Abstract: System and method for determining a classifier to discriminate between two classes—object or non-object. The classifier may be used by an object detection program to detect presence of a 3D object in a 2D image. The overall classifier is constructed of a sequence of classifiers, where each such classifier is based on a ratio of two graphical probability models. A discreet-valued variable representation at each node in a Bayesian network by a two-stage process of tree-structured vector quantization is discussed. The overall classifier may be part of an object detector program that is trained to automatically detect different types of 3D objects. Computationally efficient statistical methods to evaluate overall classifiers are disclosed. The Bayesian network-based classifier may also be used to determine if two observations belong to the same category.

Abstract: According to a method for providing a notification on a face recognition environment of the present disclosure, the method includes obtaining an input image that is input in a preview state, comparing feature information for a face included in the input image with feature information for a plurality of reference images of people stored in a predetermined database to determine, in real-time, whether the input image satisfies a predetermined effective condition for photographing. The predetermined effective condition for photographing is information regarding a condition necessary for recognizing the face included in the input image at a higher accuracy level than a predetermined accuracy level. The method further includes providing a user with a predetermined feedback for photographing guidance that corresponds to whether the predetermined effective condition for photographing is satisfied.

Abstract: The present invention aims to encourage the input of comment on content requiring the viewing user's input and prevent the comment from failing to be input in a case where the content is displayed and the viewing user inputs the comment on the content. Therefore, according to the present invention, when the content is displayed on a display apparatus, the viewing user of the content is photographed to capture photographed image data. A face image included in the displayed content and the face image of the viewing user included in the photographed image data are compared, and, if they are similar, a comment input area is displayed to encourage the viewing user to input a comment.

Abstract: In one implementation, a method includes detecting, using a processor, user input through a camera lens. The method further includes determining, using the processor, that an identity of a user, selected from identities of at least two users, is associated with the user input. The method also includes tracking, using the processor, a local interaction between the at least two users based on at least the identity, the user input, and stored rules that govern the local interaction. The tracking can include determining whether the user has complied with the stored rules that govern the local interaction. Furthermore, the local interaction can include a multiplayer game.

Abstract: An apparatus and method for calculating athlete speed non-invasively, on the field/court of play using data from a torso-mounted inertial measurement unit. The method complements existing, GPS-based methods for calculating athlete speed by enabling use in environments where GPS signal is unavailable (i.e. indoors).

Abstract: A gesture recognition system using a skin-color based method combined with motion information to achieve real-time segmentation. A Kalman filter is used to track the centroid of the hand. The palm center, palm bottom, as well as the largest distance from the palm center to the contour from extracted hand mask are computed. The computed distance to a threshold is then compared to decide if the current posture is “open” or “closed.” In a preferred embodiment, the transition between the “open” and “closed” posture to decide if the current gesture is in “select” or “grab” state.

Abstract: An information processing device 200 of the present invention includes: a recognition result acquiring means 201 for acquiring respective recognition result information outputted by a plurality of recognition engines 211, 212 and 213 executing different recognition processes on recognition target data; and an integration recognition result outputting means 202 for outputting a new recognition result obtained by integrating the respective recognition result information acquired from the plurality of recognition engines. The recognition result acquiring means 201 is configured to acquire the respective recognition result information in a data format common to the plurality of recognition engines, from the plurality of recognition engines. The integration recognition result outputting means 202 is configured to integrate the respective recognition result information based on the respective recognition result information, and output as the new recognition result.

Abstract: A determination is made in real-time regarding whether a bicyclist is present in a target image. A target image is received. The target image is classified and an error value for the target image is determined using a linear classifier. If the error value does not exceed the threshold value, the classification is outputted. Otherwise, if the error value exceeds the threshold value, the target image is classified using a non-linear classifier.

Abstract: The disclosed embodiments provide a system that processes data. During operation, the system obtains a first electronic document associated with a user. Next, the system obtains one or more locations of data elements in the first electronic document from the user and uses the one or more locations to extract a first set of data from the first electronic document. Finally, the system enables, for the user, use of the first set of data with an application without requiring manual input of the first set of data into the application.

