a guide line and the distance with respect to a stop line are accurately determined; S6 the degree of deviation of the aircraft with respect to the guide line and the distance with respect to the stop line of step S5 are outputted and displayed.

A method and device for retrieving biomechanical parameters of a stride

A method for determining biomechanical parameters of the stride of a runner, using an accelerometer device on the wrist, on the upper arm, on the head or on the shoe, comprising the steps of measuring an initial sequence of acceleration data in at least the vertical direction using said accelerometer device; identifying in said initial sequence of acceleration data at least one frequency component caused by relative motion of the accelerometer device relative to the runner center of masse; attenuating said frequency component, so as to determine a modified sequence of acceleration data; determining said biomechanical parameters from said modified sequence of acceleration data.

Point spread function classification using structural properties

A method for classifying a test image ( 16 ) includes the steps of building a classifier ( 300 ), and classifying the test image ( 16 ) with the classifier ( 300 ). After the test image ( 16 ) is classified, the test image ( 16 ) can be subsequently processed (e.g. deblurred) with improved accuracy. The classifier ( 300 ) can classify and distinguish between PSF features associated with motion blurred images, and PSF features associate with defocus blurred images. The classifier ( 300 ) can be built using a plurality of training images ( 304 ), and extracting one or more training features from each the training images ( 304 ). The PSF features can include image moments of the point spread function, and/or geometric features of the point spread function.

Self ensembling techniques for generating magnetic resonance images from spatial frequency data

Techniques for generating magnetic resonance (MR) images of a subject from MR data obtained by a magnetic resonance imaging (MRI) system, the techniques including: obtaining input MR data obtained by imaging the subject using the MRI system; generating a plurality of transformed input MR data instances by applying a respective first plurality of transformations to the input MR data; generating a plurality of MR images from the plurality of transformed input MR data instances and the input MR data using a non-linear MR image reconstruction technique; generating an ensembled MR image from the plurality of MR images at least in part by: applying a second plurality of transformations to the plurality of MR images to obtain a plurality of transformed MR images; and combining the plurality of transformed MR images to obtain the ensembled MR image; and outputting the ensembled MR image.

Methods, systems, and media for evaluating images

A method may include obtaining an image including a face. The method may further include determining at least one time domain feature related to the face in the image and at least one frequency domain information related to the face in the image. The method may further include evaluating the quality of the image based on the at least one time domain feature and the frequency domain information.

Systems and methods for radar based face authentication anti-spoofing

A method and electronic device for radar-based face authentication anti-spoofing for determining access to the electronic device. The electronic device includes a radar transceiver and at least one processor. The at least one processor is configured to transmit, via the transceiver, a first set of signals, generate a channel impulse response (CIR) based on receipt of reflections of the first set of signals, detect a first CIR tap in the CIR, determine a selection of CIR data based on the detected first CIR tap, determine a profile matching metric based on comparison of the selection of CIR data to a set of predetermined reference signals, and determine whether to allow access to the electronic device based on comparison of the profile matching metric to a profile matching threshold.

Instantaneous search and comparison method for large-scale distributed palm vein micro-feature data

The invention proposes an instantaneous search and comparison method for large-scale distributed palm vein micro-feature data, which consists of three parts: 1) feature extraction and calculation of palm vein micro-feature images; 2) building a feature database; 3) search and comparison. The technical solution provided by this invention, referring to the idea of GIS and web search method, is applied to the search and comparison of the palm vein micro-feature data, which enables instantaneous recognition on massive palm vein micro-feature data under large-scale, large-traffic and high-frequency application scenarios, and solves the technical problem that traditional palm vein recognition methods can not be applied to large-scale and large-traffic scenarios due to low speed thereof.

Method and apparatus for detecting defect pattern on wafer based on unsupervised learning

A method for clustering based on unsupervised learning according to an embodiment of the invention enables clustering for newly generated patterns and is robust against noise, and does not require tagging for training data. According to one or more embodiments of the invention, noise is accurately removed using three-dimensional stacked spatial auto-correlation, and multivariate spatial probability distribution values and polar coordinate system spatial probability distribution values are used as learning features for clustering model generation, making them robust to noise, rotation, and fine unusual shapes. In addition, clusters resulting from clustering are classified into multi-level clusters, and stochastic automatic evaluation of normal/defect clusters is possible only with measurement data without a label.

Digital identifier for a document

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining image data of an identification (ID) document and identifying a pattern of the ID document based on analysis of the image data against a predefined patterns for a particular type of document. An identifier engine of the system computes a frequency metric that defines how often the pattern reoccurs at the ID document and generates a unique identifier for the ID document based on the computed frequency metric. The unique identifier is stored at a digital fingerprint database of the system as a digital fingerprint for the ID document.

Image parameter calculating method, object tracking method, and image parameter calculating system

An image parameter calculating method comprising: (a) transforming a spatial domain target image to a frequency domain target image; (b) multiplying the frequency domain target image with a frequency domain reference image to acquire a frequency domain multiplying result; and (c) calculating at least one peak location of the spatial domain target image according to the frequency domain multiplying result.

Process for extracting periodic features from images by template matching

A method for extracting array elements from an image of an array, the array being contained within a well of a substrate is provided. The method comprises detecting coordinate locations of frequency spectrum peaks in the image by establishing local regions of the image, each local region containing a distinct frequency spectrum peak of the image; determining grid spacing and rotational characteristics of the image by analyzing the detected coordinate locations of the frequency spectrum peaks with a Fourier transform analysis; using the grid spacing and rotational characteristics of the image to generate a well template, the well template accounting for each array element's relative location within the well; and cross-correlating the generated well template with the image of the array to determine matched locations, the cross-correlated well template accounting for each array element's actual coordinate location within the well.

Method for encoding video using bias control according to pixel classification and device therefor, video decoding method and device therefor

FIELD: information technology. SUBSTANCE: invention relates to means of encoding and decoding video. parsing offset merge information indicating whether offset parameters of a current block and offset parameters of at least one neighbouring block from among video blocks are identical; restoring an offset type and offset values of current block from offset parameter of current block based on offset merge information; determining an edge class or a pixel value band of a restored pixel of current block based on an edge type or a pixel value band type of current block indicating offset type; and determining an offset value corresponding to edge class or pixel value band of restored pixel from restored offset values of current block and adjusting a pixel value of restored pixel of current block according to restored offset values of current block. Devices implement encoding and decoding methods. EFFECT: technical result is generating restored image having minimum error relative to original image. 15 cl, 20 dwg, 1 tbl РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 581 553 C2 (51) МПК H04N 19/00 (2014.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ (21)(22) Заявка: ИЗОБРЕТЕНИЯ К ПАТЕНТУ 2014102576/08, 27.06.2012 (24) Дата начала отсчета срока действия патента: 27.06.2012 (72) Автор(ы): АЛШИНА Елена (KR), АЛШИН Александр (KR) 28.06.2011 US 61/502,018 (43) Дата публикации заявки: 10.08.2015 Бюл. № 22 R U (73) Патентообладатель(и): САМСУНГ ЭЛЕКТРОНИКС КО., ЛТД. (KR) Приоритет(ы): (30) Конвенционный приоритет: (45) Опубликовано: 20.04.2016 Бюл. № 11 (85) Дата начала рассмотрения заявки PCT на национальной фазе: 28.01.2014 2 5 8 1 5 5 3 (56) Список документов, цитированных в отчете о поиске: US 2010/0111182 A1, 06.05.2010. US 2005/0117810 A1, 02.06.2005. US6043838 A, 28.03.2000. US 4661862, 28.04.1987. RU 2402811 C2, 27.10.2010. RU 2313190 C2, 20.07.2007. RU 2300144 C2, 27.05.2007. KR 2012/005086 (27.06.2012) C 2 C 2 (86) Заявка PCT: (87) Публикация заявки PCT: ...

Method of video coding using offset regulations according to pixel classification and device for this, method and device of video decoding for this

FIELD: physics. SUBSTANCE: in the video decoding method: parsing the information of the enterprises of the displacements indicates that whether offset parameters of a current block and, at least, one neighboring block from among blocks of video are identical to each other, from the received bitstream; restoring an offset type and offset values among the offset parameters of the current block based on information of combining displacements; the class definition of the edge or strip pikselnyh values of the restored pixel based on the edge type or the band type pixel values of the current block indicating the offset type; and determining offset values corresponding to the edge class or the band pixel values of the restored pixel of the offset values and the regulation of pixel value of the restored pixel according to the offset value. EFFECT: forming a reconstructed image having a minimum error relative to the original image. 20 dwg, 1 tbl РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 632 139 C1 (51) МПК H04N 19/00 (2014.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (21)(22) Заявка: 2016108975, 27.06.2012 (24) Дата начала отсчета срока действия патента: 27.06.2012 (72) Автор(ы): АЛШИНА Елена (KR), АЛШИН Александр (KR) 02.10.2017 Приоритет(ы): (30) Конвенционный приоритет: (56) Список документов, цитированных в отчете о поиске: US 2010/0111182 A1, 06.05.2010. US 28.06.2011 US 61/502,018 2014102576 28.06.2011 2005/0117810 A1, 02.06.2005. US6043838 A, 28.03.2000. US 4661862, 28.04.1987. RU 2402811 C2, 27.10.2010. RU 2313190 C2, 20.07.2007. RU 2300144 C2, 27.05.2007. (45) Опубликовано: 02.10.2017 Бюл. № 28 2 6 3 2 1 3 9 R U (54) СПОСОБ КОДИРОВАНИЯ ВИДЕО С ИСПОЛЬЗОВАНИЕМ РЕГУЛИРОВАНИЙ СМЕЩЕНИЯ СОГЛАСНО КЛАССИФИКАЦИИ ПИКСЕЛОВ И УСТРОЙСТВО ДЛЯ ЭТОГО, СПОСОБ И УСТРОЙСТВО ДЕКОДИРОВАНИЯ ВИДЕО ДЛЯ ЭТОГО (57) Реферат: Изобретение относится к средствам значений смещения из числа параметров кодирования видео, а также декодирования видео. ...

