Abstract: The present invention concerns a method, a system, a device of authenticating a user using a body part including biometric information. The method comprises stitching partial enrolment images comprising different views of the user's body part into at least one mosaic and thereby creating an enrolled image, acquiring an authentication image of the body part, wherein the size of the authentication image is a fraction of the enrolled image, determining at least one area of interest in the enrolled image, and matching the authentication image with image data of the determined area of interest in the enrolled image.

Abstract: The present invention concerns a method, a system, a device for enrolling biometric data of a body part to be used for user authentication, using a two-dimensional sensor. The method comprises capturing, using the two-dimensional sensor, images representing different views of the body part, stitching the images into at least one mosaic, generating at least one constructed image by determining at least one area of interest in the mosaic, the area of interest representing an additional view of the body part, and extracting image data of the area of interest, and enrolling the constructed images in a set of templates to be used for user authentication.

Abstract: In one aspect, a fingerprint sensor device for fingerprint detection includes a light source configured to emit light at a wavelength. The fingerprint sensor device includes an array of sensor pixels to acquire an optical image indicative of a fingerprint. Each sensor pixel includes a photodetector to detect the emitted light reflected off of a target finger and output an optical signal based on the detected reflected light. Each sensor pixel includes a collimator disposed over the photodetector to direct the reflected light in a substantially vertical direction from above the photodetector toward the photodetector. Each sensor pixel includes sensor signal detection circuitry communicatively coupled to the photodetector to acquire the outputted optical signal.

Abstract: According to an embodiment of the present invention, a display apparatus capable of image scanning and a method for driving the same are provided. According to an embodiment of the present invention, a display apparatus capable of image scanning is provided including a contact sensor arranged in each unit pixel.

Abstract: A fire detector is disclosed that successively images a particular area from geosynchronous Earth orbit satellite to attain very good signal-to-noise ratios against Poisson fluctuations within one second. Differences between such images allow for the automatic detection of small fires greater than 12 square meters. Imaging typically takes place in transparent bands of the infrared spectrum, thereby rendering smoke from the fire and light clouds somewhat transparent. Several algorithms are disclosed that can help reduce false fire alarms, and their efficiencies are shown. Early fire detection and response would be of great value in the United States and other nations, as wild land fires destroy property and lives and contribute around five percent of the US global carbon dioxide contribution. Such apparatus would incorporate modern imaging detectors, software, and algorithms able to detect heat from early and small fires, and yield detection times on a scale of minutes.

Abstract: A method and a system for rectifying a distorted fingerprint are provided. The method includes following steps. A feature of a distorted fingerprint is extracted, a reference distorted fingerprint whose feature is matched with the feature of the distorted fingerprint is searched for in a reference distorted fingerprint database, a dense distortion field of the reference distorted fingerprint is obtained in the reference distorted fingerprint database and the distorted fingerprint is rectified to a normal one according to the dense distortion field of the reference distorted fingerprint.

Abstract: Disclosed is an object dangerousness recognition method comprising steps of generating, based on an image captured by a stereo camera, a heterogeneous point cloud of an object in the image, each point in the heterogeneous point cloud having depth information and planar image information; determining, based on the depth information and the planar image information of each point in the heterogeneous point cloud, a solid shape of the object, and then, generating a first dangerousness parameter according to the solid shape; determining, based on the depth information and the planar image information of each point in the heterogeneous point cloud, a surface feature of the object, and then, generating a second dangerousness parameter according to the surface feature; and generating, based on the first and second dangerousness parameters, a comprehensive dangerousness parameter of the object.

Abstract: A face recognition method is provided. The method includes dividing an input video into different sets of frames and detecting faces of each frame in the input video. The method also includes generating face tracks for the whole video. Further, the method includes applying a robust collaborative representation-based classifier to recover a clean image from complex occlusions and corruptions for a face test sample and perform classification. In addition, the method also includes outputting the video containing the recognized face images.

