Настройки

Укажите год
-

Небесная энциклопедия

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

Подробнее
-

Мониторинг СМИ

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

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год

Применить Всего найдено 297132. Отображено 100.
23-10-2017 дата публикации

Монитор многофункциональный компьютеризированный

Номер: RU0000174590U1

Полезная модель относится к медицинской технике, а именно к биомедицинским измерениям для диагностических целей в кардиореспираторных исследованиях сердца.Технический результат заключается в упрощении, удешевлении, снижении энергопотребления, массы и уровня побочных излучений в многофункциональном компьютизированном медицинском мониторе при использовании в нем современных программно-аппаратных средств обработки, отображения и компьютеризированного анализа медицинской информации. Этот результат достигается благодаря тому, что в известном многофункциональном компьютеризированном мониторе, питаемом от сети и от аккумуляторной батареи, который содержит материнскую плату с портами для сменных карт памяти и включения в локальную вычислительную сеть, процессорный модуль SOM, многоканальный модуль ECGP измерителей биосигналов человека, клавиатуру, динамик и ЖКИ-дисплей, вход питания которого подключен к соответствующему выходу питания дисплея материнской платы, материнская плата выполнена с дополнительным интерфейсом USB HUB с возможностью подключения модулей дополнительных измерителей биосигналов человека и с возможностью применения вместо свинцовых аккумуляторов одной Li-Ion аккумуляторной батареи, процессорный модуль SOM выполнен на основе ARM-процессора с интерфейсом низковольтной дифференциальной передачи сигналов (LVDS) и установлен на материнской плате, многоканальный модуль ECGP измерителей биосигналов человека выполнен с интерфейсами USB2.0, при этом клавиатура подключена непосредственно к процессорному модулю SOM, а ЖКИ-дисплей выполнен с возможностью приема информации по каналу LVDS и подключен к соответствующему выходу процессорного модуля SOM кабелем на основе медной витой пары. 2 ил. Ц 1 174590 ко РОССИЙСКАЯ ФЕДЕРАЦИЯ 19 11 зе а в ва за (13 7 ВУ “174 59041 (51) МПК ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ А61В 5/04 (2006.01) (12) ОПИСАНИЕ ПОЛЕЗНОЙ МОДЕЛИ К ПАТЕНТУ (21)(22) Заявка: 2017102024, 23.01.2017 (24) Дата начала отсчета срока действия ...

Подробнее
29-01-2018 дата публикации

Устройство регистрации ЭКГ человека для непрерывного контроля

Номер: RU0000176791U1

Полезная модель относится к области медицинской техники и предназначена для бесконтактного контроля функционального состояния человека, в частности для бесконтактного снятия электрокардиограммы.Технический результат заявляемой полезной модели заключается в обеспечении непрерывного контроля функционального состояния пациента. РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 176 791 U1 (51) МПК A61B 5/04 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ПОЛЕЗНОЙ МОДЕЛИ К ПАТЕНТУ (52) СПК A61B 5/04 (2006.01) (21)(22) Заявка: 2017113865, 20.04.2017 (24) Дата начала отсчета срока действия патента: 29.01.2018 Приоритет(ы): (22) Дата подачи заявки: 20.04.2017 (45) Опубликовано: 29.01.2018 Бюл. № 4 Адрес для переписки: 454080, Челябинск, пр. им. В.И. Ленина, 76, ЮУрГУ, патентный отдел (56) Список документов, цитированных в отчете о поиске: RU 163596 U1, 27.07.2016. US U 1 1 7 6 7 9 1 R U (54) Устройство регистрации ЭКГ человека для непрерывного контроля (57) Реферат: Полезная модель относится к области бесконтактного снятия электрокардиограммы. медицинской техники и предназначена для Технический результат заявляемой полезной бесконтактного контроля функционального модели заключается в обеспечении непрерывного состояния человека, в частности для контроля функционального состояния пациента. Стр.: 1 U 1 2007078324 А1, 05.04.2007. CA 2620578 A1, 12.04.2007. US 20050010096 А1, 13.01.2005. US 2006111640 A1, 25.05.2006. 1 7 6 7 9 1 (73) Патентообладатель(и): федеральное государственное автономное образовательное учреждение высшего образования "Южно-Уральский государственный университет" (национальный исследовательский университет) (ФГАОУ ВО "ЮУрГУ" (НИУ)) (RU) Дата регистрации: R U 20.04.2017 (72) Автор(ы): Кодкин Владимир Львович (RU), Хафизова Анастасия Сергеевна (RU) U 1 U 1 1 7 6 7 9 1 1 7 6 7 9 1 R U R U Стр.: 2 RU 5 10 15 20 25 30 35 40 45 176 791 U1 Полезная модель относится к области медицинской техники и предназначена для бесконтактного контроля ...

Подробнее
12-01-2012 дата публикации

Object recognition system with database pruning and querying

Номер: US20120011119A1
Принадлежит: Qualcomm Inc

A database for object recognition is generated by performing at least one of intra-object pruning and inter-object pruning, as well as keypoint clustering and selection. Intra-object pruning removes similar and redundant keypoints within an object and different views of the same object, and may be used to generate and associate a significance value, such as a weight, with respect to remaining keypoint descriptors. Inter-object pruning retains the most informative set of descriptors across different objects, by characterizing the discriminability of the keypoint descriptors for all of the objects and removing keypoint descriptors with a discriminability that is less than a threshold. Additionally, a mobile platform may download a geographically relevant portion of the database and perform object recognition by extracting features from the query image and using determined confidence levels for each query feature during outlier removal.

Подробнее
26-01-2012 дата публикации

Method and apparatus for producing and reproducing augmented reality contents in mobile terminal

Номер: US20120019526A1
Принадлежит: SAMSUNG ELECTRONICS CO LTD

A method and an apparatus produce and reproduce Augmented Reality (AR) contents in a mobile terminal. In the method, contents are produced. An image including an object corresponding to the contents is recognized. Recognition information for the object corresponding to the contents is obtained based on a recognition result. AR contents including the contents and the recognition information are generated. Therefore, AR contents for an input image may be easily produced and reproduced, and the AR contents may be used as independent multimedia contents, not an auxiliary means of other contents.

Подробнее
26-01-2012 дата публикации

Systems, methods, and apparatus for otoacoustic protection of autonomic systems

Номер: US20120023581A1

Systems, methods and apparatus are provided through which in some embodiments an autonomic unit transmits an otoacoustic signal to counteract a potentially harmful incoming signal.

Подробнее
01-03-2012 дата публикации

Storing and Searching Fingerprints Derived from Media Content Based on a Classification of the Media Content

Номер: US20120054194A1
Принадлежит: Dolby Laboratories Licensing Corp

Attributes are identified in media content. A classification value of the media content is computed based on the identified attributes. Thereafter, a fingerprint derived from the media content is stored or searched for based on the classification value of the media content.

Подробнее
08-03-2012 дата публикации

Re-calibration of pre-recorded images during interventions using a needle device

Номер: US20120059251A1
Принадлежит: KONINKLIJKE PHILIPS ELECTRONICS NV

Re-calibration of pre-recorded images during interventions is proposed, utilizing an interventional system comprising an imaging device providing images of an object, a needle device, and a processing device. The needle device comprises a sensor for providing data corresponding to tissue properties. The processing device is adapted to perform an overlay registration of pre-recorded images and live images provided by the imaging device, utilizing the data from the sensor. Thus, the accuracy of an overlay of images is increased.

Подробнее
15-03-2012 дата публикации

Deep belief network for large vocabulary continuous speech recognition

Номер: US20120065976A1
Принадлежит: Microsoft Corp

A method is disclosed herein that includes an act of causing a processor to receive a sample, wherein the sample is one of spoken utterance, an online handwriting sample, or a moving image sample. The method also comprises the act of causing the processor to decode the sample based at least in part upon an output of a combination of a deep structure and a context-dependent Hidden Markov Model (HMM), wherein the deep structure is configured to output a posterior probability of a context-dependent unit. The deep structure is a Deep Belief Network consisting of many layers of nonlinear units with connecting weights between layers trained by a pretraining step followed by a fine-tuning step.

Подробнее
22-03-2012 дата публикации

Image processing based on visual attention and reduced search based generated regions of interest

Номер: US20120070075A1
Автор: Lalitha M. Eswara
Принадлежит: Honeywell International Inc

A system for complexity reduction in images involving concepts of visual attention based most probable region detection for object presence and perspective-view based reduced scale-search approaches. Visual attention concept in context uses gradient and contrast of an image. A pixel meeting certain criteria for gradient or contrast values may be further processed for object presence. Limiting image processing to such regions may reduce the complexity of digitized images. Post processing the outcome using morphological operations like dilation and erosion appropriately may help retain some of the missed object pixels in the resultant image. Typically image blocks at different scales are searched for object presence. Reduced-scale search involves removing certain scales during search. As object size in image varies with its location scales within a given scale-range if searched, may lead to higher chances of object presence. This is implemented using relative heights and widths estimation using the perspective view concept.

Подробнее
29-03-2012 дата публикации

Method and Apparatus of Neural Signal Determination and Therapy Enhancement

Номер: US20120078132A1
Принадлежит: Proteus Biomedical Inc

A method and device are provided that detect and identify a neural signal by type and optionally or automatically provide a signal that affects a nerve carrying the neural signal. A plurality of electrodes is positioned along a nerve and monitors the electrical activity of the nerve. The invented system analyzes the monitored data to determine when the monitored activity can be identified as a known type of bioelectric signal, e.g., a pain nerve signal. The system may optionally attempt to affect, disrupt, diminish, nullify or block transmission of bioelectric signals along the nerve, e.g., by directing electrical energy through an electrode to nullify a bioelectric signal along a pain nerve.

Подробнее
12-04-2012 дата публикации

Video Signature Based on Image Hashing and Shot Detection

Номер: US20120087583A1
Принадлежит: FutureWei Technologies Inc

In accordance with an embodiment, A method of comparing a first group of frames to a second group of frames includes electronically receiving the first group of frames, selecting a group of frames from the first group of frames as a first key frame set, calculating a hash distance between an image hash for each frame in the first key frame set to an image hash of each frame of a second key frame set taken from second group of frames, and choosing frames in the first group of frames with a minimum hash distances to respective reference frames to form a series of minimum hash distances.

Подробнее
19-04-2012 дата публикации

Biocompatible electrode

Номер: US20120091011A1

A biocompatible electrode formed from an integrated circuit, the electrode comprising: a semiconductor substrate; and an electrode layer at least partially comprising porous valve metal oxide.

Подробнее
19-04-2012 дата публикации

Sample and Hold Circuitry for Monitoring Voltages in an Implantable Neurostimulator

Номер: US20120092031A1
Принадлежит: Boston Scientific Neuromodulation Corp

Sample and hold circuitry for monitoring electrodes and other voltages in an implantable neurostimulator is disclosed. The sample and hold circuitry in one embodiment contains multiplexers to selected appropriate voltages and to pass them to two storage capacitors during two different measurement phases. The capacitors are in a later stage serially connected to add the two voltages stored on the capacitors, and voltages present at the top and bottom of the serial connection are then input to a differential amplifier to compute their difference. The sample and hold circuitry is particularly useful in calculating the resistance between two electrodes, and is further particularly useful when resistance is measured using a biphasic pulse. The sample and hold circuitry is flexible, and can be used to measure other voltages of interest during biphasic or monophasic pulsing.

Подробнее
19-04-2012 дата публикации

System And Method For Alerting Visually Impaired Users Of Nearby Objects

Номер: US20120092460A1
Автор: Andrew Mahoney
Принадлежит: Individual

A system and method for assisting a visually impaired user including a time of flight camera, a processing unit for receiving images from the time of flight camera and converting the images into signals for use by one or more controllers, and one or more vibro-tactile devices, wherein the one or more controllers activates one or more of the vibro-tactile devices in response to the signals received from the processing unit. The system preferably includes a lanyard means on which the one or more vibro-tactile devices are mounted. The vibro-tactile devices are activated depending on a determined position in front of the user of an object and the distance from the user to the object.