Method and apparatus for video encoding with adjusting offsets based on pixel classification, method and apparatus for video decoding with adjusting offsets based on pixel classification

본 발명은, 원본영상과의 오차가 최소화되는 복원영상을 생성하기 위한 비디오 부호화 방법 및 그 장치, 비디오 복호화 방법 및 그 장치를 제안한다. 본 발명에 따라, 수신한 비트스트림으로부터 현재 블록의 오프셋 병합 정보를 파싱하고, 오프셋 병합 정보에 기초하여 현재 블록의 오프셋 파라미터 중 오프셋 타입 및 오프셋값들을 복원하고, 오프셋 타입이 나타내는 현재 블록의 에지 타입 또는 픽셀값 밴드 타입에 기초하여 결정된 복원픽셀의 에지 클래스 또는 픽셀값 밴드에 대응하는 오프셋값을 오프셋값들로부터 선택하여 복원픽셀의 픽셀값을 오프셋만큼 조정하는 비디오 복호화 방법이 개시된다. The present invention proposes a video encoding method and apparatus, a video decoding method, and an apparatus thereof for generating a reconstructed image with a minimum error from an original image. According to the present invention, the offset merging information of the current block is parsed from the received bit stream, the offset type and offset values of the offset parameters of the current block are restored based on the offset merging information, the edge type of the current block indicated by the offset type Or an offset value corresponding to an edge class or a pixel value band of a reconstructed pixel determined based on a pixel value band type is selected from offset values and the pixel value of the reconstructed pixel is adjusted by an offset.

Two-dimensional identification method for SPR (surface plasmon resonance) and waveguide mixed absorption spectrum characteristic position

该发明公开了一种SPR与波导混合吸收谱特征位置的二维识别方法。其特点在于对二维表面等离子体(Surface plasmon resonance,SPR)多模式吸收谱对应的各激发角进行高精度自动提取。所述方法包括：通过互相关方法粗略定位出通光孔径所在圆位置，并将物镜后焦面共轭面上的图像传感器采集到的图像裁剪为包含通光孔径所在圆的矩形图像；通过局部二值化提高通光孔径和通光孔径外部分的对比度并通过互相关方法精确定位通光孔径位置，将通光孔径所在圆外图像信息移除，得到只包含多模式吸收谱对应的各激发角所在圆信息的图像；之后通过互相关方法确定多模式吸收谱对应的各激发角所在圆的圆心，通过分区域的灰度统计方法确定多模式吸收谱对应的各激发角的位置。

Device for the machine recognition of characters with an autocorrelation function generator

Image-based model-based weighing systems and methods

Method for encoding video using bias control according to pixel classification and device therefor, video decoding method and device therefor

FIELD: data processing.SUBSTANCE: invention relates to video decoding. Video decoding method includes: syntactic analysis of offset combining information indicating whether or not the offset parameters of the current block and at least one neighboring block from number of video blocks are identical to each other, from the received bitstream; recovery of the offset type and offset values from among the offset parameters of the current block based on the offset combining information; the definition of an edge class or strip of pixel values of the reconstructed pixel based on the edge type or strip type of pixel values of the current block indicating the type of offset; and determining an offset value corresponding to the edge class or the pixel value band of the recovered pixel from the offset values and adjusting the pixel value of the recovered pixel according to the offset value.EFFECT: technical result is to minimize the error between the original image and the restored image.1 cl, 1 tbl, 20 dwg РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 663 331 C1 (51) МПК H04N 19/00 (2014.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (52) СПК H04N 19/00 (2006.01); H04N 19/10 (2006.01) (21)(22) Заявка: 2017133113, 22.09.2017 (24) Дата начала отсчета срока действия патента: (73) Патентообладатель(и): САМСУНГ ЭЛЕКТРОНИКС КО., ЛТД. (KR) Дата регистрации: 03.08.2018 28.06.2011 US 61/502,018 Номер и дата приоритета первоначальной заявки, из которой данная заявка выделена: 2016108975 28.06.2011 (56) Список документов, цитированных в отчете о поиске: US 2010/0111182 A1, 06.05.2010. US 2005/0117810 A1, 02.06.2005. US 6043838, 28.03.2000. RU 2007103160, 10.08.2005. RU 2004125168 A, 27.01.2006. 2 6 6 3 3 3 1 R U Адрес для переписки: 129090, Москва, ул. Большая Спасская, д. 25, строение 3, ООО "Юридическая фирма Городисский и Партнеры" (54) СПОСОБ КОДИРОВАНИЯ ВИДЕО С ИСПОЛЬЗОВАНИЕМ РЕГУЛИРОВАНИЙ СМЕЩЕНИЯ СОГЛАСНО КЛАССИФИКАЦИИ ПИКСЕЛОВ И ...

Device and method for radial and angular or angle incrementation image analysis in conformity with content of form and coordination

FIELD: spatial light modulator, in particular, spatial light modulator with radially oriented active light modulation sectors for radial and angular light ray analysis, including Fourier transformation optical images, determining of characteristics of search, coordination or identification of image form content. SUBSTANCE: segmented radial spatial light modulator has active optical area, containing a set of extended radially active optical modulator sectors, positioned on different angular directions relatively to central axis. Aforementioned light modulator is used during separation and localization of parts of optical images of Fourier transformation from images for determining image characteristics by means of form for registration, preservation, extraction, search and comparison to other images for coordination or almost full coordination. Collateral images may be added to images for increasing optical strength in optical image of Fourier transformation without addition of new content of form and for successive comparison to characteristics of form of another image for identification of almost full coordination in addition to coordination. EFFECT: increased resolution of spatial f of image along each angular direction. 3 cl, 29 dwg ÐÎÑÑÈÉÑÊÀß ÔÅÄÅÐÀÖÈß RU (19) (11) 2 300 144 (13) C2 (51) ÌÏÊ G06K 9/58 (2006.01) G02B 27/46 (2006.01) ÔÅÄÅÐÀËÜÍÀß ÑËÓÆÁÀ ÏÎ ÈÍÒÅËËÅÊÒÓÀËÜÍÎÉ ÑÎÁÑÒÂÅÍÍÎÑÒÈ, ÏÀÒÅÍÒÀÌ È ÒÎÂÀÐÍÛÌ ÇÍÀÊÀÌ (12) ÎÏÈÑÀÍÈÅ ÈÇÎÁÐÅÒÅÍÈß Ê ÏÀÒÅÍÒÓ (21), (22) Çà âêà: 2004125168/09, 16.01.2003 (72) Àâòîð(û): ÊÐÈËË Ðèê (US) (24) Äàòà íà÷àëà îòñ÷åòà ñðîêà äåéñòâè ïàòåíòà: 16.01.2003 (73) Ïàòåíòîîáëàäàòåëü(è): ËÓÊ ÄÀÉÍÝÌÈÊÑ, ÈÍÊ. (US) R U (30) Êîíâåíöèîííûé ïðèîðèòåò: 18.01.2002 US 10/051,364 (43) Äàòà ïóáëèêàöèè çà âêè: 27.01.2006 (45) Îïóáëèêîâàíî: 27.05.2007 Áþë. ¹ 15 2 3 0 0 1 4 4 (56) Ñïèñîê äîêóìåíòîâ, öèòèðîâàííûõ â îò÷åòå î ïîèñêå: WO 01/73681 A1, 04.10.2001. WO 00/75967 A1, 14.12.2000. SU 1811628 A3, 23.04.1993. SU 1721616 A1, 23.03.1992. WO 00/05677 A1, 03. ...