Abstract: Computer-readable storage media, computing devices and methods are discussed herein. In embodiments, a computing device may be configured to perform facial recognition based on gradient based feature extractions of images of faces. In embodiments, the computing device may be configured to determine directional matching patterns of the images from the gradient based feature extraction and may utilize these directional matching patterns in performing a facial recognition analysis of the images of faces. Other embodiments may be described and/or claimed.

Abstract: Identifying and obscuring faces of specific individuals in an image may be provided. A request for an image for display on a computer display device may be received from a viewing user. One or more individuals represented in the image may be automatically determined using an image processing technique. A target individual may be identified from the one or more individuals whose facial image is to be obscured when displaying the image based an access control level associated with the viewing user and one or more criteria associated with the target individual. Responsive to the identifying, a customized image may be generated by obscuring a region having the facial image of the target individual from the image. The customized image may be transmitted for display.

Abstract: Systems and methods for performing face recognition and image searching are provided. A system for face recognition and image searching includes an ingestion system, a search system, a user device, and a database of galley files that include feature vectors. The ingestion system crawls the internet starting with a seed URL to scrape image files and generate feature vectors. Feature vectors of images input by a user may be compared by the search system to feature vectors in the gallery files. A method for generating feature vectors includes landmark detection, component aligning, texture mapping, vector computation, comparing cluster centers defined by vectors stored in a database with vectors generated based on an input image, linear discriminant analysis, and principal component analysis.

Abstract: Confidential content within a file is masked for display on a flexible display device. A legend relating the masking to the confidential content is displayed in a hidden area created by bending the flexible display device. The flexible display device monitors secondary users and their gaze towards the flexible display device and the hidden area to determine if unauthorized secondary users can see the display and hidden area of the flexible display device.

Abstract: Improved facial recognition tracking of individuals throughout a space is provided, as is identification of unexpected behavior. The system can configure itself upon setup and adjust to changing conditions, and is able to intelligently reduce the workload on the facial recognition system. Cameras are placed throughout a building and learn what typical traffic within the building looks like. Over time, the system can track multiple users throughout the system and can automatically learn the average time between cameras. A probability function for each camera can also be determined that give probabilities for each camera to camera path. This approach provides for both limiting the bandwidth and processing power required for facial recognition and also allows for behavioral analysis. This system could be implemented as a distributed system of cameras, each performing its own facial recognition and tracking, and/or with distributed cameras combined with central processing for facial recognition.

Abstract: In one embodiment, a mobile device automatically captures image frames by acquiring a real-time video sequence, selecting one or more frames from the real-time video sequence based on social network information and identity recognition, and storing the selected one or more frames in a local storage of the mobile device.

Abstract: An image processing device combines an image of a medium exposed to visible light and an image of the medium exposed to ultraviolet light so that parts printed with UV ink can be easily identified. A control device (image processing device) has an image acquisition unit that drives an image sensor -and acquires a first image by imaging the face a check when exposed to a visible first light, and acquires a second image by imaging the face of the check when exposed to an ultraviolet second light; a reverse image generating unit that generates a reversed second image by reversing light and dark in the second image; and a second synthesizing unit that generates a second synthesized image by combining the first image and the reversed second image. Because the reversed second image that is the reverse of the second image becomes an image that is light overall, a drop in the luminance and a drop in the contrast of the first synthesized image can be suppressed, and parts printed with UV ink are easily discerned.

Abstract: A control method for a vehicle includes: predicting a position of an eye point of an occupant after a state of a vehicle seat is changed based on amount of adjustment of an adjusting mechanism due to change in state of the vehicle seat; determining whether or not the predicted position of the eye point is located within a measurement range of a camera member installed to a steering member; and if it is determined that the predicted position of the eye point is not located within the measurement range of the camera member, moving the measurement range of the camera member toward the predicted position of the eye point synchronously with the steering member.

Abstract: A method and system for detecting patterns of eye movements in a series of captured images may include capturing a series of images of at least one eye of a viewer by a camera, where the series of images may comprise at least two images, calculating, by a processor, a vector of a movement of the at least one eye between the at least two images, where the vector may include a distance of the movement, a direction of the movement and a time between capturing of the images, comparing the vector to at least one characteristic of a plurality of known patterns of eye movements, and classifying the movement of the eye(s) as one of a plurality of known pattern of eye movements.