Подробнее
19-04-2012 дата публикации

Digital image analysis utilizing multiple human labels

Номер: US20120093396A1
Принадлежит: Sony Corp

Systems and methods for implementing a multi-label image recognition framework for classifying digital images are provided. The provided multi-label image recognition framework utilizes an iterative, multiple analysis path approach to model training and image classification tasks. A first iteration of the multi-label image recognition framework generates confidence maps for each label, which are shared by the multiple analysis paths to update the confidence maps in subsequent iterations. The provided multi-label image recognition framework permits model training and image classification tasks to be performed more accurately than conventional single-label image recognition frameworks.

Подробнее
26-04-2012 дата публикации

Object detection device and system

Номер: US20120099790A1

Provided are an object detection device and system. The object detection device includes an outline image extraction unit, a feature vector calculation unit, and an object judgment unit. The outline image extraction unit extracts an outline image from an input image. The feature vector calculation unit calculates a feature vector from the outline image by using histogram of oriented gradients (HOG) representing a frequency distribution of gradient vectors with respect to pixels of the outline image, and pixel coordinate information varying according to a spatial distribution of the gradient vectors. The object judgment unit judges a target object corresponding to the feature vector with reference to pre-learned data.

Подробнее
03-05-2012 дата публикации

Systems and methods to improve feature generation in object recognition

Номер: US20120106847A1
Автор: Yingyong Qi
Принадлежит: Qualcomm Inc

Present embodiments contemplate systems, apparatus, and methods to improve feature generation for object recognition. Particularly, present embodiments contemplate excluding and/or modifying portions of images corresponding to dispersed pixel distributions. By excluding and/or modifying these regions within the feature generation process, fewer unfavorable features are generated and computation resources may be more efficiently employed.

Подробнее
03-05-2012 дата публикации

Trainable hierarchical memory system and method

Номер: US20120109857A1
Принадлежит: Numenta Inc

Memory networks and methods are provided. Machine intelligence is achieved by a plurality of linked processor units in which child modules receive input data. The input data are processed to identify patterns and/or sequences. Data regarding the observed patterns and/or sequences are passed to a patent module which may receive as inputs data from one or more child modules. the parent module examines its input data for patterns and/or sequences and then provides feedback to the child module or modules regarding the parent-level patterns that correlate with the child-level patterns. These systems and methods are extensible to large networks of interconnected processor modules.

Подробнее
31-05-2012 дата публикации

Automatic recognition of images

Номер: US20120134576A1
Принадлежит: Hewlett Packard Development Co LP

Presented is a method of automatically performing an action, based on graphical input. The method comprises: receiving, for a user, an input image; comparing the input image with the contents of a user-customized database comprising a plurality of records, each record representing a predefined class of image, wherein the user has previously associated records in the database with respective specified actions; attempting to recognize the image, based on the similarity of the input image to one of the predefined classes of image represented in the user-customised database; and if the image is recognized, performing the action previously associated by the user with the class. Also presented is apparatus for recognizing an image and a method of constructing a user-customized database.

Подробнее
07-06-2012 дата публикации

Methods and apparatus for automated true object-based image analysis and retrieval

Номер: US20120140990A1
Принадлежит: Google LLC

An automated and extensible system for analysis and retrieval of images based on region-of-interest (ROI) analysis of one or more true objects depicted by an image is provided. The system uses an database that is a relational or analytical database containing searchable vectors that represent the images stored in a repository. Entries in the database are created by an image locator and ROI classifier working together to locate images within the repository and extract relevant information to be stored in the ROI database. The ROI classifier analyzes objects in an image to arrive at actual features of the true object. Graphical searches are performed by the collaborative workings of an image retrieval module, an image search requestor and an ROI query module. The image search requestor is an abstraction layer that translates user or agent search requests into the language understood by the ROI query.

Подробнее
21-06-2012 дата публикации

Lead having a conductive polymer conductor

Номер: US20120158107A1
Принадлежит: Cardiac Pacemakers Inc

A medical electrical lead includes a conductive polymer conductor fabricated from a conductor-filled polyisobutylene urethane, urea or urethane/urea copolymer.

Подробнее
12-07-2012 дата публикации

Method of detecting logos, titles, or sub-titles in video frames

Номер: US20120177249A1
Принадлежит: Intel Corp

Detecting a static graphic object (such as a logo, title, or sub-title) in a sequence of video frames may be accomplished by analyzing each selected one of a plurality of pixels in a video frame of the sequence of video frames. Basic conditions for the selected pixel may be tested to determine whether the selected pixel is a static pixel. When the selected pixel is a static pixel, a static similarity measure and a forward motion similarity measure may be determined for the selected pixel. A temporal score for the selected pixel may be determined based at least in part on the similarity measures. Finally, a static graphic object decision for the selected pixel may be made based at least in part on the temporal score.

Подробнее
30-08-2012 дата публикации

Computer-readable storage medium, image recognition apparatus, image recognition system, and image recognition method

Номер: US20120219226A1
Автор: Satoru Osako
Принадлежит: Nintendo Co Ltd

First, it is determined whether or not a contour or vertices have been detected from a certain image. Then, when it is determined that a contour or vertices have been detected from the certain image, a pattern matching process is performed on, in the image, an area surrounded by the contour or the vertices detected from the image. Then, when it is determined that a predetermined object or a predetermined design is displayed in the area, detection position information indicating a position related to the area is stored in a storage area. On the other hand, when it is determined that a contour or vertices have not been detected from the certain image, a pattern matching process is performed on the image on the basis of the detection position information stored in the storage area.

Подробнее
06-09-2012 дата публикации

Meibomian gland imaging

Номер: US20120226156A1
Принадлежит: TearScience Inc

A method of evaluating dry eye in humans wherein the flow of naturally occurring secretion to the eye is reduced or stopped due to the presence of an obstruction of a meibomian gland in the eyelid involves applying a pressure to the eyelid that mimics pressure applied during blinking; and simultaneously imaging the glands to diagnose the condition of the meibomian gland. This abstract is not to be considered limiting, since other embodiments may deviate from the features described in this abstract.

Подробнее
06-09-2012 дата публикации

Accurate and Fast Neural network Training for Library-Based Critical Dimension (CD) Metrology

Номер: US20120226644A1
Принадлежит: KLA Tencor Corp, Tokyo Electron Ltd

Approaches for accurate neural network training for library-based critical dimension (CD) metrology are described. Approaches for fast neural network training for library-based CD metrology are also described.

Подробнее
13-09-2012 дата публикации

Medical implanatble lead with fixation detection

Номер: US20120232373A1
Принадлежит: St Jude Medical AB

The invention relates to a medical implantable lead of the kind being adapted to be implanted into a human or animal body for monitoring and/or controlling of an organ inside the body. The lead comprises in a distal end a tubular header ( 3 ) inside which a shaft ( 7 ) is rotatable as well as extendable and retractable arranged and carries in a distal end a combined fixation means and electrode member in form of a helix ( 4 ), which is provided with a first contact surface being electrically connectible to a connector at the proximal end of the lead by means of an electric conductor ( 8 ), and which by means of the shaft is rotatable in relation to the lead and extendable out from the distal end to be able to fixate the distal end of the lead to the organ by being screwed into the tissue. The shaft also carries a second contact surface ( 13 ) being positioned on or adjacent a proximal portion of the helix and being connectible to a connector at the proximal end of the lead by means of an electric conductor ( 8 ). The lead comprises a conduction controlling means ( 14 ), which at least during an initial stage after implantation is capable of render the first contact surface electrically inactive and which is capable of render the first contact surface electrically active after the initial stage. By means of the inventive lead it is possible to detect whether the helix is sufficient screwed into the tissue ( 12 ) or not.

Подробнее
20-09-2012 дата публикации

Oral optical diagnosing apparatus and operating method thereof

Номер: US20120238881A1
Принадлежит: Crystalvue Medical Corp

An oral optical diagnosing apparatus and operating method are disclosed. The oral optical diagnosing apparatus includes a positioning module, an optical sensing module, a processing module, and a display module. After the positioning module selects a region to be diagnosed in a mouth, the optical sensing module will perform optical sensing on the region to be diagnosed to obtain optical information related to the region to be diagnosed. The processing module is used to analyze the optical information to generate an optical diagnosed result. The display module is used to display the optical diagnosed result.

Подробнее
27-09-2012 дата публикации

Agricultural sprayer and method

Номер: US20120241533A1
Принадлежит: Deere and Co

A system for agricultural spraying including a solution reservoir and primary pump for delivering fluid to a plurality of laterally spaced nozzles interconnected by supply conduits. A chemical reservoir and chemical injection pump are interconnected to the output of the primary pump through a mixer. Controllers for the primary pump and chemical injection pump are coordinated to run the pumps a predetermined time to fill each of the supply conduits from the chemical injection pump and primary pump so as to automatically prime the injection system.

Подробнее
04-10-2012 дата публикации

Method for Designating a Target for a Weapon Having Terminal Guidance Via Imaging

Номер: US20120250935A1
Автор: Etienne Payot
Принадлежит: Thales SA

A method for designating a target in an area, intended for a weapon having terminal guidance via imaging, by means of an airborne optronic system comprising an imager associated with geolocation means and a processing unit. It comprises the steps of: acquisition of an image of the area by the imager of the system, and geolocation of this image by the geolocation means; extraction from a database of an orthoimage of the geolocated area, called the reference virtual image; designation of the position of the target in the reference virtual orthoimage; extraction from the reference virtual orthoimage of primitives around the position of the target, called virtual primitives; determination of the position of the target with respect to these virtual primitives; transferring the virtual primitives and the position of the target to the weapon having terminal guidance via imaging.

Подробнее
11-10-2012 дата публикации

Electronic device and facial image display apparatus

Номер: US20120257801A1
Автор: Kouetsu Wada
Принадлежит: Toshiba Corp

According to one embodiment, an electronic apparatus includes a storage device which stores face thumbnail indexing information including face images and time stamp information, extracting module configure to assign time zones to a video content data and to extract face images belonging to each time zone based on a time stamp information, classifying module configure to classify facial images of the same person from the extracted facial images, calculating module configure to calculate a frequency of appearance of each classified facial image, and facial image indication module configure to display a list of the facial images included in the facial image indexing information in a facial image indication in a two-dimensional display area, the facial image indication having time-zone-specific display areas in columns corresponding to the time zones, each facial image displayed in each time-zone-specific display area being displayed in a size based on the frequency of appearance.

Подробнее
11-10-2012 дата публикации

System and method for determining the informative zone of an image

Номер: US20120257830A1
Автор: Aibo Tian, Xuemei Zhang
Принадлежит: Hewlett Packard Development Co LP

A system and a method are disclosed that determine the informative zone of an image. A system and method include receiving image data representative of an image, determining the non-redundant regions of the image based on analysis of patterns of the image data, and determining an area of the image that encompasses the non-redundant regions of the image as the informative zone of the image.

Подробнее
25-10-2012 дата публикации

Method and system for identifying a license plate

Номер: US20120269398A1
Принадлежит: Xerox Corp

A license plate localization method and system based on a combination of a top-down texture analysis and a bottom-up connected component. An image with respect to a vehicle captured by an image capturing unit can be processed in order to locate and binarize a busy area. A black run with respect to the binarized image can be analyzed and classified and one or more objects (connected components) can be generated based on the black run classification. The objects can be further classified in accordance with their size utilizing a run-length based filter to filter out a non-text object. The leftover objects can then be spatially clustered and the uniformity and linearity of the clustered objects can be examined based on a linearity test. The clustered objects can be rejected if they fail the linearity test and the detected objects can further be matched with a plate edge characteristic in order to locate a license plate.