Information processing device, information processing method, and recording medium

화상 입력부(71)는 유저를 촬상한 화상 데이터를 입력한다. 추출부(72)는 화상 입력부(71)에 의해 입력된 화상 데이터에 포함되는 유저의 손에 상당하는 영역을 추출한다. 판정부(73)는 추출부(72)에 의해 추출된 유저의 손에 상당하는 영역이 정지 상태에 있는지 여부를 판정한다. 인식부(74)는 판정부(73)에 의해 유저의 손에 상당하는 영역이 정지 상태에 있다고 판정된 경우에, 추출부(72)에 의해 추출된 유저의 손에 상당하는 영역의 형상을 인식한다. 한편, 인식부(74)는 판정부(73)에 의해 유저의 손에 상당하는 영역이 정지 상태에 있지 않다고 판정된 경우에, 추출부(72)에 의해 추출된 유저의 손에 상당하는 영역의 움직임을 인식한다. 입력부(75)는 인식부(74)에 의해 인식된 형상 또는 움직임에 대응된 데이터를 입력한다. The image input unit 71 inputs image data of the user. The extracting unit 72 extracts an area corresponding to the hand of the user included in the image data input by the image input unit 71. [ The judging unit 73 judges whether or not the area corresponding to the hand of the user extracted by the extracting unit 72 is in a stop state. The recognizing unit 74 recognizes the shape of the area corresponding to the user's hand extracted by the extracting unit 72 when the determining unit 73 determines that the area corresponding to the user's hand is in the stopped state do. On the other hand, when it is determined by the determination section 73 that the area corresponding to the user's hand is not in the stop state, the recognition section 74 determines that the area corresponding to the hand of the user extracted by the extraction section 72 Recognize movement. The input unit 75 inputs data corresponding to the shape or motion recognized by the recognition unit 74. [

Video decoding method using offset adjustment according to pixel classification and apparatus therefor

提供了一种根据像素分类使用偏移调整的视频解码方法及其设备。所述视频解码方法包括：从接收的比特流解析指示视频的多个块之中的当前块和至少一个邻近块的偏移参数是否彼此相同的偏移合并信息；基于偏移合并信息恢复当前块的偏移参数之中的偏移类型和偏移值；基于当前块的指示偏移类型的边缘类型或像素值带类型来确定恢复的像素的边缘分类或像素值带；以及从恢复的偏移值确定与恢复的像素的边缘分类或像素值带相应的偏移值并根据确定的偏移值调整恢复的像素的像素值。

System and related method for measuring optical characteristics of glass sheet on process line

FIELD: measuring equipment. SUBSTANCE: invention relates to a method and a device for measuring both the optical distortion of a transmitted image and small defects in glass sheets, embedded in a process line in a system of glass sheet processing. A system installed on a process line for measuring optical characteristics of a glass sheet, installed in a system for the manufacture of glass sheets, is claimed, containing one or more processing stations and one or more conveyors for transporting a glass sheet from station to station during processing, while the system installed on the process line contains: a device for measuring small optical or view-obstructing defects in the first selected area of a glass sheet, containing the first lumen screen containing contrast elements arranged in the form of a given pattern. It also contains the first chamber for obtaining the first image data set containing at least one image of the first lumen screen associated with the first selected area of the glass sheet, when moving the glass sheet to a pre-selected position on the conveyor between the chamber and the first lumen screen, and a computing device containing at least one processor programmed to implement logic for receiving the first image data set, generating an intensity map from the first image data set and identifying and locating small defects from the intensity map. In this case, the logic for generating an intensity map from the first image data set includes logic for generating a Fourier transform of image data, demodulating a Fourier transform, generating an inverse Fourier transform of demodulated data, extracting a two-dimensional complex number associated with each pixel, while the specified complex number has a phase component and a magnitude component, and generating an intensity map of the inverse Fourier transform by determining the square root of the sum of squares of the imaginary part of the two-dimensional complex number and the real part of the two- ...

Metrology method and apparatus for of determining a complex-valued field

Disclosed is a method of determining a complex-valued field relating to a sample measured using an imaging system. The method comprises obtaining image data relating to a series of images of the sample, imaged at an image plane of the imaging system, and for which at least two different modulation functions are imposed in a Fourier plane of the imaging system; and determining the complex-valued field from the imaging data based on the imposed modulation functions.

Method and system for inspecting a periodic structure

Es werden ein Verfahren und ein System zur Inspektion einer periodischen Struktur (1) durch einen optischen Bildaufnehmer mit einer Pixelstruktur (2) beschrieben, dessen aufgenommenes Bild (6) mit einem fehlerfreien Referenzbild (4) der periodischen Struktur (1) verglichen wird. Um die Fehler mit einfachen Mitteln zuverlässig erkennen zu können, wird in dem Referenzbild (4) an mindestens einer Position (X, Y) die Phasenlage (Phase X, Phase Y) der periodischen Struktur (1) zu der Pixelstruktur (2) des optischen Bildaufnehmers ermittelt. Das aufgenommene Bild (6) wird in Inspektionsbereiche (7) eingeteilt und für jeden Inspektionsbereich (7) wird die Phasenlage (Phase X, Phase Y) der periodischen Struktur (1) zu der Pixelstruktur (2) des optischen Bildaufnehmers ermittelt. Für den Vergleich eines Inspektionsbereichs (7) mit dem Referenzbild (4) wird dann ein Referenzbildbereich (8) ausgewählt, dessen Phasenlage (Phase X, Phase Y) mit dem Inspektionsbereich (7) korrespondiert. It become a procedure and a system for the inspection of a periodic Structure (1) by an optical image pickup having a pixel structure (2), the recorded image (6) with a faultless Reference image (4) of the periodic structure (1) is compared. To be able to reliably detect the errors with simple means is in the reference image (4) at at least one position (X, Y) the Phase angle (phase X, phase Y) of the periodic structure (1) to the Pixel structure (2) of the optical image sensor determined. The recorded Picture (6) is divided into inspection areas (7) and for each Inspection area (7) is the phase position (phase X, phase Y) of the Periodic structure (1) to the pixel structure (2) of the optical Image recorder determined. For the comparison of an inspection area (7) with the reference image (4), a reference image area (8) is then selected whose phase position (phase X, phase Y) corresponds to the inspection area (7).

Method and apparatus for user authentication using face image

본 발명은 얼굴 영상을 이용한 사용자 인증 방법 및 장치에 관한 것으로, (a) 정규화된 공간 영역의 얼굴 영상을 주파수 영역 데이터로 변환하는 단계; (b) 상기 변환된 주파수 영역 데이터로부터 에너지 밀집 영역 정보를 통하여 유효 변환 계수들을 추출하는 단계; (c) 상기 추출된 유효 변환 계수들로부터 특징 벡터를 추출하는 단계; 및 (d) 상기 추출된 특징 벡터와 기 등록된 특징 벡터를 비교하여 사용자 인증을 수행하는 단계로 구성되어, 최소한의 데이터 차원으로 얼굴 영상을 이용한 사용자 인증이 수행되기 때문에 속도와 정확도가 향상되는 사용자 인증 방법 및 장치를 제공할 수 있다. The present invention relates to a user authentication method and apparatus using a face image, comprising: (a) converting a face image of a normalized spatial domain into frequency domain data; (b) extracting effective transform coefficients from the transformed frequency domain data through energy density region information; (c) extracting a feature vector from the extracted valid transform coefficients; And (d) comparing the extracted feature vector with a previously registered feature vector to perform user authentication. The user is improved in speed and accuracy because user authentication using a face image is performed with a minimum data dimension. An authentication method and apparatus can be provided.

Apparatus and method for radial and angular or rotational analysis or images for shape content and matching

一种分段的空间光调制器(50)具有一个有源光学区域(54)，它包括关于中心轴(40)在各种角度方向上分散的多个辐射状延伸的有源光学调制器扇区(500，510，520，530，540，550，560，570，580，590，600，610，620，630，640，650)。分段的辐射状空间光调制器(50)用于分离和隔开傅立叶变换光学图案(32)，该傅立叶光学图案来自通过形状来记录、存储、检索、搜索和与其他图像比较而获得匹配或接近匹配的用于图像的特征描述的图像。可以将图像重影以增加傅立叶变换光学图案(32)中的光功率，但未加入新的形状内容，并用于与其他图像形状特征分等级比较以在识别匹配以外识别接近匹配。

Patent RU2019126738A3

ВИ“? 2019126738"” АЗ Дата публикации: 21.06.2021 Форма № 18 ИЗПМ-2011 Федеральная служба по интеллектуальной собственности Федеральное государственное бюджетное учреждение ж 5 «Федеральный институт промышленной собственности» (ФИПС) ОТЧЕТ О ПОИСКЕ 1. . ИДЕНТИФИКАЦИЯ ЗАЯВКИ Регистрационный номер Дата подачи 2019126738/28(052484) 08.02.2018 РСТ/О$2018/017388 08.02.2018 Приоритет установлен по дате: [ ] подачи заявки [ ] поступления дополнительных материалов от к ранее поданной заявке № [ ] приоритета по первоначальной заявке № из которой данная заявка выделена [ ] подачи первоначальной заявки № из которой данная заявка выделена [ ] подачи ранее поданной заявки № [Х] подачи первой(ых) заявки(ок) в государстве-участнике Парижской конвенции (31) Номер первой(ых) заявки(ок) (32) Дата подачи первой(ых) заявки(ок) (33) Код страны 1. 15/428,367 09.02.2017 05 Название изобретения (полезной модели): [Х] - как заявлено; [ ] - уточненное (см. Примечания) Система и связанный способ измерения оптических характеристик листа стекла на технологической линии Заявитель: ГЛАССТЕК, ИНК., 05 2. ЕДИНСТВО ИЗОБРЕТЕНИЯ [Х] соблюдено [ ] не соблюдено. Пояснения: см. Примечания 3. ФОРМУЛА ИЗОБРЕТЕНИЯ: [Х] приняты во внимание все пункты (см. Примечания) [ ] приняты во внимание следующие пункты: [ ] принята во внимание измененная формула изобретения (см. Примечания) 4. КЛАССИФИКАЦИЯ ОБЪЕКТА ИЗОБРЕТЕНИЯ (ПОЛЕЗНОЙ МОДЕЛИ) (Указываются индексы МПК и индикатор текущей версии) В65С 45/00 (2006.01) 5. ОБЛАСТЬ ПОИСКА 5.1 Проверенный минимум документации РСТ (указывается индексами МПК) В65С 49/00, 49/06, СОМ 21/00, 21/84, 21/88, 21/89, 21/95, 21/958 5.2 Другая проверенная документация в той мере, в какой она включена в поисковые подборки: 5.3 Электронные базы данных, использованные при поиске (название базы, и если, возможно, поисковые термины): ВУРАТЕМТЬЗ, ОУУРТ, Е-ГлЬгагу, ЕАРАТТЪУ, ЕВЗСО, Езрасепе боозе, Соое Реп, ]- Р1а(Раё, КТРКЪУ, Гех15Мех15, РАТЕМТЗСОРЕ, Ра еагсв, Оцез{е]-ОтЬи, КОРТО, ИЗРТО 6. ...