Abstract: An image evaluation device includes a storage unit that stores sample image data that represent a virtual sample image simulating a sample image included in a sample printout that is recognized as a non-defective printout; a reading unit that reads an inspection object image included in an inspection object printout obtained by printing the sample image on a recording medium by a printing device using image data representing the sample image; an extraction unit that extracts a line defect including a linear pattern formed in a specific direction from the inspection object image represented by inspection object image data, based on a difference value between the sample image data and the inspection object image data; and an evaluation unit that evaluates a visibility of the line defect extracted by the extraction unit.

Abstract: Embodiments provide an iris scanning apparatus for identifying a subject, employing a wide-angle image collector, and a method thereof. A wide angle camera is employed in the iris scanning apparatus to allow a user to easily locate a small eye region of a subject without having to check back and forth between an image display and the subject's face. The apparatus and method are also capable of measuring the distance to the subject's eye and displaying the distance information on the image display, and informing the user as to whether the eye of the subject is within operating range of the iris scanning apparatus. Also, iris scanning is automatically performed without the user's input when an eye is positioned within operating range, and is not performed if an image captured by the iris scanning apparatus does not contain an eye region, in order to prevent erroneous operation.

Abstract: In a sequence of images of a scene acquired by a stationary camera, objects are detected and tracked by determining a first set of candidate foreground regions according to a background model. A second set of candidate foreground regions is determined according to a set of foreground models. Then, candidate foreground regions in the first set and the second set are validated to produce a final set of foreground regions in the image that include the objects.

Abstract: An image processing device that accesses a storage unit that stores a feature point of a recognition-target object, the device includes an obtaining unit mounted with a user and configured to obtain image data in a direction of a field of view of the user; a recognizing unit configured to recognize the recognition-target object included in the image data by extracting a feature point from the image data and associating the extracted feature point and the feature point of the recognition-target object stored in the storage unit with each other; a calculating unit configured to calculate a location change amount of the feature point corresponding to the recognition-target object recognized by the recognizing unit from a plurality of the image data obtained at different times and calculate a motion vector of the recognition-target object from the location change amount; and a determining unit configured to determine a movement.

Abstract: Object detection and extraction is performed from image sequences utilizing circular buffers for both source images and tracking. The detection and extraction process is performed in relation to the previous and current image, and the current and next image, including: alignment, absolute difference, removal of non-overlaps, and contour detection in difference images. An intersection is performed on these two outputs to retain contours of the current image only. Recovery of missing contour information is performed utilizing gradient tracing, followed by morphological dilation. A splitting process is performed if additional objects are found in a bounding box area. A mask image bounded by object contour is created, color attributes assigned, object verification performed and outliers removed. Then untracked objects are removed from the mask and a mask is output for moving objects with rectangular boundary box information.

Abstract: A method, system, and/or computer program product tracks an object in a video. A bounding box is defined by the user in a first frame, thus representing the object to be tracked based on a point of interest. A static dictionary D is populated with the densely overlapping patches from a search window. A new frame in the video is detected, and candidate patches, in the new frame, that potentially depict the object being tracked are identified. The candidate patches are co-located with the multiple densely overlapping patches to form a dynamic candidate dictionary Y of candidate patches. Candidate patches that best match the densely overlapping patches from the first frame are identified by an L1-norm solution, in order to identify a best-matched patch in the new frame.

Abstract: A system and method of monitoring a customer space including obtaining visual data comprising image frames of the customer space over a period of time, defining a region of interest within the customer space, the region of interest corresponding to a portion of the customer space in which customers relocate objects, monitoring the region of interest for at least one predefined clutter condition, and generating a notification when the at least one predefined clutter condition is detected.

Abstract: A method and system for video-based object tracking includes detecting an initial instance of an object of interest in video captured of a scene being monitored and establishing a representation of a target object from the initial instance of the object. The dominant motion trajectory characteristic of the target object are then determined and a frame-by-frame location of the target object can be collected in order to track the target object in the video.

