Abstract: Document data corresponding to each page included in a document is stored, and furthermore, feature data indicative of a feature of the document data and a document index indicating the document are associated with the document data. A document extracting apparatus obtains input document data, calculates feature data from the input document data, judges similarity between the input document data and the document data based on the feature data, obtains a document index associated with document data similar to the input document data, and extracts a plurality of pieces of document data associated with the document index. Thus, document data concerning the document including a page corresponding to the document data similar to the input document data is extracted for a plurality of pages.

Abstract: A method is disclosed for performing stereoscopic imaging. The method may involve obtaining a first image of a scene, at a first time, using a camera disposed on a platform, where the distance between the camera and the scene is changing. The camera may be used to obtain a second image of the scene, at a second time, with one of the first and second images being larger than the other. One of the images that is larger than the other may be resized so that the sizes of the two images are substantially similar. Both of the images may be rotated a predetermined degree so that the images form a stereo pair that may be viewed with a stereoscope viewing component or made into an anaglyph for viewing with an anaglyph viewing component.

Abstract: A system for identification and/or authentication of a user in a travel terminal, the system comprising: a multiuser interactive screen having one or more interaction zones, with which a user can interact; an image generation system for generating information on the interaction zone to provide information to the user with which the user can interact and; an image capture system which generates a captured image of any item in contact with the interaction zone; a recognition system for recognizing one or more features from the captured image to enable identification and/or authentication of the user; a communication system for communicating with the user by means of the image generation means to confirm identification or request additional information.

Abstract: A computer-implemented method for for matching objects is disclosed. At least two images where one of the at least two images has a first target object and a second of the at least two images has a second target object are received. At least one first patch from the first target object and at least one second patch from the second target object are extracted. A distance-based part encoding between each of the at least one first patch and the at least one second patch based upon a corresponding codebook of image parts including at least one of part type and pose is constructed. A viewpoint of one of the at least one first patch is warped to a viewpoint of the at least one second patch. A parts level similarity measure based on the view-invariant distance measure for each of the at least one first patch and the at least one second patch is applied to determine whether the first target object and the second target object are the same or different objects.

Abstract: An information processing apparatus includes a projector, a camera, a first storage, and a controller. The projector projects a projection image containing a first operation image onto a predetermined area. The camera shoots an image of a subject within the predetermined area. The controller detects an operation to the first operation image based on the shot image shot by the camera and controls the first storage to store at least the image of the subject out of the shot image when the operation is detected.

Abstract: A camera adjusting system includes a first camera, a second camera, and a control apparatus. The first camera is movably arranged on a sliding rail to monitor a locale. The second camera captures a three dimensional (3D) image of a head of a subject. The control apparatus receives the captured 3D image of the head of the subject and simulates a corresponding 3D model according to the captured 3D image, and compares the actual 3D model with a reference 3D model, to compute a compared result, and outputs a control signal to the first camera to adjust parameters of the first camera according to the compared result.

Abstract: A computer-implemented method, system, and program includes a behavior processing system for capturing a three-dimensional movement of a monitored user within a particular environment monitored by a supervising user, wherein the three-dimensional movement is determined by using at least one image capture device aimed at the monitored user. The behavior processing system identifies a three-dimensional object properties stream using the captured movement. The behavior processing system identifies a particular defined adverse behavior of the monitored user represented by the three-dimensional object properties stream by comparing the identified three-dimensional object properties stream with multiple adverse behavior definitions.

Abstract: According to an aspect of the present invention, it is possible to visually show both of information which is originally visually recognizable and information which is originally not seen that have been provided from equipment on the same image, so that it is possible to grasp the content of information and the source of providing the information corresponding to or in association with each other. Furthermore, it is possible to view information difficult to visually recognize together with visually recognizable information, and it is possible to clearly grasp, in addition to information which can be visually obtained at the place where a user currently stays, information related to the visually obtained information, from an image visually indicating the association.