Подробнее
25-10-2012 дата публикации

Collision detection system, robotic system, collision detection method and program

Номер: US20120269422A1
Автор: Mitsuhiro Inazumi
Принадлежит: Seiko Epson Corp

A collision detection system includes a processing section, a drawing section, and a depth buffer. Depth information of an object is set to the depth buffer as depth map information. The drawing section performs a first drawing process of performing a depth test, and drawing a primitive surface on a reverse side when viewed from a predetermined viewpoint out of primitive surfaces constituting a collision detection target object with reference to the depth buffer. Further, the drawing section performs a second drawing process of drawing the primitive surface on the reverse side when viewed from a predetermined viewpoint out of the primitive surfaces constituting the collision detection target object without performing the depth test. The processing section determines whether or not the collision detection target object collides with the object on the target side based on the result of the first drawing process and the second drawing process.

Подробнее
25-10-2012 дата публикации

Surgically Implantable Electrodes

Номер: US20120271391A1
Автор: Giancarlo Barolat
Принадлежит: Individual

The present inventions provide for paddle lead electrodes that are capable of performing peripheral nerve stimulation, thereby modulating, controlling and/or reducing neuropathic pain in a patient, that are also surgically implantable, and that will remain fixed in place at the site of implantation when in use. More specifically, one or more embodiments of the electrodes of the present inventions are capable of being surgically implanted underneath a sheath of protective connective tissue that covers electrically excitable tissues and are adapted to electrically stimulate those tissues. Electrodes contemplated by embodiments of the present inventions are particularly well suited for perineurial implantation. Embodiments of the present inventions include methods of use associated with the electrodes.

Подробнее
25-10-2012 дата публикации

Analyzing the expression of biomarkers in cells with clusters

Номер: US20120271553A1
Автор: Colin Craig Mcculloch
Принадлежит: GE Global Research USA

A data set of cell profile data is stored. The cell profile data includes multiplexed biometric image data describing the expression of a plurality of biomarkers. Cell profile data is generated from tissue samples drawn from a cohort of patients having an assessment related to the commonality. Multiple sets of clusters of similar cells are generated from the data set; the proportion of cells in each cluster is examined for an association with a diagnosis, a prognosis, or a response; and a predictive set of clusters is selected based on model performance. One predictive set of clusters is selected based on a comparison of the performance of at least one model of the plurality of sets of clusters. Display techniques that aid in understanding the characteristics of a cluster are disclosed.

Подробнее
06-12-2012 дата публикации

Vehicle-mounted image processing apparatus

Номер: US20120307062A1
Принадлежит: HITACHI AUTOMOTIVE SYSTEMS LTD

There is provided a vehicle-mounted image processing device that is capable of making a plurality of processing units appropriately perform processes corresponding to scenes in which there are many types, such as people, vehicles, etc., and in which they are combined. Based on processing results of image processing by a plurality of processing units 40, the vehicle-mounted image processing device generates tag information representing the type and priority of image processing to be executed next by each of the processing units 40, and, using tag information generated during previous image processing, determines whether or not to have each of the processing units 40 perform image processing.

Подробнее
06-12-2012 дата публикации

Probes having deployable sites and methods for making the same

Номер: US20120310067A1
Принадлежит: University of Michigan

A probe for interfacing with biological tissue includes a shank. A site to receive a signal from or stimulate the biological tissue is deployably connected to the shank. An insulated interconnect is connected to the site to guide signals or a fluid between the site and the shank. An actuator displaces the site away from a protected position on the shank to a deployed position in the biological tissue to be monitored or stimulated by the site.

Подробнее
20-12-2012 дата публикации

Hybrid three-dimensional sensor array, in particular for measuring electrogenic cell assemblies, and the measuring assembly

Номер: US20120319705A1
Принадлежит: Technische Universitaet Ilmenau

The invention relates to a hybrid three-dimensional sensor array, in particular for measuring biological cell assemblies. The sensor array has a plurality of microstructured sensor plates, each having one carrier section on which a plurality of sensor needles are arranged in a comb-like manner, which carry a plurality of electrode surfaces. Furthermore, a plurality of spacer elements are provided, which are fastened between the sensor plates so that both the carrier sections and the sensor needles of adjacent sensor plates are at a distance from each other. The invention further relates to a measuring assembly for measuring electrical activities of biological cell assemblies using such a sensor array.

Подробнее
27-12-2012 дата публикации

Method and multi-scale attention system for spatiotemporal change determination and object detection

Номер: US20120328161A1
Принадлежит: Individual

A method and multi-scale attention system for the detection of objects and temporal change regions by a spatiotemporal attention operator of an image sequence, which linearly aggregates temporal change filter with spatial saliency filter and includes an extractor of salient maxima, which selects consecutive salient maxima of the spatiotemporal operator to produce the locations of the objects of interest and the centers of temporal change regions. The concept of spatial local scale introduced into the system and method for its determination allows for a scale-adaptive integration of the temporal change with spatial saliency and effective detection of different in size and location objects of interest. Can be used for object and spatiotemporal change detection in monitoring pollution, natural disasters, weather conditions and environmental changes based on satellite remote sensing imagery from various sensors.

Подробнее
10-01-2013 дата публикации

Method of obtaining spatial images on demand

Номер: US20130011017A1

Provided is a method of obtaining spatial images on demand. The server segments a spatial image into a plurality of regions to detect an isolated region whose continuity with peripheral regions is less than a threshold value, generates geographic information corresponding to the detected isolated region, and generates a capture request message including the generated geographic information. In addition, the capture request message may be transmitted to at least one terminal using unicast scheme, a multicast scheme, an anycast scheme, or a broadcast scheme. The capture request message may comprise a capture condition value such as a capture direction, a capture angle, a capture time, a zoom information and an exposure value. At least one terminal which meets the capture condition value within the capture request message transmits a captured image to the server.

Подробнее
31-01-2013 дата публикации

Determining a computer's position and system for manufacturing a tag

Номер: US20130027530A1
Принадлежит: International Business Machines Corp

A technical solution for accurately positioning a computer position, that is to say, the solution can identify the specific rack position where the computer is. And the solution has low cost and does not need manual intervention. The core idea of the solution lies in using a camera installed on the computer to read the contents of a tag on the rack, so as to identify the position information of the computer. Specifically, the solution provides a computer with a self-positioning function, wherein: a camera is installed on the computer, and the camera is configured to read the contents of a tag attached on a side of a rack to house the computer to identify the rack position where the computer is.

Подробнее
31-01-2013 дата публикации

Method and system for tracking objects

Номер: US20130031045A1

An object tracking system and method operable to minimize processing time for tracking objects is provided. The system includes a pair of filters operable to make associations between dynamic objects newly detected and previously detected. One of the pair of filters makes an association when the predicted location of the previously detected objects is within a predetermined distance of the newly detected object. The other of the pair of filters makes an association based upon the probability that a newly detected dynamic object is a previously detected dynamic object. The remaining unassociated dynamic objects are then localized so as to form discrete matrices for optimization filters.

Подробнее
14-02-2013 дата публикации

Method and apparatus of compiling image database for three-dimensional object recognition

Номер: US20130039569A1
Принадлежит: Olympus Corp, Osaka Prefecture University

A method of compiling an image database for a three-dimensional object recognition including the steps of: when a plurality of images each showing an object from different viewpoint are inputted, extracting local features from each of the images, and expressing the local features using feature vectors; forming sets of the feature vectors, each set representing a same part of the object from a series of the viewpoints, and generating subspaces, each subspace representing a characteristic of each set; and storing each subspace to the image database with an identifier of the object to perform a recognition process that is realized by the steps of: when at least one image of an object is given as a query, extracting query feature vectors; determining the subspace most similar to each query feature vector; and executing a counting process to the identifiers to retrieve an object most similar to the query.

Подробнее
21-02-2013 дата публикации

Mobile terminal and control method thereof

Номер: US20130044921A1
Принадлежит: LG ELECTRONICS INC

In a mobile terminal capable of retrieving data, and a control method thereof, the mobile terminal includes a display unit to display at least one object, and a controller to detect information included in an object selected by a user from the at least one object, retrieve objects each having data corresponding to the detected information, and process the retrieved objects to be associated with the selected object.

Подробнее
21-03-2013 дата публикации

Systems and methods for detecting cell phone usage by a vehicle operator

Номер: US20130070957A1
Принадлежит: Xerox Corp

An embodiment generally relates to systems and methods for determining cell phone usage automatically by individuals operating vehicles. A processing module can process multi-spectral images or videos of individuals and detect different regions in the image such as face regions, hand regions, and cell phone regions. Further, the processing module can analyze the regions based on locations and numbers of skin pixels and cell phone pixels to determine if the individual is holding his or her cell phone near his or her face. Based on the analysis, it can be determined whether the individual is operating the cell phone. Further, the analysis can yield a confidence level associated with the cell phone usage.

Подробнее
21-03-2013 дата публикации

Lumen Morphology and Vascular Resistance Measurements Data Collection Systems, Apparatus and Methods

Номер: US20130072805A1
Принадлежит: LIGHTLAB IMAGING, INC.

A method and apparatus of automatically locating in an image of a blood vessel the lumen boundary at a position in the vessel and from that measuring the diameter of the vessel. From the diameter of the vessel and estimated blood flow rate, a number of clinically significant physiological parameters are then determined and various user displays of interest generated. One use of these images and parameters is to aid the clinician in the placement of a stent. The system, in one embodiment, uses these measurements to allow the clinician to simulate the placement of a stent and to determine the effect of the placement. In addition, from these patient parameters various patient treatments are then performed. 1. An automated computer-based method of evaluating a segment of a lumen of a blood vessel , the method comprising the steps of:a. collecting a set of data regarding a lumen of length L using an optical coherence tomography system, the set comprising a plurality of cross sectional areas at a plurality of positions along the length;b. determining a vascular resistance ratio (VRR) using a processor and at least a portion of the set of data; andc. determining a characteristic of at least a portion of the segment disposed along the length L in response to the vascular resistance ratio.2. The method of wherein the region contains a stenotic lesion and the characteristic is a value denoting a stenotic lesion.3. The method of further comprising the step of displaying at least one of a numerical or graphical measure of a stent length and diameter used to treat the stenotic lesion.4. The method of wherein the step of determining the vascular resistance ratio is performed using a lumped resistor model.523.-. (canceled)24. A computer-based system for evaluating a region of a lumen claim 1 , the system comprising:an image acquisition system for collecting a set of data regarding a lumen of length L, the set comprising a plurality of cross sectional areas at a plurality of ...

Подробнее
28-03-2013 дата публикации

PRINTER IMAGE LOG SYSTEM FOR DOCUMENT GATHERING AND RETENTION

Номер: US20130077857A1
Принадлежит: XEROX CORPORATION

A system and method for document image acquisition and retrieval find application in litigation for responding to discovery requests. The method includes receiving automatically acquired electronic image logs comprising image data and associated records for documents processed by a plurality of image output devices within an organization. When a request for document production is received, the image logs (and/or information extracted therefrom) are automatically filtered through at least one classifier trained to return documents responsive to the document request, and documents corresponding to the filtered out image logs are output. One of the filters may be configured for filtering out documents that include attorney-client exchanges. 1. A method for processing a document production request received by an organization , comprising:receiving electronic image logs comprising image data and associated records for documents processed by a plurality of image output devices within the organization;with a data processing device, automatically filtering the electronic image logs, through a first classifier trained to return documents that are responsive to the document production request and a second classifier trained to return those of the responsive documents comprising attorney-client exchanges, the first and second classifiers having been trained through a machine learning method with training examples of the documents labeled with respective classes; andoutputting responsive documents with a label indicating whether they comprise attorney-client exchanges or not.2. The method of claim 1 , further comprising performing optical character recognition of the image data to identify textual content of the documents and wherein the electronic image logs filtered in the classification of the documents includes the textual content.3. The method of claim 1 , further comprising identifying duplicate document images and archiving only a single one of the duplicate images which ...