Abstract: A computer receives asynchronous information originating from a light sensor (10) having a pixel matrix disposed opposite a scene. The asynchronous information comprises, for each pixel of the matrix, successive events originating from this pixel and depending on variations in light in the scene. For a place of estimation (p) in the matrix of pixels and an estimation time (t), the computer selects a set (Sp t) of events originating from pixels included in a spatial neighborhood (??) of the place of estimation and which have occurred in a time interval (?) defined with respect to the estimation time, such that this set has at most one event per pixel of the spatial neighborhood. The computer quantifies the variations in the times of occurrence of the events of the set selected as a function of the positions, in the matrix, of the pixels from which these events originate.

Abstract: A computing system obtains a respective motion vector for each of a series of motion event candidates in real-time as said each motion event candidate is detected in a live video stream. In response to receiving the respective motion vector for each of the series of motion event candidates, the computing system determines a spatial relationship between the respective motion vector of said each motion event candidate to one or more existing clusters established based on a plurality of previously processed motion vectors, and in accordance with a determination that the respective motion vector of a first motion event candidate of the series of motion event candidates falls within a respective range of at least a first existing cluster of the one or more existing clusters, assigns the first motion event candidate to at least a first event category associated with the first existing cluster.

Abstract: An autonomous lock-on target tracking system and method with geospatial-aware PTZ cameras includes a camera imaging a terrain space. The camera acquires images, and first and second images are aligned. A frame-differencing operation produces a resultant image including blobs corresponding to elements in the terrain space. One of the blobs is classified as an object and tracked as a target. The target is tracked by determining the distance between a centroid of the target and a center of a field of view of the camera, and instructing the camera to move through the distance. The distance is continually updated as the camera and the target move. Disclosed are also methods for deploying the georeferencing enabled version of such PTZ camera on stationary and mobile land, sea and air platforms.

Abstract: A method of automatic obstacle location mapping comprises receiving an indication of a feature to be identified in a defined area. An instance of the feature is found within an image. A report is then generated conveying the location of said feature.

Abstract: A read-only memory (ROM) includes storage areas used as a processing setting data storage unit, a successful detection rate storage unit, and a processing time storage unit. A central processing unit (CPU) can function as a calculation unit by executing a calculation program stored on the ROM. The successful detection rate storage unit stores a predetermined successful detection rate (the probability of executing subsequent processing based on a result of a current processing). The processing time storage unit stores a predetermined processing time of each processing. The calculation unit calculates a module configuration for executing each processing according to the successful detection rate stored on the successful detection rate storage unit and the processing time stored on the processing time storage unit. The processing setting data storage unit stores setting data of a characteristic amount and a setting data of positional information about image data (the address of the image data).

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: The invention is related to a method for registering at least one part of a first image and of a second image, including the steps of providing a first image of the real environment and a coordinate system associated to the first image, a second image of the real environment, and measurements of orientation and/or distance of a capturing device with respect to the real environment while capturing the second image. A collineation warping function is then determined from the measurements associated to at least one part of the second image.

Abstract: An object detection method includes an image acquisition step of acquiring an image including a target object, a layer image generation step of generating a plurality of layer images by one or both of enlarging and reducing the image at a plurality of different scales, a first detection step of detecting a region of at least a part of the target object as a first detected region from each of the layer images, a selection step of selecting at least one of the layer images based on the detected first detected region and learning data learned in advance, a second detection step of detecting a region of at least a part of the target object in the selected layer image as a second detected region, and an integration step of integrating a detection result detected in the first detection step and a detection result detected in the second detection step.

Abstract: Methods and systems for achieving accurate segmentation of characters with respect to a license plate image utilizing a reinforcement learning approach. A vehicle image can be captured by an image capturing unit and processed utilizing an ALPR (Automatic License Plate Recognition) unit. The reinforcement learning (RL) approach can be configured to initialize a segmentation agent with a starting location. A proper segmentation path (cuts) from top to bottom and from a darker to lighter area in a cropped license plate image can be identified by the segmentation agent during a training phase. Rewards can be provided based on a number of good and bad moves. The association between a current state and a sensory input with a preferred action can be learned by the segmentation agent at the end of the training phase.