Abstract: An exemplary automatic analyzing method for test strips includes steps of: providing a test strip unit having a reacting region and an image calibration region; capturing an image of the test strip unit including an image of the reacting region and an image of the image calibration region; analyzing the image of the test strip unit to generate a first image signal of the image calibration region and a second image signal of the reacting region; comparing the first image signal with a standard signal to generate an image signal calibration parameter; calibrating the second image signal by applying the image signal calibration parameter to generate a third image signal; and comparing the third image signal with data in a database to generate a corresponding parameter value. An automatic analyzing system for test strips is also provided.

Abstract: A video and data capturing system and method includes a mobile unit having an image sensor and motion sensing equipment connected to a microprocessor. The mobile unit is installed in an object for detecting visual images and motion data associated with the object. The mobile unit communicates with a base unit capable of analyzing the image and motion data and correcting the image data so it is level with the horizon. A foot unit may be used in conjunction with the mobile unit for detection of an athlete's foot acceleration for determining when the athlete's foot comes in contact with the ground. A field unit may be used in conjunction with the mobile unit and foot unit to determine the location of the foot unit on a playing surface to assist in determining whether an athlete is in or out of bounds, or their location on the playing surface.

Abstract: A system for multimodal laser speckle imaging may include a first light source positioned to emit laser light toward a target, a second light source positioned to emit light toward the target, a camera positioned to receive light scattered from the target, and a processor.

Abstract: The present invention makes a privacy protection area set on a video frame always match a masking block for the privacy protection area, thereby preventing video images taken from the privacy protection area from being exposed. One embodiment of the invention sets a masking zone corresponding to a privacy protection area on a taken video frame, keeps examining if the set masking zone does not match the privacy protection area, and adjusts the position of the masking zone on the video frame if it is determined that the masking zone does not match the privacy protection area, thereby preventing video signals taken from the initially set privacy protection area from being outputted.

Abstract: A subject is connected to a monitoring system and videoed while being monitored. The monitoring system receives raw data from the subject and processes the raw data into waveform data, and transmits the waveform data to a marking device. The marking device simultaneously marks the waveform data with a waveform reference point and causes a light emitting diode to flash in the video, thereby creating a video reference point. A computer program locks the waveform reference point with the video reference point and thereby synchronizes the waveform data with the video.

Abstract: A system, method, and apparatus for monitoring performance of a content processing device are disclosed. A system may include a content processing device and a customer premises management system (CMS) in communication with the content processing device. The CMS generally monitors hardware performance, network performance, and video quality parameters of the content processing device. The CMS may determine an operating status of the content processing device from at least one of the hardware performance,network performance, and video quality parameters.

Abstract: An ROI setting apparatus including an ROI recognition unit and an ROI control unit is provided. In one embodiment, the ROI recognition unit contains multiple ROI recognition modules for recognizing an ROI of image data according to various methods to obtain a recognition result. The ROI control unit selects one ROI recognition module out of the ROI recognition modules and sets ROI information based on the recognition result. The ROI recognition module may be selected according to an instruction from a user input via an operation unit, or a scene type selected by a scene selection switch of an image capture unit. The ROI control unit may perform operations such as selecting, enlarging, or reducing the ROI recognized by the ROI recognition module, or changing the ROI recognition conditions according to the respective instructions from the user input via the operation unit.

Abstract: The present invention advantageously provides a means by which the privacy zone on a PTZ camera can be maintained so that an object in the camera's sight is always masked or covered. An algorithm which remembers the defined privacy zones as an area in space marked by four rays touching the four corners of the marked zone and having absolute Pan, Tilt angular coordinates is presented. The privacy zone is initially defined by a rectangle on the screen with known pixel co-ordinates which are translated into angular coordinates. Then, when the camera moves and prepares to display a new screen, the privacy zone is superimposed on the object to be masked. Locating the object and displaying its privacy zone is done by translating the absolute angular coordinates of the original privacy zone into pixel coordinates. Additionally, multiple privacy zones can be displayed on one camera screen.

Abstract: A driving method used for a solid-state imaging device according to the present invention includes: imaging an object for a first storage time when a shutter is open, in a first state that is a state where either at least a part of the peripheral circuitry is suspended or a consumption current of the peripheral circuitry is limited; imaging, in the first state, a dark output signal image including only a dark output for a second storage time when the shutter is closed; converting the dark output signal image to correspond to the image obtained for the first storage time and subtracting, from the signal image of the object, the converted dark output signal image or converting the dark output signal image to correspond to the image obtained for the second storage time and subtracting, from the signal image of the object, the converted dark output signal image.