Подробнее
28-03-2013 дата публикации

METHOD AND APPARATUS FOR SORTING LiDAR DATA

Номер: US20130080057A1
Автор: Jeffrey J. Welty
Принадлежит: Weyerhaeuser NR Co

A programmed computer or non-transitory computer readable storage media has instructions that are executable by a processor to identify LiDAR data points associated with items of vegetation or other objects. Each LiDAR data point is tested to determine if it lies within the value of a closed surface defined for higher LiDAR points. If so, the LiDAR point is grouped with the LiDAR points associated with a previously identified item of vegetation. If not, a new item of vegetation is identified.

Подробнее
25-04-2013 дата публикации

Method and system for extraction and association of object of interest in video

Номер: US20130101209A1

The present disclosure relates to an image and video processing method, and in particular, to a two-phase-interaction-based extraction and association method for an object of interest in a video. In the method, a user performs coarse positioning interaction by an interactive method which is not limited to a normal manner and has a low requirement for prior knowledge; based on this, a certain extraction algorithm which is fast and easy to implement is adopted to perform multi-parameter extraction on the object of interest. In the method, on the basis of mining video information fully and ensuring user preference, in a manner where the viewing of the user is not affected, associate value-added information with the object which the user is interested in, thereby meeting the user's requirement for deeply knowing and further exploring an attention area.

Подробнее
02-05-2013 дата публикации

Information processing apparatus, information processing method, and computer-readable stroage medium

Номер: US20130108104A1
Принадлежит: Canon Inc

A pattern light projection unit which stores information on pattern light including information on line patterns projects pattern light including line patterns having at least two lines and at least one reference line pattern serving as a reference of the line patterns on an object in accordance with the information on pattern light. An image pickup unit captures an image of the object to which the pattern light is projected. An information processing apparatus detects the reference line pattern and the line patterns from the captured image, and establishes correspondence between the information on the line patterns stored in the pattern light projection unit and the line patterns detected from the captured image in accordance with the topological positional relationship between the detected reference line pattern and the line patterns so as to identify the line patterns.

Подробнее
02-05-2013 дата публикации

Information Processing Apparatus, Information Processing Method, and Computer Program

Номер: US20130108108A1
Принадлежит: Sony Corp

An information processing apparatus that executes processing for creating an environmental map includes a camera that photographs an image, a self-position detecting unit that detects a position and a posture of the camera on the basis of the image, an image-recognition processing unit that detects an object from the image, a data constructing unit that is inputted with information concerning the position and the posture of the camera and information concerning the object and executes processing for creating or updating the environmental map, and a dictionary-data storing unit storing dictionary data in which object information is registered. The image-recognition processing unit executes processing for detecting an object from the image with reference to the dictionary data. The data constructing unit applies the three-dimensional shape data to the environmental map and executes object arrangement on the environmental map.

Подробнее
09-05-2013 дата публикации

HEAD DETECTING METHOD, HEAD DETECTING APPARATUS, ATTRIBUTE DETERMINING METHOD, ATTRIBUTE DETERMINING APPARATUS, PROGRAM, RECORDING MEDIUM, AND ATTRIBUTE DETERMINING SYSTEM

Номер: US20130114889A1
Автор: Ueki Kazuya
Принадлежит: NEC SOFT, LTD.

The present invention is to provide a head detecting method for detecting the head in an image correctly at high speed. 1. A head detecting method using: a preliminary head detection model acquired with images each containing at least a part of a head in a defined image region defined preliminarily as positive examples and with images each not containing a head in the defined image region as negative examples; and a definitive head detection model acquired with images each containing a head in a state where it matches preliminarily defined position and size in the defined image region as positive examples and with images each containing a head in a state where it does not match at least one of the preliminarily defined position and size in the defined image region as negative examples , the method comprising:an image acquiring step of acquiring an image to be detected;a preliminary head detecting step of cutting out the defined image region of the image to be detected as an image patch and detecting head images from the image to be detected by referring to the preliminary head detection model; anda definitive head detecting step of detecting a definitive head image from plural head images acquired in the preliminary head detecting step by referring to the definitive head detection model.2. The method according to claim 1 , wherein the preliminary head detection model includes multistage reference models acquired claim 1 , by defining matching degrees in stages to the preliminarily defined position and size in the definitive head detection model claim 1 , with images each matching the preliminarily defined position and size as positive examples and with images each not matching the preliminarily defined position and size as negative examples claim 1 , in the preliminary head detecting step claim 1 , detection of head is performed in stages in accordance with each stage of the multistage preliminary head detection models claim 1 , and a head image of a current stage ...

Подробнее
09-05-2013 дата публикации

IMPLANTABLE IMAGING ARRANGEMENT AND METHOD FOR USING THE SAME

Номер: US20130116552A1
Принадлежит:

According to an exemplary embodiment of the present disclosure, apparatus and method can be provided for obtaining information associated with at least one anatomical structure. The exemplary apparatus can include at least one first arrangement which can be configured to provide at least one electro-magnetic radiation to at least one portion of the at least one anatomical structure. The first arrangement(s) can include a configuration which is configured to relatively permanently attach the apparatus to or in the at least one anatomical structure. The exemplary apparatus can further include at least one interferometric arrangement configured to receive a further radiation from the portion(s) which can be associated with the electro-magnetic radiation(s). 1. An apparatus for obtaining information associated with at least one anatomical structure , comprising:at least one first arrangement which is configured to provide at least one electro-magnetic radiation to at least one portion of the at least one anatomical structure, wherein the at least one first arrangement includes a configuration which is configured to relatively permanently attach the apparatus to or in the at least one anatomical structure; andat least one interferometric arrangement configured to receive a further radiation from the at least one portion which is associated with the at least one electro-magnetic radiation.2. The apparatus according to claim 1 , wherein the configuration includes at least one of a suction arrangement claim 1 , a hooking arrangement claim 1 , an adhesive arrangement or a surface tension arrangement.3. The apparatus according to claim 1 , wherein the at least one first arrangement includes a beam scanning arrangement.4. The apparatus according to claim 3 , wherein the beam scanning arrangement includes a micro electro-mechanical system (MEMS).5. The apparatus according to claim 3 , wherein the beam scanning arrangement includes a Risley prism arrangement.6. The apparatus ...

Подробнее
16-05-2013 дата публикации

System and Method for Randomized Point Set Geometry Verification for Image Identification

Номер: US20130121598A1
Принадлежит: FutureWei Technologies Inc

Object recognition can be improved by verifying a geometric consistency between matching interesting points pairs of two images, as objects with the images are more likely to match when the matching interesting points pairs are geometrically consistent. The geometric consistency between matching interesting points pairs can be verified in accordance with a topology code distance vector (D). The topology code distance vector (D) may be evaluated in accordance with a decision tree classifier, which may be trained in accordance with previous or historic topology code distance vectors. The topology code distance vector (D) may be computed from a subset of matching interesting points pairs having the shortest matching distance.

Подробнее
16-05-2013 дата публикации

OCCLUSION-CROSSING DEVICES, ATHERECTOMY DEVICES, AND IMAGING

Номер: US20130123615A1
Принадлежит:

Described herein are methods for producing and identifying characteristic (“crescent shaped”) regions indicative of an atherectomy plaque within a vessel, and systems and devices adapted to take advantage of this characteristic region. 1. A method of identifying an atherectomy plaque mass within a vessel , the method comprising:applying circumferential radial force within the vessel to displace a rigid plaque mass and force the vessel wall to stretch away from the device;imaging the vessel to create an image; andidentifying crescent-shaped structures associated with an atherectomy plaque in the image.2. The method of claim 1 , further comprising identifying the orientation of a plaque mass based on the directionality of the crescent-shaped structures.3. The method of claim 1 , further comprising identifying the position of a plaque mass relative to outer layered structures of a vessel wall based on the crescent-shaped structures.4. The method of claim 1 , wherein imaging the vessel comprises imaging the vessel with optical coherence tomography.5. The method of claim 1 , further comprising inserting a device into the vessel claim 1 , the device applying the circumferential radial force.6. The method of claim 5 , wherein imaging the vessel comprises imaging with an imaging sensor attached to the device.7. The method of claim 6 , further comprising orienting the device within the vessel based on the crescent-shaped structures.8. The method of claim 7 , wherein orienting the device comprises pointing a directional cutter at a plaque mass identified based upon the crescent-shaped structure.9. The method of claim 7 , wherein orienting the device comprises directing the device based upon the relationship between markers in the image and the crescent-shaped structures.10. The method of claim 6 , further comprising rotating the imaging sensor to obtain the image.11. An atherectomy device having a distal end configured to dissect plaque from within a vessel claim 6 , the ...

Подробнее
23-05-2013 дата публикации

Real-Time Player Detection From A Single Calibrated Camera

Номер: US20130128034A1
Автор: G. Peter K. Carr
Принадлежит: Disney Enterprises Inc

A method for detecting the location of objects from a calibrated camera involves receiving an image capturing an object on a surface from a first vantage point; generating an occupancy map corresponding to the surface; filtering the occupancy map using a spatially varying kernel specific to the object shape and the first vantage point, resulting in a filtered occupancy map; and estimating the ground location of the object based on the filtered occupancy map.

Подробнее
23-05-2013 дата публикации

LARGE-SCALE STRONGLY SUPERVISED ENSEMBLE METRIC LEARNING

Номер: US20130129202A1
Принадлежит: NEC Laboratories America, Inc.

Systems and methods for metric learning include iteratively determining feature groups of images based on its derivative norm. Corresponding metrics of the feature groups are learned by gradient descent based on an expected loss. The corresponding metrics are combined to provide an intermediate metric matrix as a sparse representation of the images. A loss function of all metric parameters corresponding to features of the intermediate metric matrix are optimized, using a processor, to learn a final metric matrix. Eigenvalues of the final metric matrix are projected onto a simplex. 1. A method for metric learning , comprising:iteratively determining feature groups of images based on its derivative norm;learning corresponding metrics of the feature groups by gradient descent based on an expected loss;combining the corresponding metrics to provide an intermediate metric matrix as a sparse representation of the images;optimizing, using a processor, a loss function of all metric parameters corresponding to features of the intermediate metric matrix to learn a final metric matrix; andprojecting eigenvalues of the final metric matrix onto a simplex.2. The method as recited in claim 1 , wherein iteratively determining feature groups of images includes projecting an opposite of partial derivative matrix onto positive semi-definite space.3. The method as recited in claim 1 , wherein iteratively determining feature groups of images includes evaluating each feature group by a partial derivative of loss function.4. The method as recited in claim 1 , wherein optimizing the loss function includes optimizing the loss function of all metric parameters corresponding to features of the intermediate metric matrix by gradient descent.5. The method as recited in claim 4 , wherein optimizing the loss function includes determining a step size by line search.6. A system for metric learning claim 4 , comprising:a sparse block diagonal metric ensembling module configured to iteratively ...

Подробнее
23-05-2013 дата публикации

Spectral image dimensionality reduction system and method

Номер: US20130129256A1
Принадлежит: Raytheon Co

Methods for reducing dimensionality of hyperspectral image data having a number of spatial pixels, each associated with a number of spectral dimensions, include receiving sets of coefficients associated with each pixel of the hyperspectral image data, a set of basis vectors utilized to generate the sets of coefficients, and either a maximum error value or a maximum data size. The methods also include calculating, using a processor, a first set of errors for each pixel associated with the set of basis vectors, and one or more additional sets of errors for each pixel associated with one or more subsets of the set of basis vectors. Utilizing such errors calculations, an optimum size of the set of basis vectors may be ascertained, allowing for either a minimum amount of error within the maximum data size, or a minimum data size within the maximum error value.