Abstract: A device and method are provided for recognizing text on a curved surface. In one implementation, the device comprises an image sensor configured to capture from an environment of a user multiple images of text on a curved surface. The device also comprises at least one processor device. The at least one processor device is configured to receive a first image of a first perspective of text on the curved surface, receive a second image of a second perspective of the text on the curved surface, perform optical character recognition on at least parts of each of the first image and the second image, combine results of the optical character recognition on the first image and on the second image, and provide the user with a recognized representation of the text, including a recognized representation of the first portion of text.

Abstract: A rapid target detection approach with corresponding method and system to detect targets in scene pixels, efficiently, is presented. The approach includes tailoring an approximation of a target score for each scene pixel, individually, based on an “intermediate target score.” The intermediate target score includes a portion of the terms used to compute the target score. The portion is selected by computing a signal-to-clutter ratio (SCR) for a spectral reference associated with a target and ranking the terms by their contribution to the SCR. Scene pixels with low intermediate target scores are removed from further processing. The remaining scene pixels are further processed, including computing target scores to detect targets in these scene pixel. Advantageously, examples of the approach process a few terms of all scene pixels, eliminate most scene pixels, and calculate more terms on high target scoring scene pixels as needed.

Abstract: A pixel set formation unit in an image analysis unit of an image processing device forms pixel sets from original images subject to analysis. A principal analysis unit of the image analysis unit performs principal component analysis in units of pixel sets. A synthesis unit synthesizes results of analysis in units of pixel sets so as to generate images of eigenvectors of a size of the original images. An image generation unit displays the images of the eigenvectors and stores data for an image generated by using the images of the eigenvectors in a generated image storage unit.

Abstract: The disclosure provides a filtering engine for selecting a subset of hyperspectral imaging wavebands having information useful for detecting a target in a scene. Selecting these wavebands, called “sparse bands,” is an iterative process. One or more search techniques of varying computational complexity are used in the process. The techniques rely on various selection criteria, including a signal to clutter ratio that measures the “goodness” of band selection. A convenient example of the filtering engine uses several of the techniques together in a layered approach. In this novel approach, simpler computational techniques are applied, initially, to reduce a number of bands. More computationally intensive techniques then search the reduced band space. Accordingly, the filtering engine efficiently selects a set of sparse bands tailored for each target and each scene, and maintains some of the detection capability provided with a full set of wavebands.

Abstract: Methods and apparatuses for compressive sensing that enable efficient recovery of features in an input signal based on acquiring a few measurements corresponding to the input signal. One method of compressive sensing includes folding an image to generate first and second folds, and recovering a feature of the image based on the first and second folds without reconstructing the image. One example of a compressive sensing apparatus includes a lens, a focal plane array coupled to the lens and configured to generate first and second folds based on the image, and a decoder configured to receive the first and second folds and to recover a feature of the image without reconstructing the image. The feature may be a local geometric feature or a corner. Compressive sensing methods and apparatuses for determining translation and rotation between two images are also disclosed.

Abstract: Adjusting data for photographed images includes detecting a reference image in the data, where the reference image contains a detectable uniformity and adjusting the data according to the reference image. The reference image may be a uniform grid pattern of dots preprinted on paper. A paper type may be determined prior to adjusting the data according to the reference image. The paper type may be determined according to spacing and/or patterns of the dots, and/or layout of page areas covered with dots. Adjusting the data may include removing effects corresponding to a folded corner, a removed corner, an obstructed corner, lens flare spots, and/or a shadow. Positional coordinates of the data may be adjusted by normalizing the grid through a non-linear transformation that eliminates curvature of the grid and/or distortions based on perspective.

Abstract: A machine may be configured as a vehicle identification machine to identify a model of a vehicle based on an image that depicts a dashboard of the vehicle. As configured, the machine may receive an image of the dashboard, where the image depicts a layout of instrumentation within the dashboard. The machine may identify the layout of instrumentation by processing the image. For example, the machine may process the image by determining a position of an instrument within the layout of instrumentation, determining an outline of instrument, or both. The machine may access a data record that correlates a model of the vehicle with the identified layout of instrumentation and, based on the data record, identify the model of the vehicle. The machine may then provide a notification that references the vehicle, references the identified model of the vehicle, or references both.