Abstract: A server for campaign optimization is described. The server generates analytics data from users interactions with a first virtual object displayed on a plurality of devices and user interactions with a first set of user interactive features of the first virtual object from a first content dataset. The server generates and provides a second content dataset to a device based on the analytics data. The second content dataset. The device recognizes an identifier from the second content dataset and displays, in the device, the second virtual object and the second set of user interactive features of the second virtual object in response to identifying the identifier.

Abstract: Systems and methods are disclosed to track targets in a video by capturing a video sequence, detecting data association between detections and targets, where detections are generated using one or more image based detectors (tracking-by-detections); identifying one or more target of interests and estimating a motion of each individual; and applying an Aggregated Local Flow Descriptor to accurately measure an affinity between a pair of detections and a Near Online Multi-target Tracking to perform multiple target tracking given a video sequence.

Abstract: Methods and apparatus to measure brand exposure in media streams are disclosed. An example apparatus disclosed herein includes a brand identifier detector to compare first data associated with a first scene of a media stream with second data associated with a reference scene including a first brand identifier to detect the first brand identifier in the first scene of the media stream. The example apparatus also includes a measure and tracking module to combine respective locations of the first brand identifier in respective frames of a first sequence of image frames forming the first scene to determine a weighted location for the first brand identifier. The example apparatus further includes a report generator to report appearance data corresponding to the first brand identifier, the appearance data including the weighted location for the first brand identifier.

Abstract: Methods, systems, and computer program products for parsing objects are provided herein. A method includes producing a plurality of versions of an image of an object derived from an input, wherein each version comprises one of one multiple resolutions of said image of said object; computing an appearance probability at each of a plurality of regions on the one or more lowest resolution versions of said plurality of versions of said image for at least one attribute for said object; determining a configuration of the at least one attribute in the one or more lowest resolution versions based on at least the appearance probability in each of the plurality of regions; and outputting said configuration.

Abstract: A video processing apparatus includes a video analyzer that analyzes video data captured by a surveillance camera, detects an event belonging to a specific category, and outputs a detection result, a display controller that displays, together with a video of the video data, a category setting screen for setting a category of an event included in the video, and a learning data accumulator that accumulates, as learning data together with the video data, category information set in accordance with an operation by an operator to the category setting screen. The video analyzer performs learning processing by using the learning data accumulated in the learning data accumulator.

Abstract: For remote heart rate estimation, a method detects an object of interest (OOI) in each image of a video data and tracks the OOI in each image of the video data. The method identifies a region of interest (ROI) within the OOI and generates a plurality of super pixels from a plurality of pixels in each ROI. The method further generates a super-pixel time series from the plurality of super pixels in each image and removes interfering signals from the super-pixel time series. The method further models the super-pixel time series as a super-pixel model and calculates a heart beat signal from the super-pixel model. The method calculates heart characteristics from the heart beat signal. The heart characteristics include one or more of a heart rate, an inter-beat interval, and a heart rate variability.

Abstract: Methods and apparatus provide for a Cart Inspector to create a suspicion level for a transaction when a video image of the transaction portrays an item(s) left in a shopping cart. Specifically, the Cart Inspector obtains video data associated with a time(s) of interest. The video data originates from a video camera that monitors a transaction area. The Cart Inspector analyzes the video data with respect to target image(s) associated with a transaction in the transaction area during the time(s) of interest. The Cart Inspector creates an indication of a suspicion level for the transaction based on analysis of the target image(s). Creation of a high suspicion level for the transaction indicates that the transaction's corresponding video images most likely portray occurrences where the purchase price of an item transported through the transaction area was not included in the total amount paid by the customer.

Abstract: Disclosed are an apparatus and a method for detecting an object for a vehicle, the apparatus including: a camera unit configured to output a surrounding image of a vehicle; an object candidate extracting unit configured to extract an object candidate from the output surrounding image of the vehicle; a height reference filtering unit configured to output a filtered image by excluding an object having a height equal to or smaller than a threshold value from the extracted object candidate; and an object recognizing unit configured to detect a specific object from the output filtered image.