Подробнее
30-05-2013 дата публикации

Discriminative pretraining of deep neural networks

Номер: US20130138436A1
Принадлежит: Microsoft Corp

Discriminative pretraining technique embodiments are presented that pretrain the hidden layers of a Deep Neural Network (DNN). In general, a one-hidden-layer neural network is trained first using labels discriminatively with error back-propagation (BP). Then, after discarding an output layer in the previous one-hidden-layer neural network, another randomly initialized hidden layer is added on top of the previously trained hidden layer along with a new output layer that represents the targets for classification or recognition. The resulting multiple-hidden-layer DNN is then discriminatively trained using the same strategy, and so on until the desired number of hidden layers is reached. This produces a pretrained DNN. The discriminative pretraining technique embodiments have the advantage of bringing the DNN layer weights close to a good local optimum, while still leaving them in a range with a high gradient so that they can be fine-tuned effectively.

Подробнее
06-06-2013 дата публикации

Face recognition using multilayered discriminant analysis

Номер: US20130142399A1
Принадлежит: KING SAUD UNIVERSITY

Face recognition using multilayered discriminant analysis includes systems and methods applying an initial linear discriminate analysis to a database of face images in a more-or less conventional manner. Initial fuzzy logic then is applied to the results of the initial linear discriminate analysis to produce a subset of the database of face images. Thereafter, a subsequent linear discriminate analysis is applied to the subset of the database of face images and subsequent fuzzy logic is applied to the results of the subsequent linear discriminate analysis to produce a further subset of the subset of the database of face images. The application of the subsequent linear discriminate analysis and application of the subsequent fuzzy logic may be repeated until the further subset contains only one, or zero, face images.

Подробнее
06-06-2013 дата публикации

IMAGE CLUSTERING USING A PERSONAL CLOTHING MODEL

Номер: US20130142423A1
Принадлежит:

The disclosure relates to a system and a method for generating clothing feature data representative of at least one clothing feature of a piece of clothing being worn by the person in a set of images, and training a discriminative clothing classifier using the clothing feature data to provide a personal clothing model that corresponds to the piece of clothing. The personal clothing model can be used to identify additional images in which the person appears. 17407423004041250. A method performed using a physical computer system () comprising at least one processor () for generating a personal clothing model ( , ) for use in classifying an image ( , ) comprising:{'b': 16', '740', '52', '52, 'generating (), using the computer system (), clothing feature data representative of at least one clothing feature using clothing region data representative of clothing regions () detected in each image of a subset of images from a collection of images, each clothing region () being associated with a same clothing worn by a same person that appears in each image of the subset of images; and'}{'b': 18', '740', '300', '404', '300', '404', '12', '50, 'training (), using the computer system (), a discriminative clothing classifier using the clothing feature data to generate at least one personal clothing model (, ), wherein the at least one personal clothing model (, ), for use in classifying the image (, ), corresponds to the clothing.'}2300404. The method of claim 1 , further comprising using the at least one personal clothing model ( claim 1 , ) to classify an additional image in the collection of images that is not contained in the subset.3300404350300404352354300404. The method of claim 2 , wherein the using the at least one personal clothing model ( claim 2 , ) to classify an additional image in the collection of images comprises computing () a similarity score between the at least one personal clothing model ( claim 2 , ) and clothing feature data extracted from image data ...

Подробнее
06-06-2013 дата публикации

Optical Pattern Recognition Technique

Номер: US20130142424A1
Принадлежит: Individual

Disclosed is a distortion invariant system, method and computer readable medium for detecting the presence of one or more predefined targets in an input image. The input image and a synthetic discriminant function (SDF) reference image are correlated in a shift phase-encoded fringe-adjusted joint transform correlation (SPFJTC) correlator yielding a correlation output. A peak-to-clutter ratio (PCR) is determined for the correlation output and compared to a threshold value. A predefined target is present in the input image when the PCR is greater than or equal to the threshold value.

Подробнее
06-06-2013 дата публикации

Implantable neural tissue reporting probe and methods of manufacturing and implanting same

Номер: US20130144145A1
Автор: Ellis Meng
Принадлежит: University of Southern California USC

A method of manufacturing an implantable neural tissue reporting probe may include affixing multiple electrodes to polymeric material; heating the polymeric material to a temperature that is above its glass transition temperature, but below its melting temperature; applying force to the polymeric material while heated so as to cause the polymeric material to change into a shape that is suitable for implanting in neural tissue, the shape including a compartment having at least one opening therein sized to permit dendritic growth to occur through the opening from outside of the compartment to within the compartment after the probe is implanted; and allowing the polymeric material to cool down below its glass transition temperature while maintaining the shape of the compartment, including while maintaining the shape of the opening therein. Related probes and methods of implanting them into neural tissue are also disclosed.

Подробнее
13-06-2013 дата публикации

Post-processing a multi-spectral image for enhanced object identification

Номер: US20130148847A1
Принадлежит: Xerox Corp

What is disclosed is a system and method for post-processing a multi-spectral image which has already been processed for pixel classification. A binary image is received which contains pixels that have been classified using a pixel classification method. Each pixel in the image has an associated intensity value and has a pixel value of 1 or 0 depending on whether the pixel has been classified as a material of interest or not. The image is divided into a plurality of blocks of pixels. On a block by block basis, pixel values in a block are changed according to a threshold-based filtering criteria such that pixels in the same block all have the same binary value. Once all the blocks have been processed, contiguous pixels having the same binary value are grouped to form separate objects. In such a manner, pixel classification errors in the post-processed binary image can be reduced.

Подробнее
13-06-2013 дата публикации

Image Classification

Номер: US20130148881A1
Автор: Hui Xue
Принадлежит: Alibaba Group Holding Ltd

The present disclosure introduces a method and an apparatus for classifying images. Classification image features of an image for classification are extracted. Based on a similarity relationship between each classification image feature and one or more visual words in a pre-generated visual dictionary, each classification image feature is quantified by multiple visual words in the visual dictionary and a similarity coefficient between each classification image feature and each of the visual words is determined. Based on the similarity coefficient of each visual word that corresponds to different classification image features, a weight of each visual word is determined to establish a classification visual word histogram of the image for classification. The classification visual word histogram is input into an image classifier that is trained by sample visual word histograms arising from multiple sample images. An output result is used to determine a classification of the image for classification.

Подробнее
13-06-2013 дата публикации

Image processing method

Номер: US20130148893A1
Принадлежит: MBDA UK Ltd

An image-processing method comprising convolving a selected feature of interest (FOI) within the image with a mask of a first size, repeating the convolution with a mask of a second size, and calculating the ratio of the convolution responses, as an indication of the size of the FOI. Preferably the convolution masks are Laplacian of Gaussian. The method can be useful for prioritising potential targets in a field of view for presentation to an operator.

Подробнее
20-06-2013 дата публикации

Device and method for dispensing a liquid product that is to be sprayed onto a surface

Номер: US20130153676A1
Принадлежит: EXEL INDUSTRIES SA

The device according to the invention comprises a bar that includes several consecutive ducts with at least one inlet connected to a source of the liquid product and outlets communicating with nozzles. The device further comprises several sensors for measuring a physical property making it possible to determine a pressure difference between ducts or a pressure in one respective duct, several members designed to vary the pressures inside respective ducts, as well as at least one control unit estimating the pressure differences between ducts and driving the members to reduce those pressure differences or equalize those pressures. This device thus limits the pressure differences, and therefore flow differences, of the liquid product between the nozzles, in particular between the ends of very long bars moving over significant bankings.

Подробнее
20-06-2013 дата публикации

System and method for rapid oct image acquisition using compressive sampling

Номер: US20130156283A1

A method for rapid OCT image acquisition includes acquiring by OCT a plurality of compressive measurements (y) representing a set of under-sampled OCT data in a Dirac domain below a Nyquist rate by sampling an object of interest at randomly spaced vertical and horizontal lines in a Cartesian geometry using a raster scan, and recovering a 3D volumetric OCT image (f) from the compressive measurements (y) using compressive sampling. The method may also include recovering the 3D volumetric OCT image (f) from the compressive measurements (y) based at least in part on a sparsifying matrix (S) capable of transforming the 3D volumetric OCT image (f) into a sparse representation, such as a matrix representation of the 3D volumetric OCT image (f) in a shift-invariant wavelet transform domain. The method may also be applied to radial OCT scan patterns.

Подробнее
20-06-2013 дата публикации

Reciprocating Drive Optical Scanner for Surgical Endoprobes

Номер: US20130158392A1
Принадлежит:

A microsurgical endoprobe and method for use are provided. The microsurgical endoprobe may have a cannula assembly with a proximal element and a distal element coupled to a mechanical actuator. The microsurgical endoprobe may be configured to rotate at least one of the proximal element and the distal element in a first direction for an arc period, perform a microsurgical procedure on the tissue, and rotate the at least one of the proximal element and the distal element in a second direction opposite to the first direction for the arc period. The microsurgical endoprobe may include a hand-piece having a motor with a cannula assembly coupled to the hand-piece. 1. A microsurgical endoprobe comprisinga hand-piece comprising a motor;a cannula assembly coupled to the hand-piece; a first tube able to rotate about a longitudinal axis;', 'a second tube within the first tube, able to rotate within the first tube;', 'a distal optical element attached to the first tube; and', 'a proximal optical element attached to the second tube; wherein, 'the cannula assembly comprisingthe motor is coupled to provide a reciprocating rotational motion to at least one of the second tube and the first tube for an arc period.2. The endoprobe of wherein the distal optical element and the proximal optical element comprise a GRIN (gradient index) lens.3. The endoprobe of wherein the GRIN lenses have a face cut at a non-orthogonal angle relative to a longitudinal axis.4. The endoprobe of wherein at least one of the distal optical element and the proximal optical element comprise a prism.5. The endoprobe of wherein the reciprocating motion includesa first cycle rotating the first tube in a first direction and counter-rotating the second tube; anda second cycle rotating the second tube in the first direction and counter-rotating the first tube.6. The endoprobe of wherein the arc period is less than or equal to 180 degrees.7. The endoprobe of wherein at least one of the distal optical element and the ...

Подробнее
20-06-2013 дата публикации

Concentric Drive Scanning Probe

Номер: US20130158393A1
Принадлежит:

An endoprobe for microsurgical procedures is provided, including a hand-piece having a concentric drive having a proximal coupling and a distal coupling and a cannula assembly coupled to the hand-piece. The cannula assembly may include an outer tube having a longitudinal axis and an inner tube positioned within the outer tube, the distal coupling providing a first rotation to the outer tube about the longitudinal axis and the proximal coupling providing a second rotation to the inner tube within the outer tube. According to embodiments disclosed herein a method for scanning a light beam using a cannula assembly as described above is also provided. 1. An endoprobe for microsurgical procedures , comprising:a hand-piece having a concentric drive comprising a proximal coupling and a distal coupling;a cannula assembly coupled to the hand-piece; an outer tube having a longitudinal axis;', 'an inner tube positioned within the outer tube, the distal coupling providing a first rotation to the outer tube about the longitudinal axis and the proximal coupling providing a second rotation to the inner tube within the outer tube., 'the cannula assembly comprising2. The endoprobe of claim 1 , wherein the hand-piece includes a first motor coupled to the distal coupling to provide the first rotation and a second motor coupled to the proximal coupling to provide the second rotation.3. The endoprobe of claim 2 , further including a controller coupled to the first motor and the second motor claim 2 , wherein the first motor provides a rotation to the inner tube in one direction and the second motor provides a rotation to the outer tube in an opposite direction.4. The endoprobe of claim 1 , wherein the proximal coupling and the distal coupling are controlled independently of each other.5. The endoprobe of claim 1 , wherein the proximal coupling and the distal coupling are concentrically located about a probe longitudinal axis.6. The endoprobe of claim 1 , wherein the cannula assembly ...