Digital identifier for a document

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining image data of an identification (ID) document and identifying a pattern of the ID document based on analysis of the image data against a predefined patterns for a particular type of document. An identifier engine of the system computes a frequency metric that defines how often the pattern reoccurs at the ID document and generates a unique identifier for the ID document based on the computed frequency metric. The unique identifier is stored at a digital fingerprint database of the system as a digital fingerprint for the ID document.

Method for detecting precipitation on a windscreen

The invention relates to a method for detecting precipitation, especially rain and fog, on a windscreen, which is not based on an active illumination of the windscreen or a measurement of the reflectivity, but on a camera using a plurality of adjacent pixels for detecting an image of a target area. Said target area is located in the surroundings of the vehicle, and the windscreen is thus represented in a blurred manner. In the event of a blurred representation, raindrops or fog on the windscreen produce a soft-focus effect in the image. The sharpness of the image and/or the difference in contrast of adjacent pixels is evaluated and the presence of precipitation is detected therefrom, the image is then preferably subjected to a two-dimensional Fourier transformation and the spatial frequencies are evaluated. A first image is recorded especially for a low contrast target area, a windscreen wiper passing over the windscreen in the visual region of the camera or a heating process is activated, and a second image is then recorded, and both images are evaluated according to changes.

Method for automatic searching similar image in image data base

一种图像检索系统(5)和方法将基于柱状图的特征与子波帧分解特征相结合，以及双流程渐进检索处理。所提出的本发明相对于照明的变化以及几何失真而言是稳定的。在第一轮检索过程中，获得了卡南－洛维颜色空间中的图像柱状图的矩特征并被用于过滤最不相似的图像。在第二轮检索中，多分辨率的WF分解被循环的应用于剩余图像。最低等级的一组低通过滤子图象的系数在减去平均数和标准化之后被用来作为包括空间颜色信息的特征。模数和方向系数是根据每一个等级的高通滤波的X－Y方向的子图象来计算的，并且中心矩是从最相似方向系数的方向柱状图导出的以获得TRSI方向/边缘/形状特征。因为本发明相对于照明的变化以及几何失真而言是稳固的和稳定的，本发明十分适合应用于实时图像/视频数据库(20)的索引和检索应用。

Face recognition method, and method for searching and displaying character appearance using the same

얼굴 인식 방법 및 이를 이용한 인물 검색/표시 방법이 개시된다. 본 발명의 얼굴 인식 방법은 얼굴을 검출하는 단계; 얼굴의 전체 영역으로부터 하나 이상의 얼굴 구성 요소를 추출하는 단계; 얼굴 전체 영역 및 얼굴 구성 요소 영역 각각에 대하여 DCT를 수행하여 최종 DCT 계수를 산출하는 단계; 최종 DCT 계수에 대하여 각각 선형 판별 분석을 적용하여, DCT/LDA 특징값을 추출하는 단계; 얼굴 구성 요소 영역 각각에 대하여 가중치를 산출하는 단계; 가중치와 DCT/LDA 특징값을 이용하여 최종 특징값을 산출하는 단계; 및 최종 특징값을 등록된 인물의 특징값과 비교하여 인물을 판별하는 단계를 포함한다. 본 발명의 얼굴 검색/표시 방법은 상기 얼굴 인식 방법을 이용하여 인식된 얼굴 인식 결과를 이용하여 인물 변경 장면을 표시하고, 얼굴 인식 결과를 분석하여 인물별 등장 구간을 시간축 상에 표시하는 단계를 포함한다. 본 발명에 의하면, 얼굴 인식의 속도와 정확도가 향상되고, 손쉽게 등장 인물의 변화 장면 및 인물별 등장 구간 등을 파악할 수 있다. Disclosed are a face recognition method and a person search / display method using the same. The face recognition method of the present invention includes detecting a face; Extracting one or more facial components from the entire area of the face; Calculating a final DCT coefficient by performing DCT on each of the entire face region and the face component region; Extracting DCT / LDA feature values by applying linear discriminant analysis to the final DCT coefficients, respectively; Calculating weights for each of the facial component regions; Calculating a final feature value using the weight and the DCT / LDA feature value; And determining the person by comparing the final feature value with the feature value of the registered person. The face searching / displaying method of the present invention includes displaying a person change scene by using a face recognition result recognized using the face recognition method, and analyzing a face recognition result to display an appearance section for each person on a time axis. do. According to the present invention, the speed and accuracy of face recognition can be improved, and it is possible to easily grasp the changing scene of the character and the appearance period of each character.

Optical coin discrimination systems and methods for use with consumer-operated kiosks and the like

Systems and associated methods for optical coin discrimination are disclosed herein. In one embodiment, a method for discriminating coins includes obtaining a digital image of a coin, identifying the outline of the coin using a suitable algorithm, and determining the diameter of the coin using the outline of the coin. The method of this embodiment further includes generating a rectangular image of the coin using, for example, a log-polar transform, generating a series of, for example, Fourier transforms from the rectangular image, and identifying spectral peak locations and intensities in the Fourier transform results. The diameter of the coin, spectral peak location, spectral peak intensity of the coin and/or other aspects of the coin can then be compared to known values for different coins to discriminate the coin.

DEVICE AND METHOD FOR RADIAL AND ANGULAR OR WITH AN INCREASING ANGLE OF ANALYSIS OF IMAGES APPLICABLE TO THE CONTENT OF FORM AND CONSISTENCY

ÐÎÑÑÈÉÑÊÀß ÔÅÄÅÐÀÖÈß (19) RU (11) 2004 125 168 (13) A (51) ÌÏÊ G06K 1/00 (2006.01) ÔÅÄÅÐÀËÜÍÀß ÑËÓÆÁÀ ÏÎ ÈÍÒÅËËÅÊÒÓÀËÜÍÎÉ ÑÎÁÑÒÂÅÍÍÎÑÒÈ, ÏÀÒÅÍÒÀÌ È ÒÎÂÀÐÍÛÌ ÇÍÀÊÀÌ (12) ÇÀßÂÊÀ ÍÀ ÈÇÎÁÐÅÒÅÍÈÅ (21), (22) Çà âêà: 2004125168/09, 16.01.2003 (71) Çà âèòåëü(è): ËÓÊ ÄÀÉÍÝÌÈÊÑ, ÈÍÊ. (US) (30) Ïðèîðèòåò: 18.01.2002 US 10/051,364 (72) Àâòîð(û): ÊÐÈËË Ðèê (US) (85) Äàòà ïåðåâîäà çà âêè PCT íà íàöèîíàëüíóþ ôàçó: 18.08.2004 (74) Ïàòåíòíûé ïîâåðåííûé: Åãîðîâà Ãàëèíà Áîðèñîâíà (86) Çà âêà PCT: US 03/01281 (16.01.2003) Àäðåñ äë ïåðåïèñêè: 129010, Ìîñêâà, óë. Á.Ñïàññêà , 25, ñòð.3, ÎÎÎ "Þðèäè÷åñêà ôèðìà Ãîðîäèññêèé è Ïàðòíåðû", ïàò.ïîâ. Ã.Á. Åãîðîâîé (54) ÓÑÒÐÎÉÑÒÂÎ È ÑÏÎÑÎÁ ÄËß ÐÀÄÈÀËÜÍÎÃÎ È ÓÃËÎÂÎÃÎ ÈËÈ Ñ ÏÐÈÐÀÙÅÍÈÅÌ ÓÃËÀ R U Ôîðìóëà èçîáðåòåíè 1. Ñïîñîá îïðåäåëåíè õàðàêòåðèñòèê èçîáðàæåíè ïðèìåíèòåëüíî ê ñîäåðæàíèþ ôîðìû, âêëþ÷àþùèé â ñåá ôîðìèðîâàíèå îïòè÷åñêîãî îáðàçà ïðåîáðàçîâàíè Ôóðüå èçîáðàæåíè ñ ïîìîùüþ ñâåòîâîé ýíåðãèè, ïðîñòðàíñòâåííóþ ôèëüòðàöèþ ñâåòîâîé ýíåðãèè îò îïòè÷åñêîãî îáðàçà ïðåîáðàçîâàíè Ôóðüå ïóòåì îòáîðà ñâåòîâîé ýíåðãèè îò äèñêðåòíûõ ÷àñòåé îïòè÷åñêîãî îáðàçà ïðåîáðàçîâàíè Ôóðüå íà ìíîæåñòâå óãëîâûõ íàïðàâëåíèé è îòäåëåíèå òàêèõ äèñêðåòíûõ ÷àñòåé îò äðóãèõ ÷àñòåé îïòè÷åñêîãî îáðàçà ïðåîáðàçîâàíè Ôóðüå äë îáðàçîâàíè ìíîæåñòâà ïðîôèëüòðîâàííûõ îáðàçîâ ñâåòîâîé ýíåðãèè îò óêàçàííûõ äèñêðåòíûõ ÷àñòåé, îáíàðóæåíèå èíòåíñèâíîñòåé ñâåòîâîé ýíåðãèè, ðàñïðåäåëåííîé â ïðîôèëüòðîâàííûõ îáðàçàõ, äë ñîîòâåòñòâóþùèõ óãëîâûõ íàïðàâëåíèé, è ñîõðàíåíèå èíòåíñèâíîñòåé ñâåòîâîé ýíåðãèè, îáíàðóæåííûõ â ïðîôèëüòðîâàííûõ îáðàçàõ, âìåñòå ñ ñîîòâåòñòâóþùèìè óãëîâûìè íàïðàâëåíè ìè. 2. Ñïîñîá ïî ï.1, êîòîðûé âêëþ÷àåò â ñåá ôîêóñèðîâàíèå îïòè÷åñêîãî îáðàçà ïðåîáðàçîâàíè Ôóðüå íà àêòèâíóþ îïòè÷åñêóþ îáëàñòü ïðîñòðàíñòâåííîãî ìîäóë òîðà ñâåòà, èçáèðàòåëüíóþ àêòèâèçàöèþ ó÷àñòêîâ ïðîñòðàíñòâåííîãî ìîäóë òîðà ñâåòà íà âûáðàííûõ óãëîâûõ íàïðàâëåíè õ äë ïîâîðîòà ïëîñêîñòè ïîë ðèçàöèè äèñêðåòíûõ ÷àñòåé ñâåòîâîé ýíåðãèè îïòè÷åñêîãî îáðàçà ïðåîáðàçîâàíè Ôóðüå, îòäåëåíèå ñâåòà ñ ïîâåðíóòîé ...