Abstract: This specification describes technologies relating to biometric authentication based on images of the eye. In general, one aspect of the subject matter described in this specification can be embodied in methods that include obtaining images of a subject including a view of an eye. The methods may further include determining a behavioral metric based on detected movement of the eye as the eye appears in a plurality of the images, determining a spatial metric based on a distance from a sensor to a landmark that appears in a plurality of the images each having a different respective focus distance, and determining a reflectance metric based on detected changes in surface glare or specular reflection patterns on a surface of the eye.

Abstract: A finger guide device that positions a finger (or minutiae containing digit) of a human subject on a fingerprint sensor in a manner optimal for the data capture operation of authentication of identification of said subject, wherein a relevant portion of the finger is in alignment with a sensor or scanner. The finger guide device may also be used for enrollment of the initial fingerprint data into the system. The device may contain an outer surface ridge which feels somewhat uncomfortable due to application of a high pressure per square inch on small areas of the finger when the finger is incorrectly positioned to encourage correct placement of the finger.

Abstract: A finger guide device that positions a finger (or minutiae containing digit) of a human subject on a fingerprint sensor in a manner optimal for the data capture operation of authentication of identification of said subject, wherein a relevant portion of the finger is in alignment with a sensor or scanner. The finger guide device may also be used for enrollment of the initial fingerprint data into the system. The device may contain an outer surface ridge which feels somewhat uncomfortable due to application of a high pressure per square inch on small areas of the finger when the finger is incorrectly positioned to encourage correct placement of the finger.

Abstract: An approach is provided to generate forms with template inclusions. In the approach, optical character recognition (OCR) text is compared to corresponding text in a selected form. Characters of text in the OCR text are then replaced with text from the template text, the replacing results in a form with template inclusions. The form with template inclusions is then processed by a forms processing operation.

Abstract: A method for information recognition using an Optical Character Recognition (OCR) program includes acquiring an image of an object to be recognized, analyzing a layout of the contents of the image and extracting character area blocks in the image, determining character lines in the character area blocks, and recognizing, by the OCR program, character information of the key character lines in the character area blocks.

Abstract: Extracting card data comprises receiving, by one or more computing devices, a digital image of a card; perform an image recognition process on the digital representation of the card; identifying an image in the digital representation of the card; comparing the identified image to an image database comprising a plurality of images and determining that the identified image matches a stored image in the image database; determining a card type associated with the stored image and associating the card type with the card based on the determination that the identified image matches the stored image; and performing a particular optical character recognition algorithm on the digital representation of the card, the particular optical character recognition algorithm being based on the determined card type. Another example uses an issuer identification number to improve data extraction. Another example compares extracted data with user data to improve accuracy.

Abstract: An article for use as a negotiable instrument includes a substrate having a front side and reverse side; first machine-printed information on the substrate's front side including an account number associated with the negotiable instrument, and a unique identifier associated with the negotiable instrument, the first machine-printed information uniquely identifying the negotiable instrument; and second machine-printed information on the substrate's reverse side that corresponds to the first machine-printed information such that comparison of respective images of the substrate's front and reverse sides indicates that the images correspond to the same negotiable instrument.

Abstract: An image recognition device includes an edge direction evaluation unit configured to evaluate a direction of an edge at each coordinate by assigning points to the coordinate when a deviation amount between a direction of an outline of an abundance ratio higher than a predetermined abundance ratio threshold value among directions of an outline of a character available for the vehicle number plate and the direction of the edge at each coordinate of the image is less than a predetermined deviation amount threshold value and a vehicle number plate region extraction unit configured to extract a region of the vehicle number plate from the image based on a distribution of the points assigned by the edge direction evaluation unit.

Abstract: The invention provides a portable apparatus for reading a license plate, sensing speed and recognizing a face, which comprises a camera placed on the front right and front left and both sides of the system which enables the system to capture images and recognize faces, LED lighting located around the cameras which are directed towards a visual direction and which enable capturing of legible images even at night time, police lights placed at the front and rear faces of the base which can flash on and off when necessary, an alarm control device, Ethernet connection forming the network, cooling device which eliminates the heat formed inside the apparatus, a control card which operates the police lights, modem which continuously provide wireless communication and a top cover which encloses the entire system.