Abstract: An imaging preventing apparatus includes imaging means for obtaining an imaged image signal by performing imaging processing, image analyzing means for performing image analyzing processing on the imaged image signal obtained by the imaging means, imaging preventing operation performing means for performing a preventing operation against imaging by a different camera system, and control means for determining the possibility of being imaged by a different camera system based on the analysis result information by the image analyzing means and, if it is determined that there is a possibility of being imaged, causing the imaging preventing operation performing means to perform the preventing operation.

Abstract: The invention relates to a method and system for the acquisition and correlation matching of points belonging to a stereoscopic pair of images, whereby the pair is formed by a first image and a second image representing a scene. According to the invention, the two images of the pair are acquired with a single acquisition instrument (30) comprising two sensors CCD (31, 32) in the optical focal plane. The matching of the acquired stereoscopic pair consists in determining, by means of correlation, the point in the second image that is homologous to a point in the first image. Said correlation is performed for a point from the first image using an optimally-sized correlation window. When the homologous point of a point from the first image has been determined, the position deviation between the point from the first image and the homologous point thereof is entered in a table. Once all of the homologous points of the points from the first image have been found, the results table is reset barycentrically.

Abstract: Systems and methods are disclosed for implementing and managing distributed video surveillance systems. Systems and methods in accordance with the present invention provide a well-organized structure for describing and implementing distributed video surveillance systems and service protocols for managing the surveillance activities of clusters of video surveillance cameras. In particular, the service protocols provide a high degree of control over the surveillance activities of video surveillance cameras. In addition, the service protocols also provide a great deal of flexibility in selecting and managing a wide range of analytical and managerial tools for available for analyzing and organizing video track information.

Abstract: An image enhancer that includes a laser for emitting an optical signal toward an object in a turbid medium, a modulator for modulating laser intensity of the optical signal, an RF source for driving the modulator and for providing a reference signal, an optical detector for detecting the modulated optical signal that is reflected from the object, the optical detector converting the reflected optical signal into an electrical signal, the electrical signal having RF and DC components, an I/Q demodulator for mixing the RF component of the electrical signal with the reference signal and producing in-phase and quadrature phase signal components that can be digitized and processed such that both contrast and range images of the object are produced.

Abstract: To provide a vehicle monitor apparatus capable of acquiring more information through effective utilization of an image taking region of a camera on the occasion of taking interior and exterior images of a vehicle with the camera. A vehicle monitor apparatus 1 is provided with a drive recorder 11 and a reflecting mirror 12. The drive recorder 11 is provided with a camera 14 and the camera 14 is arranged to take a forward image of the vehicle 2. In an image taking region of the camera 14, the reflecting mirror 12 is located in a range where a hood 23 should be imaged if the reflecting mirror 12 were excluded, and the camera 14 takes an image of an exterior situation outside the vehicle viewed through a windshield 22, and an image projected by the reflecting mirror 12.

Abstract: According to the image reproducing device, the image reproducing method, the image reproducing program and the image capturing device of the present invention, if a face image is not detected in an image, a main object can be zoomed by detecting the center part of the image or a focused object. If a plurality of face images are detected from an image, the detected face images can be zoomed in order by simple operation.

Abstract: Sensors around the periphery of the remote control unit detect contact with the user's hand. A trained model-based pattern classification system analyzes the periphery sensor data and makes a probabilistic prediction of the user's hand size. The hand size is then used to control a mapping system that defines how gestures by the user's thumb upon a touchpad of the remote control unit are mapped to the control region upon a separate display screen.

Abstract: An imaging module for biometrics authentication comprises: a light source irradiating a living body with light capable of passing through the living body; a prism having an incidence surface including an incidence area for taking in light emerging from the living body, two or more reflecting surfaces for reflecting the light taken in through the incidence area, and an outlet surface for outputting the light reflected by the reflecting surfaces; and a camera module including a lens for focusing the light emerging from the outlet surface of the prism and an image pickup device for converting the light focused thereon by the lens into an electric signal and outputting the electric signal.