Unmanned aerial vehicle micro-motion characteristic signal detection method based on weight-agnostic neural network

本发明公开了一种基于权重不可知神经网络的无人机微动特征信号检测方法，其特征是，包括如下步骤：1）计算信号的循环谱；2）通过MATLAB处理得到循环谱等高图，并选择观测区域；3）训练权重不可知神经网络；4）利用训练好的权重不可知神经网络进行微动特征识别。这种方法有很好的抗干扰性，神经网络的结构更简单，计算量更小，对无人机微动特征信号识别的准确率更高。

Method and device of characteristic extraction

FIELD: physics. SUBSTANCE: device realizes a method for extracting characteristics comprising the following stages: segmenting the image into a plurality of units, wherein each unit includes a plurality of cells, converting each cell from the spatial domain to a frequency domain, and extracting a characteristic of histogram of oriented gradient (HOG) of the image in the frequency domain. The stage of extracting the characteristic of histogram of oriented gradient (HOG) of the image in the frequency domain comprises the following sub-stages: calculating the magnitude of the gradient and the gradient direction of each cell in the frequency domain to obtain the descriptor of each cell, calculating the corresponding descriptor of each unit in the frequency domain to obtain the HOG characteristic of each unit, and calculating the HOG characteristic of each image unit in the frequency domain to obtain the HOG characteristic of the image. The stage of calculating the HOG characteristic of each image unit to obtain the HOG characteristic of the image comprises the sub-stages of adjusting the HOG characteristic of each unit in the image from the original L*1-dimensional vector to the M*N matrix, wherein each unit includes M*N pixels, and L=M*N, and the HOG image characteristic is obtained based on the corrected HOG characteristic of each unit and the corresponding position of each unit in the image. EFFECT: providing the possibility of increasing the frequency and accuracy of detection in the recognition of structures. 11 cl, 11 dwg, 1 tbl РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 632 578 C2 (51) МПК G06K 9/46 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (21)(22) Заявка: 2016110721, 29.12.2015 (24) Дата начала отсчета срока действия патента: 29.12.2015 Дата регистрации: Приоритет(ы): (30) Конвенционный приоритет: (56) Список документов, цитированных в отчете о поиске: Henrick Skibbe и др. "CIRCULAR 25.11.2015 CN ...

Method and system of comparing videofiles

FIELD: physics. SUBSTANCE: device comprises a communication interface for exchanging data over a data network with a video store, wherein the video store stores a plurality of video, a processor operatively connected to the communication interface, the processor being configured to receive a plurality of video candidates from the video store, a video candidate from a plurality of video candidates potentially close to the video duplication for the first video, the first video has the duration of the first video, the definition of the duration variable, wherein the duration variable parameter is determined based on the duration of the first video, selecting the first video candidate from the plurality of video candidates, the first video candidate having the duration of the first video candidate, comparing the duration of the first video candidate with the parameter of the duration variable in response to the fact that the duration of the first video candidate is in the range of the parameter of the duration variable, determining that the first video candidate is a valid candidate for the near duplicate video for the first video. EFFECT: increasing the effectiveness of determining video candidates, close to duplicating video. 13 cl, 4 dwg РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 632 127 C1 (51) МПК G06F 17/30 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (21)(22) Заявка: 2016113166, 07.04.2016 (24) Дата начала отсчета срока действия патента: 07.04.2016 (73) Патентообладатель(и): Общество с ограниченной ответственностью "Яндекс" (RU) Дата регистрации: (56) Список документов, цитированных в отчете о поиске: WO 2010/011991 A2, 28.01.2010. US Приоритет(ы): (22) Дата подачи заявки: 07.04.2016 (45) Опубликовано: 02.10.2017 Бюл. № 28 C 1 R U Стр.: 1 C 1 (54) СПОСОБ И СИСТЕМА СРАВНЕНИЯ ВИДЕОФАЙЛОВ (57) Реферат: Изобретение относится к способу и устройству длительностью первого видео, определение для выбора видеокандидата. ...

Methods and computer device for determination, if a bullet is authentic

FIELD: computer equipment.SUBSTANCE: invention relates to means for verification of bullet authentication. Computer device or its logic circuit takes, for example, through a camera or through a communication network, an image of a bullet-candidate, for example, one-dimensional or two-dimensional barcode, uses an image to perform measurements of the characteristic of attribute of bullet-candidate, as a result a profile for this attribute is created. Computer device filters, from the profile of attribute, all spatial frequency components, which are indicated as frequency components of sibling. In some embodiments, the computer device performs an inverse procedure and filters out all frequency components except those indicated as frequency sibling components.EFFECT: high accuracy of identification.26 cl, 40 dwg РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 682 407 C1 (51) МПК G06K 19/08 (2006.01) G06T 7/00 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (52) СПК G06K 7/1413 (2018.08); G06K 7/1417 (2018.08); G06K 7/1434 (2018.08); G06K 9/00577 (2018.08); G06K 9/2018 (2018.08); G06K 9/522 (2018.08); G06K 9/6215 (2018.08); G06K 9/6218 (2018.08) (21)(22) Заявка: 2018136107, 13.03.2017 13.03.2017 Дата регистрации: R U (24) Дата начала отсчета срока действия патента: (72) Автор(ы): ВОЙГТ Маттиас (US), СОБОРСКИ Майкл Л. (US), АЙЮБ Рафик (US) (73) Патентообладатель(и): СИС-ТЕК СОЛЮШНЗ, ИНК. (US) 19.03.2019 (56) Список документов, цитированных в отчете о поиске: RU 2380750 С2, 27.01.2010. RU 14.03.2016 US 62/307,901 2370377 C2, 10.07. 2006. US 2015/262347 A1, 17.09.2015. US 2015/379321 A1, 31.12.2015. US 2015/083801 A1, 26.03.2015. (45) Опубликовано: 19.03.2019 Бюл. № 8 (85) Дата начала рассмотрения заявки PCT на национальной фазе: 15.10.2018 (86) Заявка PCT: 2 6 8 2 4 0 7 Приоритет(ы): (30) Конвенционный приоритет: 2 6 8 2 4 0 7 R U (87) Публикация заявки PCT: C 1 C 1 US 2017/022097 (13.03.2017) WO 2017/160715 (21.09.2017) Адрес ...

Image discrimination device, image search device, image search program, and recording medium

Method and apparatus for video encoding with adjusting offsets based on pixel classification, method and apparatus for video decoding with adjusting offsets based on pixel classification

본 발명은, 원본영상과의 오차가 최소화되는 복원영상을 생성하기 위한 비디오 부호화 방법 및 그 장치, 비디오 복호화 방법 및 그 장치를 제안한다. 본 발명에 따라, 수신한 비트스트림으로부터 현재 블록의 오프셋 병합 정보를 파싱하고, 오프셋 병합 정보에 기초하여 현재 블록의 오프셋 파라미터 중 오프셋 타입 및 오프셋값들을 복원하고, 오프셋 타입이 나타내는 현재 블록의 에지 타입 또는 픽셀값 밴드 타입에 기초하여 결정된 복원픽셀의 에지 클래스 또는 픽셀값 밴드에 대응하는 오프셋값을 오프셋값들로부터 선택하여 복원픽셀의 픽셀값을 오프셋만큼 조정하는 비디오 복호화 방법이 개시된다. The present invention proposes a video encoding method and apparatus, a video decoding method, and an apparatus thereof for generating a reconstructed image with a minimum error from an original image. According to the present invention, the offset merging information of the current block is parsed from the received bit stream, the offset type and offset values of the offset parameters of the current block are restored based on the offset merging information, the edge type of the current block indicated by the offset type Or an offset value corresponding to an edge class or a pixel value band of a reconstructed pixel determined based on a pixel value band type is selected from offset values and the pixel value of the reconstructed pixel is adjusted by an offset.