Abstract: In techniques for category histogram image representation, image segments of an input image are generated and bounding boxes are selected that each represent a region of the input image, where each of the bounding boxes include image segments of the input image. A saliency map of the input image can also be generated. A bounding box is applied as a query on an images database to determine database image regions that match the region of the input image represented by the bounding box. The query can be augmented based on saliency detection of the input image region that is represented by the bounding box, and a query result is a ranked list of the database image regions. A category histogram for the region of the input image is then generated based on category labels of each of the database image regions that match the input image region.

Abstract: Techniques for using infrared imaging to create digital images for use in product customization are described. In an embodiment, an infrared photograph of a product with imprinted markup is received and a visible light photograph of the product with the imprinted markup is received. The imprinted markup is visible in the visible light photograph but is not visible in the infrared photograph. Instructions for rendering a customization image of the product depicting a particular customization are determined based in part on the infrared photograph and visible light photograph, where the particular customization is not in the infrared photograph or the visible light photograph.

Abstract: An electronic device includes a housing and an electronic card connector fixed on the housing. The electronic card connector includes a tray and a fixing member. The tray includes a main body defining a card slot. The tray further includes two elastic arms protruding from two sidewalls of the tray respectively. The elastic arms include protrusions. The fixing member includes two notches corresponding to the two protrusions. When the main body receives in the second accommodating space, each of the two protrusions receives in one of the two notches respectively to engage the tray with the fixing member. When a pressure applied on the two elastic arms to enable the two protrusions to disengage from the two notches, the tray is disengaged from the fixing member.

Abstract: An information processing apparatus comprises a first acquiring controller which acquires a first file; a second acquiring controller which acquires area information to indicate a storage area on a predetermined storage medium, the first file acquired by the first acquiring controller being stored in the storage area; a generating controller which generates a second file having an additional information area capable of storing additional information, from the first file acquired by the first acquiring controller; and a storing controller which stores the area information acquired by the second acquiring controller as the additional information in the additional information area of the second file generated by the generating controller.

Abstract: A method of calibrating a printer using a reflective scanner is disclosed. Because the reflective scanner used for calibration may only be able to accurately measure a limited density range that is less than the full density range of the printer, some information from the reflective scanner is disregarded or deemphasized during the calibration process. A calibration page is printed and scanned. Lookup tables (LUTs) that comprise the printer calibration values are updated based on adjustments calculated from the scanner for density regions where the scanner produces relatively accurate measurements, but updated based on the preexisting settings for density regions where the scanner produces relatively inaccurate measurements. In transitions regions between accurate and inaccurate regions, the LUTs are adjusted based on a combination of measurements from the scanner and the preexisting settings.

Abstract: An apparatus for printing on a receiver with a plurality of colored dry inks and a dry white ink, the apparatus includes a look-up table having a set of one dimensional look-up tables for each of the colored inks and black inks, which look-up table which receives a value corresponding to a laydown at each pixel location of the receiver; wherein the look-up table determines a laydown of white ink at each pixel location depending on the laydown of the colored inks and black ink; and a logic and control unit which determines an amount of white ink to laydown by computing a value from the determined white laydowns of each look-up table.

Abstract: An information processing apparatus including a hot folder, comprises: a first determination unit configured to determine whether print processing of the job data stored in the hot folder is executable; a printing unit configured to print the job data determined to be executable; a second determination unit configured to determine whether the printing unit has normally ended the print processing of the job data; a specifying unit configured to specify outline information of a status of the print processing of the job data; an acquisition unit configured to acquire detailed information of the status of the print processing of the job data; and a creation unit configured to create a printing status notification file including the outline information of the status of the print processing of the job data specified and the detailed information of the status of the print processing of the job data acquired.

Abstract: Provided is an image forming system including: an image forming section which forms images on sheets; a post-processing device which executes post-processing on the sheets on which the images are formed on the image forming section; and a controller which controls the image forming apparatus and the post-processing device, wherein the image forming section forms the images on the sheets in a state corresponding to the post-processing as a trial print with respect to a job for which the post-processing is designated, and the post-processing device ejects the sheets in a state that the post-processing is not completed on the sheets on which the images are formed.