Abstract: A method and apparatus for processing an image are provided. A processor is configured to detect a region of at least one object from the image, define a plurality of straight lines approximating a boundary of the detected region of the at least one object, and based on the number of points at which each of the plurality of first straight lines coincide with the boundary, extract first image data for a polygonal region. The polygonal region has vertexes at a plurality of first intersection points at which the plurality of straight lines intersect each other. Second image data may be generated by correcting distortion of the first image data. A storage unit stores the second image data, which may also be displayed or transmitted.

Abstract: A system for calculating a visibility range from a vehicle is disclosed. The system comprises a high dynamic range image sensor system comprising a pixel array including a plurality of pixels. The image sensor further includes readout circuitry in electrical communication with each pixel of the pixel array. The readout circuitry is operable to readout a distinct pixel value corresponding to one of a plurality of exposure times for each pixel in a single image frame. The system further comprises at least one processor in communication with the readout circuitry. The processor is operable to calculate a visibility range from the vehicle based on a plurality of image processing algorithms.

Abstract: A method for providing an image of a subject is provided. The plurality of Cartesian points is divided into a first group and a second group, wherein all of the Cartesian points in the first group have a kr that is less than or equal to kr of all of the Cartesian points in the second group. The second group is divided into N subgroups. An inversion recovery radio frequency is applied to the subject. K-space data for the first group of Cartesian points for M different time periods is acquired, wherein k-space data is acquired for only one sub-group sequentially and cyclically for the M different time periods. For each time period i of the M different time periods, acquired k-space data for the first group of Cartesian points at time period i and k-space data from N consecutive subgroups of Cartesian points.

Abstract: A multidimensional histogram is used to characterize an image (or object), and is used to identify candidate matches with one or more reference images (or objects). An exemplary implementation employs hue information for two of the dimensions, and a second derivative function based on luminance for a third dimension. The simplicity and speed of the detailed arrangements make them well suited for use with cell phones and other mobile devices, which can use the technology for image/object recognition, e.g., in visual search applications.

Abstract: A method for capturing hyperspectral images using a regular color camera. In the method, the camera takes multiple images of a scene, with the camera oriented differently for each image. For a camera carried by an aircraft or spacecraft, this allows hyperspectral imaging without the cost or weight of a hyperspectral camera.

Abstract: At least some embodiments of the present disclosure feature systems and methods for assessing the impact of visual features within a region of a scene. With the input of a visual representation of a scene and at least one selected region within the scene, the system applies a visual attention model to the visual representation to determine visual conspicuity of the at least one selected region. The system computes feature-related data associated with a plurality of features of the at least one selected region. Based on the visual conspicuity and the feature-related data, the system assesses an impact that at least one of the features within the at least one selected region have on the visual conspicuity.

Abstract: Techniques are disclosed for image feature representation. The techniques exhibit discriminative power that can be used in any number of classification tasks, and are particularly effective with respect to fine-grained image classification tasks. In an embodiment, a given image to be classified is divided into image patches. A vector is generated for each image patch. Each image patch vector is compared to the Gaussian mixture components (each mixture component is also a vector) of a Gaussian Mixture Model (GMM). Each such comparison generates a similarity score for each image patch vector. For each Gaussian mixture component, the image patch vectors associated with a similarity score that is too low are eliminated. The selectively pooled vectors from all the Gaussian mixture components are then concatenated to form the final image feature vector, which can be provided to a classifier so the given input image can be properly categorized.

Abstract: Undated photos are organized by estimating the date of each photo. The date is estimated by building a model based on a set of reference photos having established dates, and comparing image characteristics of the undated photo to the image characteristics of the reference photos. The photo characteristics can include hues, saturation, intensity, contrast, sharpness and graininess as represented by image pixel data. Once the date of a photo is estimated, it can be tagged with identifying information, such as by using the estimated date to associate the photo with a node in a family tree.