Abstract: Embodiments of the present invention describe a collaborative framework for mining of surveillance videos to detect abnormal events, which introduces a two-stage training process to alleviate the high false alarm problem. In the first stage, unsupervised clustering is performed on the segments of the video streams and a set of abnormal events are combined with user feedback to generate a clean training set. In the second stage, the clean training set is used to train a more precise model for the analysis of normal events and the motion detection results from multiple cameras can be cross validated and combined. This description is not intended to be a complete description of, or limit the scope of, the invention. Other features, aspects, and objects of the invention can be obtained from a review of the specification, the figures, and the claims.

Abstract: A system and method for tracking objects between multiple frames of a video is described. One method for tracking objects begins with a viewer initially identifying an object in a frame of video. If the viewer requires zooming, he can also select a scale factor for the identified object. Once the user has identified an object for tracking, the computer system identifies a reference point on the object and identifies the motion vectors for that reference point. Using the motion vectors, the computer system can track the identified object as it moves across the screen and can reposition an image acquisition area to track the location of the identified object in subsequent video frames.

Abstract: Methods and apparatus are described which provide secure interactive communication of text and image information between a central server computer and one or more client computers located at remote sites for the purpose of storing and retrieving files describing and identifying unique products, services, or individuals. A feature of the system is the ability to associate an identification image with a plurality of accounts, transactions, or records and identify a user not physically present at the client computer. Textual information and image data from one or more of the remote sites are stored separately at the location of the central server computer, requests for information are entered from remote terminals, the system being able to respond to multiple user requests simultaneously, and the information requested is recalled and downloaded for review to be displayed at the remote site.

Abstract: A central system for receiving captured transaction data from a plurality of remote capture devices over a network, the remote capture devices including a mobile device type and a fixed location device type, the system comprising: a receipt module to receive the captured transaction data; a processing module to process the received captured transaction data; and a storage module to store the processed transaction data such that characteristic data of the mobile device type is associated with the stored transaction data for said processed transaction data originating from a remote capture device of the mobile device type.

Abstract: A verification information generation system includes first and second data processing apparatuses. The first data processing apparatus has a unit holding first secret information, a unit receiving information associated with the second secret information from the second apparatus, a unit generating key information on the basis of the first secret information and the information associated with the second secret information, a unit generating key derivation auxiliary information allowing the key information to be derived from the second secret information, a unit generating verification information on the basis of information to be verified and the key information, and a unit outputting the information to be verified, the verification information, and the key derivation auxiliary information. The second secret information is information which is set in advance in the second data processing apparatus.

Abstract: A value document authentication apparatus and system that includes value document substrates having a uniform distribution of one or more phosphors that emit infrared radiation in one or more wavelengths, which can be measured at the same location on the value document that is illuminated by a phosphor exciting light source when the document passes the light source with a uniform velocity. The illumination and measurement locations on the value document can be offset. The measured infrared radiation as a series of overlapped measurements along a pre-selected track in the value document represents an intensity profile, which can be normalized after removing high variations. The normalized intensity profile of a test value document can be compared with normalized intensity profile from valid reference documents to authenticate the test value document.

Abstract: A border or perimeter is protected from intruders, such as illegal immigrants, terrorists with WMD or smugglers of drugs. The method comprises a detection and communication processing system capable of a high probability of detection and low probability of false positives. The system includes land-based sensor particles and sensitive airborne or land-based camera processing units. The sensors are sown over key border or perimeter landscape areas and are activated by specific pressure levels characteristic of the weight of transiting intruders whereby the sensors emit characteristic optical signals. Specific emitted indicators detect people, vehicles, or particular animals.

Abstract: In one arrangement, a first user sends information from a portable device and receives a response that depends, at least in part, on the location of a second user's portable device. The information sent from the first portable device may be based on data captured by a sensor in that device. In another arrangement, a user of a portable device sends two types of data, sensor-related data and location-related data, and receives a response that is based on both of these of data. In one particular such embodiment, the user scans a barcode or watermark from a coupon or other printed object, and sends decoded payload data—together with location data (e.g., GPS data)—to a remote server. The remote server routes the information to a vendor near the user who can, e.g., fulfill an order for food delivery to the user.