Abstract: A method of operating a module is disclosed. The method includes adjusting an impedance between a power connection and a ground connection to regulate a power connection voltage targeted to a predetermined target voltage, and setting a module communication address based on the adjustment. The power connection voltage is a voltage on the power connection. Other methods are disclosed.

Abstract: A bar code generation and processing system for medical and other use comprises at least one repository and a bar code processor. The at least one repository of information includes, identification data of multiple bar code scanners and also associates a bar code displayed in an image associated with an executable application and presented on a device with, the executable application and at least one of, (a) the device and (b) a data destination associated with the application. The bar code processor receives identification data of a bar code scanner and data representing the bar code displayed in the image and uses the information in associating the bar code with the data destination associated with the application and a particular bar code scanner of the multiple bar code scanners. The bar code processor communicates data acquired using the particular bar code scanner to the data destination in response to the association.

Abstract: The pattern printed sheet 1 of the present invention includes a substrate 2 and a non-visible light-reflective transparent pattern 3 printed on a surface of the substrate, wherein an ink for forming the transparent pattern 3 contains a non-visible light-reflective material capable of selectively reflecting a light having a wavelength in a non-visible light range, and the transparent pattern 3 printed on the surface of the substrate 2 has a multilayer structure in section which is repeated at predetermined intervals as observed by a scanning electron microscope, and reflects only a circular polarization component in a predetermined rotation direction relative to an incident light applied thereto.

Abstract: Methods and systems for generating and authenticating barcodes and in particular generating secure barcodes are disclosed. In one embodiment, a method, performed by a certificate authority for creating a trusted content, comprises receiving, via a receiver, a target content and verifying the target content to determine whether the target content is safe or appropriate. Further, the method comprises, based on a result of the verifying, generating and storing, in a storage medium, response data; generating, via a processor, and storing in the storage medium an identifier corresponding to the response data; generating, via the processor, resolution data, the resolution data including the identifier and an address of the certificate authority; and transmitting, via a transmitter, the resolution data as the trusted content.

Abstract: A method of enhancing a matrix barcode with environment image. The method comprises generating, by a server, an original matrix barcode based on source information, capturing, by a camera, an image of the original matrix barcode in a graphic environment comprising the matrix barcode and at least part of the graphic environment information, and parsing the image to obtain the source information and the at least part of the graphic environment information. The method further comprises generating a key based on the at least part of the graphic environment information, encrypting the source information with the key to obtain encrypted source information, encoding the encrypted source information into a first matrix barcode, and encoding the key into a key matrix barcode.

Abstract: Provided is a device and system for performing communication using wireless power, and a communication device using wireless power. The device may calculate a slope of an envelope in a waveform of energy stored in a target resonator through mutual resonance with a source resonator, and estimate a point placed within a predetermined interval around a point at which the slope reaches a maximum as a starting point of the mutual resonance between the source resonator and the target resonator.

Abstract: The present invention provides value tokens having improved security while achieving enhanced decorative effects, contrasting edge “spots”, increased physical weight, and flexibility of construction and design. Stacked structures formed from pluralities of layers are featured.

Abstract: Methods, computer readable media, and apparatuses provide robotic explosive hazard detection. A robot intelligence kernel (RIK) includes a dynamic autonomy structure with two or more autonomy levels between operator intervention and robot initiative A mine sensor and processing module (ESPM) operating separately from the RIK perceives environmental variables indicative of a mine using subsurface perceptors. The ESPM processes mine information to determine a likelihood of a presence of a mine. A robot can autonomously modify behavior responsive to an indication of a detected mine. The behavior is modified between detection of mines, detailed scanning and characterization of the mine, developing mine indication parameters, and resuming detection. Real time messages are passed between the RIK and the ESPM. A combination of ESPM bound messages and RIK bound messages cause the robot platform to switch between modes including a calibration mode, the mine detection mode, and the mine characterization mode.

Abstract: A coordination processor receives data from a simulated role-play environment having a performer that is assigned a role. Further, the coordination processor composes an instruction to the performer to perform an action in the simulated role-play environment. The instruction is selected to implement a narrative possibility in a role-playing simulation. In addition, the instruction is sent to an interface that provides the instruction to the performer in the simulated role-play environment.