Abstract: A computing device classifies user activities. The device receives eye tracking data for a person viewing a page having multiple contiguous regions. The eye tracking data comprises a temporal sequence of fixations, where each fixation has a duration and a location. The device partitions the fixations into clusters, where each cluster has a consecutive sub-sequence of the fixations. The device assigns a provisional user activity label to each fixation based on a set of characteristics of the fixation. The device also groups together consecutive fixations that have the same label to partition the fixations into groups. For each group that matches a respective cluster, the device retains the provisional label assignment as a final user activity label assigned to each of the fixations in the respective group. The device also reconciles non-matching groups with non-matching clusters, using the regions, to form a set of non-overlapping modified groups.

Abstract: A computer-implemented method of generating a spatio-temporal pattern model for spatio-temporal pattern recognition includes receiving one or more training trajectories. Each of the training trajectories includes diverse data points that represent a spatio-temporal pattern. The received training trajectories define an area that is partitioned into one or more observed clusters, and a non-observed complementary cluster. The spatio-temporal pattern model is generated so as to include both of the observed clusters and the non-observed complementary cluster.

Abstract: The ability to identify anomalous behavior in video recordings is important for security and public safety. Current identification techniques, however, suffer from a number of limitations. The present invention describes a novel identification technique that permits unsupervised, automatic identification of moving objects and anomaly detection in real-time recordings (MovA). The present invention specifically utilizes a novel real-time manifold learning system (RML), which generates a semantic crowd behavior descriptor that the inventors call a Trackogram. The Trackogram can be used to identify anomalous crowd behavior collected from video recordings in a real-time manner. MovA can be used to detect anomaly in standard video datasets. Importantly, MovA is also able to identify anomalies in night-vision stereo sequences. Ultimately, MovA could be incorporated into a number of existing products, including video monitoring cameras or night-vision goggles.

Abstract: To provide a training data generating device capable of easily generating a large amount of training data used for machine-learning a dictionary of a discriminator for recognizing a crowd state. A person state determination unit 72 determines a person state of a crowd according to a people state control designation as designation information on a person state of people and an individual person state control designation as designation information on a state of an individual person in the people. A crowd state image synthesis unit 73 generates a crowd state image as an image in which a person image corresponding to the person state determined by the person state determination unit 72 is synthesized with an image at a predetermined size acquired by a background extraction unit 71, and specifies a training label for the crowd state image.

Abstract: An image forming apparatus includes a printing unit printing, on a printed matter on which a first color patch for color adjustment is printed, an image based on digital print data including a second color patch, and a measurement unit measuring the first and second color patches. An information processing apparatus adjusts color information for printing the image, based on a result of measurement of the first and second color patches measured by the measurement unit, and instructs the image forming apparatus to print the image based on the adjusted color information.

Abstract: If an ink color decomposition table with a maximum ink amount, which is different from a created color decomposition table, is automatically generated using the created color decomposition table, and used for, for example, inkjet printing, the ink use amount may be excessive, leading to unevenness in glossiness. According to an embodiment of this invention, for example, in a case where an ink limit amount at each grid point of a color decomposition lookup table to be used for image processing is held, and the color decomposition lookup table is automatically generated, the ink amount of each grid point is controlled to be equal to or smaller than the limit amount.

Abstract: A Bluetooth low energy (BLE)-based asset tag transmits a code that identifies an asset. A device is attached to the asset. The code is scanned with a scanner supported by the device. An advertising beacon is transmitted in an advertising packet having a payload with a Bluetooth low energy (BLE)-based radio supported by the device. The scanned code is automatically loaded into the payload. The advertising packet with the scanned code in the payload is periodically transmitted as a series of beacon pulses.

Abstract: Novel TCDA/ZnO compositions in which the ZnO particles have an average particle size less than 100 nm are disclosed. Reversible thermochromatic sensors employing the TCDA nanocomposites and methods of printing TCDA/ZnO nanocomposite thin films forming the reversible thermochromatic sensors using inkjet printing techniques are also disclosed.