Подробнее
27-06-2013 дата публикации

SYSTEMS, METHODS, AND APPARATUS FOR 3-D SURFACE MAPPING, COMPLIANCE MAPPING, AND SPATIAL REGISTRATION WITH AN ARRAY OF CANTILEVERED TACTILE HAIR OR WHISKER SENSORS

Номер: US20130166484A1
Принадлежит:

Systems, methods, and apparatus are provided using signals from a set of tactile sensors mounted on a surface to determine a surface topography. An example method includes receiving a set of moment and force input data from one or more identified topographies. The example method includes using a neural network to receive input from a training data set based on the first set of moment and force input data from the one or more identified topographies. Network weights to be used by the neural network to produce the training data set are modified via an evolutionary algorithm that tests vectors of candidate network weights. The example method includes receiving a moment and force input from a test object surface and reconstructing the surface topology based on the neural network outputs. 1. A method of determining surface topography of an object , the method comprising:receiving a first set of moment and force input data from one or more identified topographies;using a neural network to receive a training data set based on the first set of moment and force input data from the one or more identified topographies, wherein network weights to be used by the neural network are modified via an evolutionary algorithm that tests vectors of candidate network weights; andreceiving a second set of moment and force input data from an object surface and using the second set of data to provide a surface mapping of the object.3. The method of claim 1 , further comprising spatially registering local topographic mappings to form a combined mapped surface.4. The method of claim 1 , wherein the second set of moment and force input data from an object surface is to be obtained using a sensor array of tactile whisker or hair-like sensors.5. The method of claim 4 , where the sensor array comprises a four by four array.6. The method of claim 1 , wherein the surface mapping comprises a spatial map of the surface.7. The method of claim 6 , wherein the surface mapping comprises a compliance map ...

Подробнее
04-07-2013 дата публикации

Automated Network Disturbance Prediction System Method & Apparatus

Номер: US20130173514A1
Принадлежит: REV2 NETWORKS, INC.

An apparatus and method are provided for generating a prediction warning when an operational disturbance is detected in a computer, software program or in network. A classifying portion classifies problems or outages according to an impact that the problem or the outage has on the computer, software program or network. An analysis portion analyzes data and establishes links between isolated computer, software or network problems or outages, and outputs a likely cost of a future computer, software or network problem or outage. A reporting portion reports the prediction warning in response to the likelihood of the computer, software or future network problem or outage in a format that is selected based on a type of user. 1. An apparatus for generating a prediction warning when a future operational disturbance is predicted in a network , the apparatus comprising:a classifier that classifies problems or outages of a network according to an impact that the problem or the outage has on the network;an analyzer that analyzes data and establishes links between network problems or outages, the analyzer outputs a probable monetary cost of a future network problem or outage; anda reporting unit that reports the prediction warning indicating a future operational disturbance of the network problem or outage in a format that is selected based on a type of user.2. The apparatus according to claim 1 , further comprising a database that stores information relating to network problems or outages from a plurality of data sources.3. The apparatus according to claim 2 , further comprising a collecting unit that collects the information autonomously from the plurality of data sources.4. The apparatus according to claim 1 , wherein the data sources are selected from the group consisting of printed matter claim 1 , electronic data stored in a database claim 1 , and telemetry data.5. The apparatus according to claim 1 , further comprising a materiality unit that assigns a materiality score ...

Подробнее
11-07-2013 дата публикации

Image concealing via efficient feature selection

Номер: US20130177244A1
Принадлежит: General Electric Co

A novel technique for unsupervised feature selection is disclosed. The disclosed methods include automatically selecting a subset of a feature of an image. Additionally, the selection of the subset of features may be incorporated with a congealing algorithm, such as a least-square-based congealing algorithm. By selecting a subset of the feature representation of an image, redundant and/or irrelevant features may be reduced or removed, and the efficiency and accuracy of least-square-based congealing may be improved.

Подробнее
11-07-2013 дата публикации

SYSTEM AND METHOD FOR ACQUIRING IMAGES FROM WITHIN A TISSUE

Номер: US20130178735A1
Автор: Iddan Gavriel J.
Принадлежит: GIVEN IMAGING LTD.

Systems and methods for imaging within depth layers of a tissue include illuminating light rays at different changing wavelengths (frequencies), collimating illuminated light rays using a collimator, and splitting light rays using a beam splitter, such that some of the light rays are directed towards a reference mirror and some of the rays are directed towards the tissue. The systems and methods further include reflecting light rays from the reference mirror towards the imager, filtering out non-collimated light rays reflected off the tissue by using a telecentric optical system, and reflecting collimated light rays reflected off the tissue towards the imager, thus creating an image of an interference pattern based on collimated light rays reflected off the tissue and off the reference mirror. The method may further include creating full 2D images from the interference pattern for each depth layer of the tissue using Fast Fourier transform. 1. A system for acquiring images from within depth layers of a tissue , said system comprising:an illumination source for illuminating a tissue, wherein said illumination source illuminates a large illumination beam area;a collimator for collimating the light from the illumination source; a beam splitter located between the illumination source and the tissue;', 'a moveable reference mirror; and', 'an imager,', 'wherein optical axes of said moveable mirror and said imager are perpendicular to the optical axis of collimated light from said illumination source and to collimated light from said tissue, and wherein said beam splitter is located between said moveable mirror and said imager; and, 'an interferometer comprisingtelecentric optical system for passing through only collimated reflected light, said telecentric optical system located between the beam splitter and the tissue,wherein said imager is to generate an interference pattern for each depth layer of the tissue, according to the collimated reflected light.2. The system ...

Подробнее
18-07-2013 дата публикации

Method and Apparatus for Training a Probe Model Based Machine Vision System

Номер: US20130182948A1
Принадлежит:

A method for training a pattern recognition algorithm including the steps of identifying the known location of the pattern that includes repeating elements within a fine resolution image, using the fine resolution image to train a model associated with the fine image, using the model to examine the fine image resolution image to generate a score space, examining the score space to identify a repeating pattern frequency, using a coarse image that is coarser than the finest image resolution image to train a model associated with the coarse image, using the model associated with the coarse image to examine the coarse image thereby generating a location error, comparing the location error to the repeating pattern frequency and determining if the coarse image resolution is suitable for locating the pattern within a fraction of one pitch of the repeating elements. 1. A method for training a pattern recognition algorithm for a machine vision system that uses models of a pattern to be located , the method comprising the steps of:(a) identifying the known location of the pattern that includes repeating elements within a fine image resolution image;(b) using the fine image resolution image to train a model associated with the fine image;(c) using the model associated with the fine image to examine the fine image resolution image and to generate a score space;(d) examining the score space to identify a repeating pattern frequency;(e) using a coarse image at a coarse image resolution that is coarser than the finest image resolution image to train a model associated with the coarse image;(f) using the model associated with the coarse image to examine the coarse image thereby generating a location error;(g) comparing the location error to the repeating pattern frequency; and(h) based on the comparison, determining if the coarse image resolution is suitable for locating the pattern within a fraction of one pitch of the repeating elements.2. The method of further including the step ...

Подробнее
18-07-2013 дата публикации

MONITORING DATA ANALYZING APPARATUS, MONITORING DATA ANALYZING METHOD, AND MONITORING DATA ANALYZING PROGRAM

Номер: US20130185236A1
Автор: Tonouchi Toshio
Принадлежит: NEC Corporation

An object of the present invention is to reduce a prediction error even if a monitoring target system has a plurality of patterns of use. A monitoring data analyzing apparatus includes a log data file configured to accumulate log data including monitoring data in a monitoring target system set as a target of performance management, a data classifying section configured to classify the log data into a plurality of groups on the basis of characteristics of use status data included in the log data and indicating statuses of use of components of the monitoring target system, and a regression-model generating section configured to execute a regression analysis of the log data and generate a regression model for each of the groups. 1. A monitoring data analyzing apparatus comprising:a data accumulating section configured to accumulate log data including monitoring data in a monitoring target system set as a target of performance management;a data classifying section configured to classify the log data into a plurality of groups on the basis of characteristics of use status data included in the log data and indicating statuses of use of components of the monitoring target system; anda regression-model generating section configured to execute a regression analysis of the log data and generate a regression model for each of the groups.2. The monitoring data analyzing apparatus according to claim 1 , further comprising a characteristic-data-item extracting section configured to extract claim 1 , out of data items included in the log data claim 1 , the data items related to an explanatory variable of the regression model as characteristic data items.3. The monitoring data analyzing apparatus according to claim 2 , wherein the characteristic-data extracting section calculates claim 2 , for each of the groups claim 2 , dependencies on the explanatory variable in the data items of the data forming the group claim 2 , and extracts data items having the calculated dependencies ...

Подробнее
25-07-2013 дата публикации

High density multi-electrode array

Номер: US20130187253A1
Принадлежит: International Business Machines Corp

A high density micro-electrode array includes a transistor layer including a plurality of access transistors and a substrate in operable communication with the transistor layer including, wherein at least a portion of the substrate includes a plurality of trenches. The system includes a plurality of electrodes at least partially located in the plurality of trenches, wherein each of the plurality of electrodes is connected to at least one of the plurality of access transistors and wherein each of the electrodes is separated by a distance less than approximately one microns.

Подробнее
25-07-2013 дата публикации

Automated indexing for distributing event photography

Номер: US20130188844A1
Автор: David A. Goldberg
Принадлежит: Hysterical Sunset Ltd

The present method relates to the automated indexing of event images for distribution. The automated indexing can use automated facial recognition to determine which people are in each image. The images indexed in this fashion can be presented in a gallery, ordered by characteristics of the people in the images such as their name or room number, so as to facilitate the selection of the images by the people. The identification of the people in the images can be assisted by security or other information regarding the people that may be available to the event manager. Furthermore, the closeness of the relationships of two people can be inferred from the degree to which the people are in the same images, allowing the people in the images to be placed into groups, which can be hierarchical and/or overlapping, and which can assist in the organization of images being presented to the people, either in a gallery or electronic display format.

Подробнее
25-07-2013 дата публикации

Method to assess aesthetic quality of photographs

Номер: US20130188866A1
Принадлежит: Telefonica SA

A method to assess aesthetic quality of photographs, including classifying photographs into categories; generating computational models of image aesthetics, each computational model of image aesthetics associated to one different category of the categories; extracting a plurality of features from a photograph, the plurality of features being simplicity features, global features computed in the whole image and/or low-level features in contrasting regions of an image of said photograph. The contrasting regions are partitions of the image obtained by applying an image segmentation algorithm based on feature contrast to the photograph. The method also including applying a computational model of image aesthetics to at least part of the plurality of features extracted from said photograph, the computational model applied according to the category of the photograph, in order to assess aesthetic quality of the photograph.

Подробнее
01-08-2013 дата публикации

Virtual environment generating system

Номер: US20130194259A1
Принадлежит: Individual

A system and related methods for visually augmenting an appearance of a physical environment as seen by a user through a head-mounted display device are provided. In one embodiment, a virtual environment generating program receives eye-tracking information, lighting information, and depth information from the head-mounted display. The program generates a virtual environment that models the physical environment and is based on the lighting information and the distance of a real-world object from the head-mounted display. The program visually augments a virtual object representation in the virtual environment based on the eye-tracking information, and renders the virtual object representation on a transparent display of the head-mounted display device.

Подробнее
01-08-2013 дата публикации

Image processor, image processing method, learning device, learning method and program

Номер: US20130195351A1
Автор: Takehiro Hamada
Принадлежит: Sony Corp

Disclosed herein is an image processor including: a feature point extraction section adapted to extract the feature points of an input image; a correspondence determination section adapted to determine the correspondence between the feature points of the input image and those of a reference image using a feature point dictionary; a feature point coordinate distortion correction section adapted to correct the coordinates of the feature points of the input image corresponding to those of the reference image; a projection relationship calculation section adapted to calculate the projection relationship between the input and reference images; a composite image coordinate transform section adapted to generate a composite Image to be attached from a composite image; and an output image generation section adapted to merge the input image with the composite image to be attached.