Method and device for classifying urine visible components

本发明提供了尿液有形成分分类方法和装置。该方法包括：将有形成分区块中有形成分外周区域的平均像素值和中心区域的平均像素值的差，用作分类器的特征集中的特征；以所述分类器对尿液有形成分分类。本发明的一个实施例旨在提高尿液有形成分分类的精度。

METHOD FOR EMBEDDING WATERMARK IN VIDEO DATA AND APPARATUS, METHOD FOR EXTRACTING WATERMARK IN VIDEO DATA AND APPARATUS, DEVICE, AND STORAGE MEDIUM

Disclosed in this application are a method for embedding a watermark in video data and apparatus, a method for extracting a watermark in video data and apparatus, a device, and a storage medium. The method for embedding the watermark includes: acquiring a target image frame in video data; performing time-frequency transformation on the target image frame to obtain target frequency domain data, the target frequency domain data comprising a matrix formed by frequency domain coefficients; changing the frequency domain coefficients in the target frequency domain data according to watermark data to obtain watermarked frequency domain data; performing inverse time-frequency transformation on the watermarked frequency domain data to obtain a watermarked image frame; and synthesizing watermarked video data according to the watermarked image frame.

Method and system for determining whether a target object was present during a scanning operation

本发明揭示用于确定是否通过扫描器检测对象的方法、装置及系统。确定、修改及评估快速傅里叶变换“FFT”。可相对于与所获取图像的像素值对应的经增益补偿像素值的子集确定每一FFT。

System, Method And Program Product For Camera-Based Object Analysis

A system, method and program product for camera-based object analyses including object recognition, object detection, and/or object categorization. An exemplary embodiment of the computerized method for analyzing objects in images obtained from a camera system includes receiving image(s) having pixels from the camera system; calculating a pool of features for each pixel; then deriving either a pool of radial moment of features from the pool of features and a geometric center of the image(s) or a pool of central moments of features from the pool of features; then calculating a normalized descriptor, based on an area of the image(s) and either of the derived pool of moments of features; and then based on the normalized descriptor, a computer then either recognizes, detects, and/or categorizes an object(s) in the image(s).

Model-based metrology using images

Methods and systems for combining information present in measured images of semiconductor wafers with additional measurements of particular structures within the measured images are presented herein. In one aspect, an image-based signal response metrology (SRM) model is trained based on measured images and corresponding reference measurements of particular structures within each image. The trained, image-based SRM model is then used to calculate values of one or more parameters of interest directly from measured image data collected from other wafers. In another aspect, a measurement signal synthesis model is trained based on measured images and corresponding measurement signals generated by measurements of particular structures within each image by a non-imaging measurement technique. Images collected from other wafers are transformed into synthetic measurement signals associated with the non-imaging measurement technique and a model-based measurement is employed to estimate values of parameters of interest based on the synthetic signals.

Image processing system

In order to start a frequency analysis process before completion of acquisition of an image so as to shorten a processing time, a first frequency analysis unit performs one-dimensional frequency analysis on each pixel line. A second frequency analysis unit collects a predetermined number of one-dimensional frequency analysis results from the first frequency analysis unit and performs further one-dimensional frequency analysis so as to obtain a final two-dimensional frequency analysis result.

Device and method for processing video data for the detection of living organisms

Dispositif et procédé de traitement de données vidéos pour détection du vivant Dispositif et procédé de traitement de données vidéos pour détection du vivant Un dispositif d’analyse de données vidéo, comprend : - un premier analyseur (6) agencé pour exécuter une mesure de photopléthysmographie à distance sur des données vidéos (25) à analyser reçues en entrée, comprenant un séparateur (20) agencé pour déterminer des régions d’intérêts (27) dans les données vidéos à analyser (25), un agrégateur (22) agencé pour déterminer un signal de photopléthysmographie à distance à partir des données vidéos à analyser (25) relatives à chaque région d’intérêt, et un calculateur (24) agencé pour calculer un signal spectral à partir du signal de photopléthysmographie, et pour en tirer un ou plusieurs signaux physiologiques (29), - un testeur (8) agencé pour recevoir ledit un ou plusieurs signaux physiologiques (29) et pour retourner une première valeur de présence humaine, - un deuxième analyseur (10) agencé pour recevoir les données vidéos à analyser et pour leur appliquer un réseau de neurones pour en tirer une deuxième valeur de présence humaine, le réseau de neurones étant entraîné sur des données vidéos similaires aux données vidéos à analyser et des jeux de caractéristiques extraites de ces données vidéos obtenus par analyse locale et/ou par apprentissage automatique, et - un unificateur (12) agencé pour recevoir la première valeur de présence humaine et la deuxième valeur de présence humaine, et pour retourner une valeur de présence humaine unifiée. Fig.1 Device and method for processing video data for detection of living beings Device and method for processing video data for detecting living beings A device for analyzing video data, comprises: - a first analyzer (6) arranged to perform a photoplethysmography measurement at distance on video data (25) to be analyzed received as input, comprising a separator (20) arranged to determine regions of interest (27) in the video data ...

CODING OF CONCENTRIC INFORMATION

L'invention concerne un procédé de codage en fréquence, module et phase d'une représentation numérique, dans le domaine spatial, d'un élément annulaire, comportant les étapes suivantes : appliquer (301) à tout point de l'élément une conversion polaire à angle constant, d'où il résulte que l'élément est déplié sous forme rectangulaire; transférer (302), dans le domaine fréquentiel, tout point de la forme rectangulaire convertie au moyen d'une transformée de Fourier; filtrer (303) les données discrètes résultant du transfert au moyen d'au moins un filtre passe-bande, réel, bidimensionnel, orienté selon l'axe des phases; appliquer (304) une transformée de Hilbert aux résultats du filtrage; appliquer (305) une transformée de Fourier inverse aux résultats de la transformée de Hilbert; et extraire (306) des informations de phase et de module, dans le domaine spatial. The invention relates to a method for frequency, module and phase coding of a digital representation, in the spatial domain, of an annular element, comprising the following steps: applying (301) to any point of the element a polar conversion at constant angle, from which it follows that the element is unfolded in rectangular form; transfer (302), in the frequency domain, any point of the rectangular shape converted by means of a Fourier transform; filtering (303) the discrete data resulting from the transfer by means of at least one bandpass filter, real, two-dimensional, oriented along the phase axis; applying (304) a Hilbert transform to the results of the filtering; apply (305) an inverse Fourier transform to the results of the Hilbert transform; and extracting (306) phase and module information, in the space domain.

METHOD OF CHARACTERIZING A MATERIAL BY TAVELURE ANALYSIS

L'invention propose un procédé de caractérisation d'un matériau dans lequel est formée une surface, comprenant les étapes consistant à : - projeter sur la surface un faisceau lumineux cohérent, pour générer sur ladite surface des tavelures résultant d'interférences des rayons lumineux diffusés par ladite surface, - acquérir une image de ladite surface sur laquelle apparaissent les tavelures, traiter ladite image pour calculer au moins un critère de caractérisation du matériau, et - à partir des critères, déterminer le matériau constituant la surface, dans lequel l'étape de traitement de l'image comprend : - le calcul d'une fonction d'autocorrélation de l'intensité lumineuse sur l'image et le calcul de la valeur d'au moins un critère établi à partir de ladite fonction, et - le calcul de la valeur d'au moins un critère représentatif d'une distribution de déphasages des rayons lumineux diffusés par la surface. The invention proposes a method for characterizing a material in which a surface is formed, comprising the steps of: projecting a coherent light beam onto the surface, to generate on the surface scabs resulting from interference from the scattered light rays by said surface, - acquiring an image of said surface on which scabs appear, treating said image to calculate at least one criterion for characterizing the material, and - from the criteria, determining the material constituting the surface, in which the step processing of the image comprises: - calculating an autocorrelation function of the luminous intensity on the image and calculating the value of at least one criterion established from said function, and - calculating the value of at least one criterion representative of a distribution of phase shifts of the light rays diffused by the surface.

Method for detecting an object on a road surface, autonomous driving method and automotive lighting device

La présente invention concerne un procédé de détection d'un objet sur une surface routière, le procédé comprenant les étapes consistant à projeter un motif lumineux sur la surface routière, à acquérir une image du motif lumineux projeté, à détecter une ombre dans l'image acquise et à utiliser certaines caractéristiques de l'ombre pour obtenir des informations sur les caractéristiques d'un objet. L'invention propose également un procédé de conduite autonome utilisant cette détection d'objet et un dispositif d'éclairage automobile.Figure pour le résumé : figure 3 A method of detecting an object on a road surface, the method comprising the steps of projecting a light pattern onto the road surface, acquiring an image of the projected light pattern, detecting a shadow in the image acquired and to use certain characteristics of the shadow to obtain information on the characteristics of an object. The invention also proposes an autonomous driving method using this object detection and an automobile lighting device. Figure for the summary: figure 3

CHARACTER RECOGNITION PROCESS

Procédé de reconnaissance de caractères dans une image d'un document comprenant au moins un champ alphanumérique, le procédé comprenant les étapes de : - renforcer un contraste de l'image pour faire ressortir les caractères présents dans l'image ; - détecter des contours d'objets présents dans l'image pour créer un masque faisant ressortir les caractères ; - segmenter l'image en utilisant un arbre à composantes connexes et en lui appliquant le masque de manière à extraire de l'image les caractères ; - effectuer une reconnaissance de caractères sur les objets extraits. Dispositif pour la mise en œuvre de ce procédé. Method for recognizing characters in an image of a document comprising at least one alphanumeric field, the method comprising the steps of: - reinforcing a contrast of the image to bring out the characters present in the image; - detect the contours of objects present in the image to create a mask highlighting the characters; - segment the image using a tree with connected components and applying the mask to it so as to extract the characters from the image; - perform character recognition on the extracted objects. Device for implementing this process.