Abstract: A video monitoring system is proposed, which is used to mask objects in a monitored scene that involve the privacy of an individual. Such objects include vehicle license plates or the person himself. An unmasking occurs when proof of legitimacy is entered. In a modification, a combination of a stationary camera and a moving camera also permits the masking of individual objects in the monitored scene.

Abstract: A device for verifying polarization-variant images has first and second illumination arrangements deployed in fixed spatial relation to a camera to illuminate the camera's field of view. A polarizing arrangement is deployed so as to selectively overlie the second illumination source without overlying the first illumination source, thereby allowing switching between differing conditions of polarized illumination without requiring moving optical elements. Also disclosed are various methods employing such a device for authentication and fraud prevention. Alternative implementations employ two cameras with a single illumination arrangement.

Abstract: An information processing apparatus includes: a detection mechanism that includes a transparent substrate on which a detection electrode pattern is provided in biaxial directions and detects, with one of main surface sides of the transparent substrate being an input operation surface, a position on the input operation surface within the biaxial space that an object has touched, the transparent substrate being capable of transmitting near-infrared light; a to-be-authenticated-object placement portion provided in the vicinity of the input operation surface and on which the object is placed as an object to be authenticated; a first light source to irradiate the near-infrared light onto the object to be authenticated; and a photographic camera that is provided on the other one of the main surface sides of the transparent substrate and photographs the object to be authenticated onto which the near-infrared light has been irradiated via the transparent substrate.

Abstract: An apparatus for monitoring an access portal through an enclosure around a hazard comprises a line-scan camera mounted above the portal so that its linear field of view extends along a generally opposite threshold of the portal and can detect electromagnetic radiation reflected from an object passing through the portal. The apparatus distinguishes signals from the camera corresponding to items that are intended to pass through the portal for example on a conveyor from signals corresponding to items, particularly intruders that are not intended to pass through the portal. The apparatus preferably comprise an elongate sodium discharge lamp mounted above the portal and provided with a reflector so that monochromatic light therefrom is concentrated in a narrow strip extending along the threshold and the camera is sensitive only to this monochromatic light.

Abstract: In some embodiments, object recognition using global similarity-based classifier is presented. In this regard, an apparatus is introduced comprising: a camera, a display, and a processor, the processor to: receive an image from the camera, convert the image to a numerical representation, compute a similarity function between the converted image and a plurality of prototype image representations, and classify the output of the similarity function to identify the image. Other embodiments are also disclosed and claimed.

Abstract: A camera is used to sense cargo in a cargo space. An image of at least a portion of a cargo space is captured using the camera, and a digital signal processor classifies the image as representing an empty cargo space or a non-empty cargo space. Additionally, a type of cargo represented by the captured image may also be classified by the digital signal processor and an indication of the type of cargo output.

Abstract: According to one of embodiments, a system of facial information processing being captured facial image data of a user, and a feature point of a face of the user is extracted from this facial image data and encoded. The facial image data is associated with a unique identifier and/or the encoded feature point to be registered in an address management table.

Abstract: Associating subimages is disclosed. A first set of one or more subimages associated with a first image and a second set of one or more subimages associated with a second image are received. It is determined that a first subimage of the first set corresponds to a second subimage of the second set based at least in part on spatial information associated with the first subimage. The first subimage and the second subimage are associated.

Abstract: A method for testing a monitoring device (20) of an automatic labeling machine (10) for containers (12) for correct functioning, in the case of which, a specially marked measuring container (14) is fed thereto, upon whose detection, a labeling process is discontinued at least for this measuring container (14), and the measuring container (14) provided with markings (16) is scanned by at least one optical sensing device (21) of the monitoring device (20).

Abstract: A system and method for encoding and authenticating documents and data storage discs uniquely is described which can provide a means to authenticate a document such as a passport or identification document or driving licence or contract or a music compact disc (CD) or data CD or DVD or holographic DVD or credit card. The documents each comprise an encoding formed from a unique number or pattern or datagram image, which is either printed so that it can be read directly by a viewing device, or the encoding is cut by laser to create a pattern or perforation matrix into the document thereby leaving the unique number or pattern or datagram as a matrix of small holes or perforations in the document through which light may pass. The authentication process thus involves viewing and decoding the encoding and generating a computed result using a stored decoding algorithm.