Подробнее
01-08-2013 дата публикации

IMAGE INDEX GENERATION BASED ON SIMILARITIES OF IMAGE FEATURES

Номер: US20130195361A1
Автор: CHEN KE, Deng Yu
Принадлежит: ALIBABA GROUP HOLDING LIMITED

Embodiments of the present application relate to an image index generation method, system, a device, and a computer program product. An image index generation method is provided. The method includes selecting an image included in an image library for which an image index is to be generated, determining at least one target region included in the image, extracting visual features from the determined at least one target region, determining a similarity value of the selected image and image included in the image library based on the extracted visual features, determining image categories to which the images belong to based on the determined similarity values among the images, and assigning category identifiers to the images in accordance with an identifier assignment method, the identifier assignment method assigns the same category identifiers to images belonging to the same image category, and different category identifiers to images belonging to different image categories. 1. A method for managing images , comprising:selecting, from a storage device, an image included in an image library for which an image index is to be generated;determining at least one target region included in the image;extracting a set of one or more visual features from the determined at least one target region;determining, using one or more computer processors, a similarity value of the selected image and another image included in the image library based on the extracted set of visual features;determining image categories to which the images included in the image library belong, based at least in part on the determined similarity value of the selected image and the other image; andassigning category identifiers to the images included in the image library, wherein a same category identifier is assigned to images belonging to a same image category, and different category identifiers are assigned to images belonging to different image categories.2. The method as described in claim 1 , wherein:the ...

Подробнее
01-08-2013 дата публикации

HEMOGLOBIN CONTRAST IN MAGNETO-MOTIVE OPTICAL DOPPLER TOMOGRAPHY, OPTICAL COHERENCE TOMOGRAPHY, AND ULTRASOUND IMAGING METHODS AND APPARATUS

Номер: US20130197346A1
Автор: Milner Thomas E.

Provided herein are systems, methods, and compositions for the use of optical coherence tomography for detection of cells. 1. A method for detecting a lymphocyte , comprising: applying a first magnetic field strength to the lymphocyte , wherein the lymphocyte comprises a cellular membrane and a magnetically susceptible material; applying a second magnetic field strength to the lymphocyte , wherein the second magnetic field strength is different from the first magnetic field strength and interacts with the magnetically susceptible material to cause a change in the lymphocyte relative to interaction of the lymphocyte with the first magnetic field strength; and detecting the lymphocyte by detecting the change in the lymphocyte , wherein the change is detected using a phase sensitive frequency domain optical coherence tomographic imaging modality including a common path interferometer during the application of at least one of the first and second magnetic field strengths.2. The method of claim 1 , wherein the change is selected from the group consisting of:movement of the lymphocyte, movement of the magnetically susceptible material, a change in the cellular membrane tension level, and a change in the internal strain field of the lymphocyte.3. The method of claim 1 , wherein the phase sensitive optical coherence tomographic imaging modality comprises using a probe for transmitting and receiving light energy to and from the lymphocyte.4. The method of claim 3 , wherein the probe further comprises a magnetic source for applying at least one of the first and second magnetic field strengths to the lymphocyte.5. The method of claim 1 , wherein at least one of the first and second magnetic field strengths is applied to the lymphocyte from a magnetic source located external to the probe.6. The method of claim 1 , wherein the magnetically susceptible material is located within the lymphocyte.7. The method of claim 1 , wherein the magnetically susceptible material is targeted to ...

Подробнее
08-08-2013 дата публикации

METHOD FOR THE COMPUTER-AIDED LEARNING OF A RECURRENT NEURAL NETWORK FOR MODELING A DYNAMIC SYSTEM

Номер: US20130204815A1
Принадлежит:

A method for the computer-aided learning of a recurrent neural network for modeling a dynamic system which is characterized at respective times by an observable vector with one or more observables as entries is provided. The neural network includes both a causal network with a flow of information that is directed forwards in time and a retro-causal network with a flow of information which is directed backwards in time. The states of the dynamic system are characterized by first state vectors in the causal network and by second state vectors in the retro-causal network, wherein the state vectors each contain observables for the dynamic system and also hidden states of the dynamic system. Both networks are linked to one another by a combination of the observables from the relevant first and second state vectors and are learned on the basis of training date including known observables vectors. 115.-. (canceled)16. A method for computer-aided learning of a recurrent neural network for modeling a dynamic system which is characterized at respective times by an observable vector comprising one or more observables as entries , the method comprising: wherein the causal network describes an information flow proceeding forward in time between first state vectors of the dynamic system, wherein a first state vector at a respective point in time comprises one or more first entries which are each assigned to an entry of the observable vector, and one or more hidden states of the dynamic system,', 'wherein the retro-causal network describes an information flow proceeding backward in time between second state vectors of the dynamic system, wherein a second state vector at a respective point in time comprises one or more second entries which are each assigned to an entry of the observable vector, and one or more hidden states of the dynamic system,, 'providing a recurrent neural network comprising a causal network, a retro-causal network, an observable vector with one or more ...

Подробнее
15-08-2013 дата публикации

RECEPTIVE FIELD LEARNING FOR POOLED IMAGE FEATURES

Номер: US20130208977A1
Автор: Huang Chang, Jia Yangqing
Принадлежит: NEC Laboratories America, Inc.

Systems and methods are disclosed for image classification by receiving an overcomplete set of spatial regions, jointly optimizing the classifier and the pooling region for each pooled feature; and performing incremental feature selection and retraining using a grafting process to efficiently train the classifier. 1. An image classification method , comprising:receiving an overcomplete set of spatial regions;jointly optimizing the classifier and the pooling region for each pooled feature; andperforming incremental feature selection and retraining using a grafting process to efficiently train the classifier.2. The method of claim 1 , comprising extracting local image patches and converting the images to a set of overcomplete representation (coding).3. The method of claim 1 , comprising determining statistics of local representations over predefined spatial regions (pooling).4. The method of claim 1 , comprising collecting statistics to perform a final image classification task.7. The method of claim 1 , comprising performing fast approximate learning.9. The method of claim 8 , comprising approximately retraining a model on selected subset.10. The method of claim 1 , comprising performing local patch based claim 1 , multiple-layer pipelining to find predetermined image features for a task.11. An image classification system claim 1 , comprising:means for receiving an overcomplete set of spatial regions, andmeans for jointly optimizing the classifier and the pooling region for each pooled feature; andmeans for performing incremental feature selection and retraining using a grafting process to efficiently train the classifier.12. The method of claim 1 , comprising means for extracting local image patches and converting the images to a set of overcomplete representation (coding).13. The system of claim 11 , comprising means for determining statistics of local representations over predefined spatial regions (pooling).14. The system of claim 11 , comprising means for ...

Подробнее
15-08-2013 дата публикации

Sensing probe comprising multiple, spatially separate, sensing sites

Номер: US20130211222A1
Автор: Simon F. Giszter
Принадлежит: Philadelphia Health and Education Corp

A single sensing probe comprising multiple, spatially separate, sensing sites is utilized to sense neural activity. The sensing probe includes multiple conductors each with multiple sensing sites in a fixed geometric arrangement. The sensing probe is configured to comprise multiple combined sensing sites in polytrode configuration. By appropriately combining the wire groupings at each combined sensing site, activity sensed from a single wire with multiple sensing sites, can be coupled with other wires to unmix signals from the spatially separate sites and leverage the power of combinatorics to maximize total recording bandwidth and single neuron/unit yield per wire and per probe.

Подробнее
22-08-2013 дата публикации

METHOD AND APPARATUS FOR WARNING A DRIVER OF CARELESS DRIVING

Номер: US20130215274A1

Provided is an apparatus for sensing careless driving using a camera attached to a vehicle and warning a driver of a careless driving state, the apparatus including: a driving state determination unit for sensing a driving state of a vehicle based on a video of lanes; a lane-deviation sensing unit for sensing whether the vehicle deviated from the lane based on the video of lanes received from an image-processing unit; and a careless driving warning unit for generating a warning signal based on driving state information and lane deviation information received from the driving state determination unit and the lane-deviation sensing unit, respectively. 1. An apparatus for warning a driver of careless driving , the apparatus comprising:a driving state determination unit for sensing a driving state of a vehicle based on a video of lanes;a lane-deviation sensing unit for sensing whether the vehicle deviated from the lane based on the video of lanes received from an image-processing unit; anda careless driving warning unit for generating a warning signal based on driving state information and lane deviation information received from the driving state determination unit and the lane-deviation sensing unit, respectively.2. The apparatus of claim 1 , wherein the driving state determination unit recognizes a left lane and a right lane of the vehicle in the video of lanes claim 1 , and sets a center point of the vehicle on a horizontal line connecting the left lane and the right lane.3. The apparatus of claim 2 , wherein the driving state determination unit calculates a standard deviation of the vehicle moving left or right based on the center point during a predetermined period of time claim 2 , and when the standard deviation is higher than a threshold value claim 2 , senses the driving state of the vehicle to be a careless driving state.4. The apparatus of claim 1 , wherein the lane-deviation sensing unit senses that the vehicle deviated from the lane when only one lane is ...

Подробнее
22-08-2013 дата публикации

SYSTEMS, METHODS AND COMPUTER PROGRAM PRODUCTS FOR IDENTIFYING OBJECTS IN VIDEO DATA

Номер: US20130216094A1
Автор: DeLean Bruno
Принадлежит:

Image based operating systems and methods are provided that identify objects in video data and then take appropriate action in a wide variety of environments. In some embodiments, the image based operating systems and methods allow a user to activate other devices and systems by making a gesture. 1. A method of identifying an object in a feed of images , the method comprising the steps of:a. analyzing a plurality of sequential frames from a feed of frames;b. selecting in each frame, one or more unit areas of interest;c. applying to each unit area a plurality of detectors, wherein each detector provides a value expressing one aspect of a target object;d. assembling data in a sample vector, wherein the data comprises a plurality of components and each component is the individual value outcome of a given detector applied on a given unit area from a given frame; ande. evaluating the performance of the sample vector by counting in the vicinity of the sample vector, all vectors known with the target object to form a first count, and counting all vectors known with or without the target object, as acquired during a training phase to form a second count, wherein the ratio of the first count to the second count estimates the probability of the presence of the target object.2. The method of claim 1 , wherein the target object is a global target that can be decomposed in subparts and each subpart is a component of the sample vector.3. The method of claim 2 , wherein each individual subpart has been trained on a specific set of data and wherein consolidated detection is later trained on a set involving the final global target.4. The method of claim 1 , wherein each of the plurality of components comprises an aggregate score.5. The method of claim 1 , wherein the data is in a form of a two dimensional matrix.6. A method of identifying an object in a feed of images claim 1 , the method comprising the steps of:receiving video data, wherein said video data corresponds to a ...

Подробнее
22-08-2013 дата публикации

Round-trip engineering apparatus and methods for neural networks

Номер: US20130218821A1
Принадлежит:

Apparatus and methods for high-level neuromorphic network description (HLND) framework that may be configured to enable users to define neuromorphic network architectures using a unified and unambiguous representation that is both human-readable and machine-interpretable. The framework may be used to define nodes types, node-to-node connection types, instantiate node instances for different node types, and to generate instances of connection types between these nodes. To facilitate framework usage, the HLND format may provide the flexibility required by computational neuroscientists and, at the same time, provides a user-friendly interface for users with limited experience in modeling neurons. The HLND kernel may comprise an interface to Elementary Network Description (END) that is optimized for efficient representation of neuronal systems in hardware-independent manner and enables seamless translation of HLND model description into hardware instructions for execution by various processing modules. 1. Computer readable apparatus comprising a storage medium , said storage medium comprising at least one computer program with a plurality of instructions , said at least one program being capable of implementing round-trip engineering method in a neural network by at least:enabling receiving user inputs via a graphical user interface;based at least in part on first user input indicative of a plurality of nodes within said network, automatically generating first single network description instruction;based at least in part on second user input indicative of a tag, automatically generating second single network description instruction; andbased at least in part on third user input indicative of node connections, automatically generating third single network description instruction; and 'said first, second and third single instructions, when executed, are configured to: (i) generate said plurality of nodes; (ii) select a portion of said plurality of nodes based on said tag, ...