CHARACTER RECOGNITION METHOD

Procédé de reconnaissance de caractères dans une image d'un document comprenant au moins un champ alphanumérique, le procédé comprenant les étapes de : - renforcer un contraste de l'image pour faire ressortir les caractères présents dans l'image ; - détecter des contours d'objets présents dans l'image pour créer un masque faisant ressortir les caractères ; - segmenter l'image en utilisant un arbre à composantes connexes et en lui appliquant le masque de manière à extraire de l'image les caractères ; - effectuer une reconnaissance de caractères sur les objets extraits. Dispositif pour la mise en œuvre de ce procédé. A method of recognizing characters in an image of a document comprising at least one alphanumeric field, the method comprising the steps of: - enhancing a contrast of the image to bring out the characters present in the image; - detect contours of objects present in the image to create a mask highlighting the characters; - segment the image using a related component tree and applying the mask to extract the characters from the image; - perform character recognition on extracted objects. Device for implementing this method

Texture description method and texture retrieval method using Gabor filter in frequency domain

본 발명은 영상신호를 주파수 공간으로 변환하고 가보 필터링하여 질감 특징을 추출하기 위하는 주파수 공간상에서의 질감표현방법 및 이를 이용한 질감기반 검색방법에 관한 것이다. The present invention relates to a texture expression method in frequency space and texture-based retrieval method using the same in order to extract a texture feature by transforming the image signal into a frequency space and gabor filtering. 이러한 주파수 공간상에서의 질감표현방법은, 시간영역의 영상을 주파수영역으로 변환하는 제 1 단계와; 상기 주파수영역으로 변환된 영상을 N×M 개의 필터영역을 가지는 가보 필터에 적용하여 필터링하는 제 2 단계; 상기 가보 필터의 N×M 필터영역에 대응하는 주파수 공간분할 레이아웃의 각 채널에서 상기 가보 필터링된 영상의 질감 특징값들을 추출하는 제 3 단계; 및 상기 영상의 질감 특징값들을 이용하여 상기 영상의 질감기술자를 표현하는 제 4 단계를 포함한다. The texture expression method in the frequency space includes a first step of converting an image of a time domain into a frequency domain; A second step of applying the filtered image to the Gabor filter having N × M filter regions by filtering the image converted into the frequency domain; Extracting texture feature values of the Gabor-filtered image from each channel of the frequency space division layout corresponding to the N × M filter region of the Gabor filter; And a fourth step of expressing a texture descriptor of the image by using texture feature values of the image.

APPARATUS FOR EXAMINING MEDIA BY ULTRASONIC ECHOGRAPHY

L invention concerne un dispositif de fermeture pour abri ou similaires. Le bâti 1 du dispositif de fermeture est muni d au moins un passage de flux 2; d un moyen de fermeture 3 monté déplaçable pour chaque passage; et d une butée formée dans le bâti pour chaque moyen de fermeture. Le moyen de fermeture est déplaçable entre une position ouverte permettant un flux d air normal et une position ouverte engendrée par un choc de pression, position de fermeture à laquelle le moyen de fermeture est pressé contre la butée de manière à fermer le passage respectif. Le but est de fournir une structure simple et stable, dont le fonctionnement soit le plus efficace possible. En conséquence, le passage 2 est défini par des éléments/éléments partiels 5a, 5b sensiblement en forme de U s ouvrant l un vers l autre dans le sens du flux. L élément/élément partiel (respectivement 5a et 5b) sur le côté d entrée d un flux A et B est disposé de manière à fonctionner comme élément de guidage de flux, et l élément/élément partiel (respectivement 5a et 5b) sur le côté de sortie du flux A et B est disposé de manière à fonctionner comme élément de suppression du choc de pression. The invention relates to a closing device for a shelter or the like. The frame 1 of the closure device is provided with at least one flow passage 2; of a closing means 3 mounted movable for each passage; and a stop formed in the frame for each closing means. The closure means is movable between an open position allowing a normal air flow and an open position generated by a pressure shock, in which closed position the closure means is pressed against the stop so as to close the respective passage. The aim is to provide a simple and stable structure, the operation of which is as efficient as possible. As a result, the passage 2 is defined by substantially U-shaped elements / partial elements 5a, 5b opening towards each other in the direction of flow. The element / partial element (respectively 5a and 5b) on the inlet ...

Systems and methods for evaluating pigmented tissue lesions

Systems and methods for discriminating between malignant and benign pigmented skin lesions based on optical analysis using spatial distribution maps, morphological parameters, and additional diagnostic parameters derived from images of tissue lesions. A handheld optical transfer diagnosis device is disclosed capable of capturing a series of reflectance images of a skin lesion at a variety of angles of illumination and observation.

IMAGE SENSOR FOR OPTICAL CODE (S) RECOGNITION

Un capteur d'image CMOS pour lecteur de code dans un système de reconnaissance optique de code intègre un circuit de traitement numérique (7) qui applique un processus de calcul sur les données d'image de capture (DATA) au fur et à mesure de leur acquisition par le circuit de lecture séquentiel (4) du capteur, pour calculer une macro-image (Macro-data ) à partir des données d'image de capture, qui correspond à des informations de localisation de code(s) dans l'image de capture, et transmettre cette macro-image dans la trame d'image (DATA-OUT) à la suite des données d'image de capture, en pied de trame. A CMOS image sensor for code reader in an optical code recognition system integrates a digital processing circuit (7) which applies a calculation process to the capture image data (DATA) as and when their acquisition by the sequential reading circuit (4) of the sensor, to calculate a macro-image (Macro-data) from the capture image data, which corresponds to location information of code (s) in the capture image, and transmit this macro-image in the image frame (DATA-OUT) following the capture image data, at the foot of the frame.

METHOD OF CHARACTERIZING A MATERIAL BY TAVELURE ANALYSIS

METHOD FOR PROCESSING POSTAL OBJECTS ON TEXTURIZED BACKGROUND

Un procédé de traitement d'objets postaux dans lequel on déplace avec un convoyeur les objets postaux devant une caméra et on forme une image numérique de chaque objet postal, avec dans chaque image numérique ledit objet postal qui est inscrit dans un fond d'image, est caractérisé en ce que les objets postaux sont déplacés dans le convoyeur de telle sorte que chaque image numérique d'un objet postal comporte un fond d'image (3) constitué par un motif tramé périodique. A method of processing postal objects in which the postal objects are moved with a conveyor in front of a camera and a digital image of each postal item is formed, with in each digital image said postal item which is inscribed in a background image, is characterized in that the postal objects are moved in the conveyor so that each digital image of a postal object comprises an image background (3) constituted by a periodic halftone pattern.

Bandpass filter for detecting texture of iris, has passband which is real, bi-dimensional, oriented along phase axis and resulting from product of pair of identical one-dimensional Hamming windows having specified transfer function

The bandpass filter has a passband which is real, bi-dimensional, oriented along the phase axis and resulting from the product of pair of identical one-dimensional Hamming windows. The transfer function of each window is given as Xi(f)= alpha i+(1- alpha i)\*cos( pi \*(f-fqi)\/f0i), where f is the current frequency, alpha i is a real number between 0 and 1, fqi is central frequency of the passband and f0i is half of the passband centered on fqi.

METHOD AND DEVICE FOR ALLOCATING CHARACTERISTICS

2016110721 А ко РОССИЙСКАЯ ФЕДЕРАЦИЯ до ам вх —” 7 ВУ ® 2016 14 < “< (50) МПК СОбТ 1/00 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ЗАЯВКА НА ИЗОБРЕТЕНИЕ (21)(22) Заявка: 2016110721, 29.12.2015 (71) Заявитель(и): СЯОМИ ИНК. (СМ) Приоритет(ы): (30) Конвенционный приоритет: (72) Автор(ы): 25.11.2015 СМ 201510827886.1 ЛУН Фэй (СМ), (43) Дата публикации заявки: 28.09.2017 Бюл. № 28 КАН (С®), (85) Дата начала рассмотрения заявки РСТ на национальной фазе: 23.03.2016 (86) Заявка РСТ: СМ 2015/099310 (29.12.2015) Адрес для переписки: 109012, Москва, ул. Ильинка, 5/2, ООО "Союзпатент" (54) СПОСОБ И УСТРОЙСТВО ВЫДЕЛЕНИЯ ХАРАКТЕРИСТИКИ (57) Формула изобретения 1. Способ выделения характеристик, содержащий этапы, на которых: сегментируют изображение на множество блоков, при этом каждый блок включает в себя множество ячеек: преобразуют каждую ячейку из пространственной области в область частот; и выделяют характеристику гистограммы ориентированного градиента (НОО) изображения в области частот. 2. Способ по п. 1, в котором этап преобразования каждой ячейки из пространственной области в область частот содержит подэтап, на котором выполняют дискретное косинусное преобразование (ОСТ) каждой ячейки. 3. Способ по п. 1, в котором этап преобразования каждой ячейки из пространственной области в область частот содержит подэтап, на котором выполняют дискретное преобразование Фурье (РЕТ) каждой ячейки. 4. Способ по п. 2, в котором этап выделения характеристики гистограммы ориентированного градиента (НОО) изображения в области частоты содержит подэтапы, на которых: вычисляют магнитуду градиента и направление градиента каждой ячейки в области частот для получения дескриптора каждой ячейки; подсчитывают соответствующий дескриптор каждого блока в области частоты для получения характеристики НОС каждого блока; и подсчитывают характеристику НОС каждого блока изображения в области частот для получения характеристики НОС изображения. 5. Способ по п. 4, в котором этап ...