Abstract: A method for re-identifying an image is provided. The method comprises obtaining a plurality of images and generating a correspondence map between the plurality of images. The method further comprises defining a plurality of region signatures for one or more regions comprising the plurality of images and comparing the plurality of images based on the correspondence map and the plurality of region signatures to perform image re-identification.

Abstract: Methods and systems are provided for analyzing and assessing documents using a writing profile for documents, such as a payment instrument. A method may include providing a document to a computer system. In an embodiment, the method may further include comparing writing in information fields of the document to at least one forger writing profile representation. In some embodiments, at least one forger writing profile representation may be obtained from at least one information field of at least one document that includes forged information. In an embodiment, the document may be identified as a document including forged information from an approximate match of at least one forger writing profile representation with writing in the document.

Abstract: One embodiment of the present invention relates to a machine-readable form configuration (and associated method). Another embodiment of the present invention relates to a system for interpreting at least one user mark (and associated methods). In one example, a plurality of user marks may be interpreted. In another example, the machine-readable form may be a lottery play slip, survey, test, or the like. In another example, the system may interpret user mark(s) made on a lottery play slip, survey, test or the like. In another example, the system may interpret user mark(s) made on a paper or the like having non-planar distortion(s).

Abstract: A pipeline architecture for analyzing multiple streams of video is embodied, in part, in a layer of application program interfaces (APIs) to each stage of processing. Buffer queuing is used between some stages, which helps moderate the load on the CPU(s). Through the layer of APIs, innumerable video analysis applications can access and analyze video data flowing through the pipeline, and can annotate portions of the video data (e.g., frames and groups of frames), based on the analyses performed, with information that describes the frame or group. These annotated frames and groups flow through the pipeline to subsequent stages of processing, at which increasingly complex analyses can be performed. At each stage, portions of the video data that are of little or no interest are removed from the video data. Ultimately, “events” are constructed and stored in a database, from which cross-event and historical analyses may be performed and associations with, and among, events may be made.

Abstract: The present invention relates to computer capture of object motion. More specifically, embodiments of the present invention relate to capturing of facial movement or performance of an actor. Embodiments of the present invention provide a head-mounted camera system that allows the movements of an actor's face to be captured separately from, but simultaneously with, the movements of the actor's body. In some embodiments of the present invention, a method of motion capture of an actor's performance is provided. A self-contained system is provided for recording the data, which is free of tethers or other hard-wiring, is remotely operated by a motion-capture team, without any intervention by the actor wearing the device. Embodiments of the present invention also provide a method of validating that usable data is being acquired and recorded by the remote system.

Abstract: An apparatus for playing video content includes a play means (100) for playing video content. The video content includes overlapping scenes (621, 622, 641, 642, 661, 662, 681, 682), with each scene having an associated scene signature. A scene hopping selector (44) is operative while the play means (100) is playing video content for selecting a hop. The selecting defines a current scene (102) which the play means (100) is playing at a time of the selection, and a current scene signature corresponding to the current scene (102). A similar scene hopping processor (104) operates responsive to a defining of a current scene (102). The similar scene hopping processor (104) compares the current scene signature with other scene signatures of the video content to identify a similar scene (106). The similar scene hopping processor (104) causes the play means (100) to transfer the playing to the similar scene (106).

Abstract: A pipeline architecture for analyzing multiple streams of video is embodied, in part, in a layer of application program interfaces (APIs) to each stage of processing. Buffer queuing is used between some stages, which helps moderate the load on the CPU(s). Through the layer of APIs, innumerable video analysis applications can access and analyze video data flowing through the pipeline, and can annotate portions of the video data (e.g., frames and groups of frames), based on the analyses performed, with information that describes the frame or group. These annotated frames and groups flow through the pipeline to subsequent stages of processing, at which increasingly complex analyses can be performed. At each stage, portions of the video data that are of little or no interest are removed from the video data. Ultimately, “events” are constructed and stored in a database, from which cross-event and historical analyses may be performed and associations with, and among, events may be made.