Подробнее
29-08-2013 дата публикации

Locking Plate with Screw Fixation from Opposite Cortex

Номер: US20130226248A1
Принадлежит: OSTEOMED LLC

An apparatus for supporting a bone includes a plate configured for positioning on a tension side of the bone. Two or more fasteners are configured to extend from an opposite side of the bone to the plate, and engage the plate after extending through the bone. The plate has an attachment mechanism operable to engage with the fasteners. In other aspects, a method of performing a surgical procedure includes positioning a plate on a tension side of a bone, and forming a hole from an opposite side of the bone to the plate. A fastener is inserted through the hole to the plate, and the plate is adjusted into position on the bone surface on the tension side of the bone. One or more additional holes are formed from the opposite side of the bone to the plate, and one or more additional fasteners are inserted.

Подробнее
05-09-2013 дата публикации

System and Method for Reducing Angular Geometric Distortion in an Imaging Device

Номер: US20130231558A1
Принадлежит: VOLCANO CORPORATION

A system and method are provided for significantly reducing or substantially eliminating angular geometric distortions in devices designed for imaging and/or inspection of an interior portion or surface of a cavity. A series of processing steps or methods may be employed to eliminate Non-Uniform Rotational Distortion (NURD) in such devices, for example, unidirectional and bi-directional intravascular ultrasonic (IVUS) imaging systems. The system may include a processor and an electronic module which control operation of a transducer assembly provided at a distal end of a catheter assembly. The system invokes a first processing step or method to collect and store raw angle and line data, as well as one or more of second and third processing steps or methods which adjust for NURD experienced during backlash of a bi-directional imaging system and a fourth processing step or method which performs a line-to-line correlation function. 165-. (canceled)66. A system for imaging a vessel , comprising: receive imaging data from the ultrasound imaging device while the ultrasound imaging device is rotated in the first and second directions; and', removing backlash NURD that is generated when the rotational direction of the ultrasound imaging device is changed between the first and second directions based on backlash NURD data associated with the ultrasound imaging device; and', 'performing angular correlation to remove backlash NURD that is generated when the rotational direction of the ultrasound imaging device is changed between the first and second directions., 'reduce non-uniform rotational distortion (NURD) generated in the received imaging data by performing at least one of], 'a processing system configured to be in communication with a flexible elongate member having an ultrasound imaging device attached thereto, the ultrasound imaging device configured to rotate in a first direction and a second direction opposite the first direction, the processing system configured ...

Подробнее
05-09-2013 дата публикации

CONTINUOUS-WEIGHT NEURAL NETWORKS

Номер: US20130232097A1
Принадлежит: California Institute of Technology

A computer-based multi-layer artificial network named Continuous-weight neural network (CWNN) configured to receive an input feature set wherein the input feature set comprises a variable number of features is disclosed. A method for classifying input sets based on a trained CWNN is also disclosed. Various implementation examples are also provided. 1. A computer-based multi-layer artificial network named continuous-weight neural network (CWNN) configured to receive an input feature set wherein the input feature set comprises a variable number of features.2. The CWNN of claim 1 , wherein each feature of the variable number of features is represented by an input pair comprising an input value and an input point provided to the CWNN claim 1 , the input value being a real number input value and the input point being a real vector input point.3. The CWNN of claim 1 , wherein the input feature set is an impulse representation (IR).4. The CWNN of further comprising a main network and a control network claim 2 , wherein the control network is a multilayer perceptron.5. The CWNN of claim 4 , wherein the control network comprises an input layer comprising Cnodes claim 4 , and wherein Cequals to a dimension of the real vector input point.6. The CWNN of claim 5 , wherein the control network further comprises an output layer comprising Cnodes claim 5 , and wherein the main network comprises a hidden layer comprising Cnodes.7. The CWNN of claim 6 , wherein the main network further comprises a plurality of input nodes equal to the variable number of features claim 6 , and wherein the input value of the variable number of features is fed to the input nodes.8. The CWNN of claim 7 , further comprising:{'sub': O', 'O, 'Cconnections between the Cnodes of the hidden layer and an input node of the main network; and'}{'sub': O', 'O', 'O, 'Cweights associated to each of the Cconnections, wherein the Cweights are in correspondence of an output of the control network.'}9. The CWNN of claim 8 ...

Подробнее
12-09-2013 дата публикации

Systems and Methods for Adaptive Smart Environment Automation

Номер: US20130238538A1
Принадлежит: WSU Research Foundation

Several embodiments of systems and methods for adaptive smart environment automation are described herein. In one embodiment, a computer implemented method includes determining a plurality of sequence patterns of data points in a set of input data corresponding to a plurality of sensors in a space. The input data include a plurality of data points corresponding to each of the sensors, and the sequence patterns are at least partially discontinuous. The method also includes generating a plurality of statistical models based on the plurality of sequence patterns, and the individual statistical models corresponding to an activity of a user. The method further includes recognizing the activity of the user based on the statistical models and additional input data from the sensors. 1a plurality of sensors installed in a space, the sensors being configured to provide input data including a plurality of data points corresponding to each of the sensors; and an activity miner configured to analyze the input data from the plurality of sensors to determine a plurality of sequence patterns of data points, the sequence patterns being at least partially discontinuous; and', 'an activity model configured to generate a plurality of statistical models based on the plurality of sequence patterns, the individual statistical models corresponding to an activity of a user., 'a controller operatively coupled to the sensors, the controller including. A computer system, comprising: This application is a continuation of, and claims priority to U.S. application Ser. No. 12/552,998, filed on Sep. 2, 2009, which claims priority to U.S. Provisional Application No. 61/096,257, filed on Sep. 11, 2008, the disclosures of which are incorporated herein by reference in their entirety.This work was supported by National Science Foundation Grants #IIS-0121297 and #IIS-0647705 and National Institutes of Health Subcontract #1R21DA024294-01.This technology is related to systems and methods for smart ...

Подробнее
19-09-2013 дата публикации

Multispectral Detection of Personal Attributes for Video Surveillance

Номер: US20130243256A1
Принадлежит: International Business Machines Corp

Techniques, systems, and articles of manufacture for multispectral detection of attributes for video surveillance. A method includes generating one or more training sets of one or more multispectral images, generating a group of one or more multispectral box features, using the one or more training sets to select one or more of the one or more multispectral box features to generate a multispectral attribute detector, and using the multispectral attribute detector to identify a location of an attribute in video surveillance, wherein using the multispectral attribute detector comprises, for one or more locations on each spectral band level of the multispectral image, applying the multispectral attribute detector and producing an output indicating attribute detection or an output indicating no attribute detection, and wherein the attribute corresponds to the multispectral attribute detector.

Подробнее
26-09-2013 дата публикации

ROTATION-FREE RECOGNITION OF HANDWRITTEN CHARACTERS

Номер: US20130251249A1
Автор: Du Jun, Huo Qiang
Принадлежит: MICROSOFT CORPORATION

A character recognition system receives an unknown character and recognizes the character based on a pre-trained recognition model. Prior to recognizing the character, the character recognition system may pre-process the character to rotate the character to a normalized orientation. By rotating the character to a normalized orientation in both training and recognition stages, the character recognition system releases the pre-trained recognition model from considering character prototypes in different orientations and thereby speeds up recognition of the unknown character. In one example, the character recognition system rotates the character to the normalized orientation by aligning a line between a sum of coordinates of starting points and a sum of coordinates of ending points of each stroke of the character with a normalized direction. 1. A system comprising:one or more processors;memory, communicatively coupled to the one or more processors, storing executable instructions that, when executed by the one or more processors, configure the one or more processors to perform acts comprising:receiving a plurality of handwritten textual characters;rotating each handwritten textual character to a predetermined orientation based on information of a starting point and an ending point of each stroke of each handwritten textual character;extracting features from the plurality of rotated, handwritten textual characters;training a character recognition model based on optimizing a sample-separation-margin (SSM) based minimum classification error (MCE) objective function using a resilient propagation (Rprop) algorithm;compressing parameters of the character recognition model using a split vector quantization (SVQ) technique; andconstructing a two-level fast-match tree for recognition of an unknown textual character at run time.2. One or more computer-readable media storing executable instructions that , when executed by one or more processors , configure the one or more ...

Подробнее
03-10-2013 дата публикации

Mobile device configured to travel on a transmission line and provide assistance

Номер: US20130256613A1
Принадлежит: ELWHA LLC

Described embodiments include a system and an apparatus. A described system includes a mobile device configured to travel on a transmission line between two transmission towers of a power transmission system, physically assist installation of a new conductor cable or line between the two transmission towers, and wirelessly communicate with an installation controller. The system includes the installation controller configured to control travel by the mobile device over the transmission line, to control provision of physical assistance by the mobile device, and to wirelessly communicate with the mobile device.

Подробнее
03-10-2013 дата публикации

Image processing device determining binarizing threshold value

Номер: US20130257892A1
Автор: Masaki Kondo, Ryohei OZAWA
Принадлежит: Brother Industries Ltd

An image processing device comprising: a processor to perform: acquiring target image data representing a target image including a letter; and generating binary image data representing the letter in the target image by using the target image data, the generating of the binary image data comprising: identifying a background color value representing color of background of the target image; identifying a letter color value representing color of the letter in the target image; determining a characteristic value concerning a sharpness of the letter in the target image; determining a binarizing threshold value by using the background color value, the letter color value, and the characteristic value; and performing a binarizing process on the target image data by using the binarizing threshold value to generate the binary image data.

Подробнее
03-10-2013 дата публикации

Systems and Methods for Semantically Classifying and Extracting Shots in Video

Номер: US20130259375A1
Принадлежит: Individual

The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.

Подробнее
03-10-2013 дата публикации

Systems and methods for landmark detection

Номер: US20130259387A1
Принадлежит: Otter Creek Holdings LLC

A computer-implemented method for detecting a landmark. An image is received. A feature in the received image is detected. The detected feature is compared to a plurality of images of landmarks stored in a database. Upon determining the detected feature matches an image of a landmark, information associated with the landmark is retrieved from the database. The retrieved information is displayed on a computing device.

Подробнее
03-10-2013 дата публикации

METHOD FOR CLASSIFYING BIOMETRIC DATA

Номер: US20130262356A1
Принадлежит:

Methods, systems, and computer program products for biometric authentication and more particularly to a method for classifying biometric data consisting in constructing, on the basis of a first universal statistical model and based on a set of first individual collections of biometric data, a second statistical model comprising a plurality of statistical sub-models and taking into consideration the biometric specificities of an individual or class of individuals, such that the first and second statistical models jointly define a highly discriminatory universal statistical model. 11. A method for classifying biometric data () belonging to a first continuous and limited area of representation corresponding to at least one determined type biometric sensor , comprising:a step of acquiring by said at least one sensor of determined type biometric data in the form of a set of multidimensional vectors of parameters,{'b': 1', '2, 'a step of defining a second area of representation wherein each biometric data () is represented by a first distribution () such that the biometric data are represented thereto by a first set of first distributions, the first distributions responding to a same probability distribution function of at least one first parameter, such that the first set of first distributions is defined by a first set of first parameters determined based on biometric data,'}{'b': 3', '11, 'a first step of constructing a first statistical model () in automatic classification of a universal collection () of biometric data in the second area of representation,'}{'b': 31', '11, 'the first statistical model being defined by at least one second finite set of second distributions (), the second distributions responding to a same probability distribution function of at least one second parameter and being distributed in the second area of representation according to at least one second set of second parameters, such that each second distribution defines a sub-space of the ...

Подробнее