Information conversion system

Video decoding device using merge information to code SAO offset parameters

A video encoding method and apparatus and video decoding method and apparatus to generate a restored image having a minimum error with respect to an original image. The video decoding method includes: parsing offset merge information indicating whether offset parameters of a current block and at least one neighboring block from among blocks of video are identical to each other from a received bitstream; restoring an offset type and offset values among the offset parameter of the current block based on the offset merge information; determining an edge class or a pixel value band of a restored pixel based on an edge type or a pixel value band type of the current block indicating the offset type; and determining an offset value corresponding to the edge class or the pixel value band of the restored pixel from the offset values and adjusting a pixel value of the restored pixel according to the offset value.

High-performance closed-form single-scan calculation of oblong-shape rotation angles from binary images of arbitrary size using running sums

A method for performing a high-performance closed-form single-scan calculation of oblong-shape rotation angles from binary images of arbitrary size on a processor using running sums is disclosed. Running sums are calculated and stored throughout each scan, and the results are obtained in closed form by simple post-scan computation. An algorithmic embodiment may execute on one or more hardware processors with limited or constrained computation power, available instruction cycles, available memory, etc. Exemplary hardware processors are found in one or more CPUs of a desktop, laptop, tablet, or handheld computing device, and may be an embedded processor or a signal processor chip. The resulting method may be used for touch or optical user interfaces, real-time image recognition, real-time machine vision, and other purposes.

Radar target classification system for jet aircraft

The target classification system uses the doppler spectrum obtained from te radar echo signals, with suppression of the spectrum components resulting from clutter and the velocity of the radar target, before classification of the target by analysis of periodic, spectral lines within the doppler spectrum, e.g. via a neural network. The analogue radar echo signal is converted into a corresponding digital echo signal, with the time range divided into a number of time increments, each provided with a respective complex sample value, corresponding to an amplitude value. A given number of sample values are grouped in a main block, subjected to Fourier transformation for conversion into the frequency range, each spectrum subjected to removal of clutter and velocity vector components and amplitude normalisation, and the indication vector obtained for the block compared with the indication vectors of known targets.

Architecture to generate binary descriptor for image feature point

An embodiment of an image processor device includes technology to fetch a feature point data set from outside a local memory, locally store three or more fetched feature point data sets in the local memory, compute orientation information for each fetched feature point data set, compute first descriptor information based on the computed orientation information and a first locally stored feature point data set in parallel with a fetch and local store of a second feature point data set in the local memory, and compute second descriptor information based on the computed orientation information and the second locally stored feature point data set in parallel with the compute of the first descriptor information. Other embodiments are disclosed and claimed.

Device and method for processing video data to detect life

Dispositif et procédé de traitement de données vidéos pour détection du vivant Dispositif et procédé de traitement de données vidéos pour détection du vivant Un dispositif d'analyse de données vidéo, comprend : - un premier analyseur (6) agencé pour exécuter une mesure de photopléthysmographie à distance sur des données vidéos (25) à analyser reçues en entrée, comprenant un séparateur (20) agencé pour déterminer des régions d'intérêts (27) dans les données vidéos à analyser (25), un agrégateur (22) agencé pour déterminer un signal de photopléthysmographie à distance à partir des données vidéos à analyser (25) relatives à chaque région d'intérêt, et un calculateur (24) agencé pour calculer un signal spectral à partir du signal de photopléthysmographie, et pour en tirer un ou plusieurs signaux physiologiques (29), - un testeur (8) agencé pour recevoir ledit un ou plusieurs signaux physiologiques (29) et pour retourner une première valeur de présence humaine, - un deuxième analyseur (10) agencé pour recevoir les données vidéos à analyser et pour leur appliquer un réseau de neurones pour en tirer une deuxième valeur de présence humaine, le réseau de neurones étant entraîné sur des données vidéos similaires aux données vidéos à analyser et des jeux de caractéristiques extraites de ces données vidéos obtenus par analyse locale et/ou par apprentissage automatique, et - un unificateur (12) agencé pour recevoir la première valeur de présence humaine et la deuxième valeur de présence humaine, et pour retourner une valeur de présence humaine unifiée.

Coding of concentric information

A method for coding in frequency, module and phase a digital representation, in the space field, of a ring-shaped element, including the steps of: applying to any point of the element a polar conversion at constant angle, whereby the element is unfolded in rectangular form; transferring, to the frequency field, any point of the converted rectangular shape by means of a Fourier transform; filtering the discrete data resulting from the transfer by means of at least one real, bidimensional, band-pass filter, oriented along the phase axis; applying a Hilbert transform to the filtering results; applying an inverse Fourier transform to the results of the Hilbert transform; and extracting phase and module information in the space field.

Presentation of digital materials based on matrix invariance

FIELD: information technology. ^ SUBSTANCE: system for creating compact description of digital materials has a reception module which can receive digital material, a segmentation module which can breakdown the said material into a set regions, a computation module which can calculate feature vectors for each region from the said set, where the feature vectors are calculated based on matrix invariance which include singular decomposition, an output module which can generate an output result using a combination of calculated feature vectors, where the output result forms a vector of hash-values for the said digital material, where the vector of hash-values is compact presentation of the digital material such that, digital material is identified based on the said compact presentation. ^ EFFECT: broader functionalities. ^ 9 cl, 3 dwg РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) 2 387 006 (13) C2 (51) МПК G06F 21/24 G06F 17/18 (2006.01) (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ, ПАТЕНТАМ И ТОВАРНЫМ ЗНАКАМ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (21), (22) Заявка: 2004135760/09, 06.12.2004 (30) Конвенционный приоритет: 06.01.2004 US 10/752,268 (73) Патентообладатель(и): МАЙКРОСОФТ КОРПОРЕЙШН (US) (43) Дата публикации заявки: 20.05.2006 C 2 2 3 8 7 0 0 6 Адрес для переписки: 129090, Москва, ул. Б.Спасская, 25, стр.3, ООО "Юридическая фирма Городисский и Партнеры", пат.пов. Ю.Д.Кузнецову, рег.№ 595 C 2 R U (56) Список документов, цитированных в отчете о поиске: US 6606744 B1, 12.08.2003. RU 2193825 C2, 27.11.2002. US 6134343 A, 17.10.2000. WO 03/092197 A1, 06.11.2003. CHENG, YONGQING et al «Aircraft identification based on algebraic method», [он-лайн] 07.1992. Найдено в Интернете по адресу: , реферат. (54) ПРЕДСТАВЛЕНИЕ ЦИФРОВЫХ МАТЕРИАЛОВ, ОСНОВАННОЕ НА ИНВАРИАНТНОСТЯХ МАТРИЦ (57) Реферат: Изобретение относится к технологии представления сигналов. Техническим результатом является расширение функциональных ...

Apparatus and method for radial and angular or rotational analysis of images for characterising andfor matching shape content

Method for comparing three-dimensional surface triangulations of e.g. dinosaur, involves comparing three dimensional surface triangulation are based on three dimensional-moment invariants that are calculated as similar characteristics

The method involves computing three dimensional-moment invariants for location description of relevant vertices of three dimensional-surface triangulations within defined local areas. Numerical characteristics are determined in a form of accurate surface momentum of the three dimensional-surface triangulations without sampling. The three dimensional-moment invariants are computer from the determined numerical characteristics. The three dimensional surface triangulation are compared based on three dimensional-moment invariants that are calculated as similar characteristics.

Device, method and recording medium for video inspection

A device is provided which detects image patterns which may cause photosensitive attacks, based on the contrast intensity and values of frequency bands having a peak value. A frame image constituting video is image analyzed for contrast intensity and spatial frequency, in the contrast detector and the peak seeker respectively.

Image processing apparatus, image processing method, and image processing program

An image processing apparatus for searching for corresponding points between a first image and a second image is provided. The image processing apparatus includes window setting means for setting a window for each of the first image and the second image, phase information extraction means for extracting phase information by subjecting a representation included in each set window to frequency decomposition, corresponding points determination means for determining corresponding points between the first image and the second image based on comparison of the phase information extracted from each window, and window size control means for causing the window setting means to set a window different in size in accordance with a frequency used for calculation of the frequency decomposition. The window size control means causes the window setting means to set a window having a first size in response to a first frequency and to set a window having a second size smaller than the first size in response to a second frequency higher than the first frequency.