Abstract: An image data file management system according to the present invention includes a plurality of inspection sections which acquire an image of a subject and acquire various kinds of inspection results by performing image processing with respect to image data of the subject, and an image server which stores respective sets of the image data acquired by the respective inspection sections in association with information of the subject.

Abstract: Methods and systems for document image decoding incorporating a Stack algorithm improve document image decoding. The application of the Stack algorithm is iterated to improved decoding. A provisional weight is determined for a partial path to reduce template matching. In addition, semantically equivalent hypotheses are identified to reduce redundant hypotheses.

Abstract: A method for optical inspection and an apparatus for optical inspection of a surface of a substrate, the apparatus includes (i) An optical head comprising a two-dimensional matrix of photodetectors, which is positioned opposite the substrate so as to capture a sequence of area images of respective areas of the surface, (ii) A rotation device, which is coupled to rotate the substrate about a rotation axis, (iii) A translation device, coupled to impart motion to at least one of the optical head and the rotation device so that the optical head is translated radially relative to the substrate while the rotation device rotates the substrate, whereby the area images in the sequence are arrayed in a spiral pattern with respect to the surface, and (iv) An image processor, which is coupled to receive and process the area images so as to determine a characteristic of the surface.

Abstract: Detecting video phenomena, such as fire in an aircraft cargo bay, includes receiving a plurality of video images from a plurality of sources, compensating the images to provide enhanced images, extracting features from the enhanced images, and combining the features from the plurality of sources to detect the video phenomena. The plurality of sources may include cameras having a sensitivity of between 400 nm and 1000 nm and/or may include cameras having a sensitivity of between 7 and 14 micrometers. Extracting features may include determining an energy indicator for each of a subset of the plurality of frames. Detecting video phenomena may also include comparing energy indicators for each of the subset of the plurality of frames to a reference frame.

Abstract: An iris identification system for confirming identity of a person and method thereof are disclosed. The iris identification system comprises a mode converter for selecting one of registration and identification modes, an image input means, a luminance adjustment module, a registration module, an identification module, a reference iris image storage, and a main control unit. The registration module captures iris images when the registration mode is selected, preprocesses the captured iris image, defines the preprocessed iris image as main, auxiliary, negative main and compensation data, encodes the defined data, and registers the encoded data as data of the reference iris images; The identification module captures an iris image when the identification mode is selected, preprocesses the captured iris image, defines the preprocessed iris image as main, auxiliary, negative main and compensation data, encodes the defined data, and analyzes similarity both data.

Abstract: A method of reliably capturing biometric print images includes determining the print quality of a scanned image, detecting prints in the scanned image, and determining whether the scanned image is ready for capture. The method includes filtering the scanned image, binarizing the filtered image, detecting print area, print contrast, and print shape of the binarized image, and separating the print image into individual print images based on the print area, contrast, and shape. Each individual print image is classified base on a predetermined quality threshold and a quality classification of each individual print image is indicated. The method includes a predetermined capture delay time period, quality time period, and scanner timeout period. An operator can annotate issues regarding missing or unacceptable print images. A system of reliably capturing biometric print images includes a scanner including a print capture manager, a computer, and a communication link between the computer and scanner.

Abstract: In the prior art, in character recognition of a language having many characters, such as Japanese, a feature vector is extracted from an input pattern, distances between the feature vector and reference vectors are calculated, and a character corresponding to a reference vector having the smallest distance value is selected as a recognized character. However, in the character recognition of a language having many characters, since the number of the reference vectors to be compared is large, there is a limit in improvement of processing speed of the character recognition. In the present invention, reference vectors corresponding to target characters are classified into plurality of classes based on occurrence frequencies of characters. When distances between the feature vector and the reference vectors are calculated, a comparison is sequentially made from the reference vectors of a class having a high character occurrence frequency, so that the processing speed of the character recognition is improved.

Abstract: A system augments stylus keyboarding with shorthand gesturing. The system defines a shorthand symbol for each word according to its movement pattern on an optimized stylus keyboard. The system recognizes word patterns by identifying an input as a stroke, and then matching the stroke to a stored list of word patterns. The system then generates and displays the matched word to the user.

Abstract: A method and computer program product are disclosed for identifying output classes with multi-modal dispersion in feature space and incorporating multi-modal structure into a pattern recognition system architecture. A plurality of input patterns, determined not to be associated with any of a set of at least one represented output class by a pattern recognition classifier, are rejected. The rejected pattern samples are grouped into clusters according to the similarities between the pattern samples. Clusters that contain samples associated with a represented output class are identified via independent review. The classifier is then retrained to recognize the identified clusters as output pseudoclasses separate from the represented output class with which they are associated. The system architecture is reorganized to incorporate the output pseudoclasses. The output pseudoclasses are rejoined to their associated class after classification.

Abstract: A knowledge-based hierarchical method for detecting regions of interests (ROIs) uses prior knowledge of the targets and the image resolution in detecting ROIs. The result produces ROIs that contain only one target that is completely enclosed within the ROI. The detected ROI can conform to the shape of the target even if the target is of irregular shape. Furthermore, the method works well with images that contain connected targets or targets broken into pieces. The method is not sensitive to contrast levels and is robust to noise. Thus, this method effectively detects ROIs in common real world imagery that has a low resolution without costly processing while providing fast and robust results.

Abstract: Techniques are provided to classify patterns in isogenous pattern sources. Techniques are provided to determine a computationally inexpensive upperbound on the true score or joint probability of the field label and field features over all field labels. Candidate field labels associated with promising upperbound scores are dynamically queued. True scores are computed for a subset of the candidates fields resulting in reduced computations to determine a field label. Techniques are also provided to determine optimal variables for any system with shared constraints.

Abstract: A method for determining peak summit locations for multiple peaks on a three-dimensional contour includes the step of determining a highest point on the contour. Next, a peak summit of a peak on the contour is identified. The peak summit is related to the highest point on the contour. Next, the points on the contour associated with the peak on the contour are determined, and the contour is modified to zero out the points on the contour associated with the peak. The above steps are then repeated until all of the peak summits on the contour are identified.

Abstract: Apparatus and method for registration comprises a computer and a server in communication via a network, an intranet and/or the Internet, means for entry of data into the computer, and a signature or biometric digitizer including coupling software for directly entering digitized signature or biometric data electronically into the computer. The data and digitized signature or biometric data are communicated to the server. The registration apparatus and method may be utilized for voter or other registration and/or another transaction.

Abstract: An image correction system comprises a detection application accessible by a processor and adapted to identify a viewing direction of at least one eye of a subject within an image. The system also comprises a reconstruction application accessible by the processor and adapted to automatically modify the image to modify the viewing direction of the at least one eye of the subject.

Abstract: A computer-implemented method is disclosed for recognizing edges in a digital image having a plurality of pixels with gray-scale values defining features. The method includes recognizing edges of the features by cearting a new image in which pixels in the new image corresponding to pixels in the gray-scale image that have a brightness value meeting a predetermined threshold are assigned a first binary value to represent edge regions, while remaining pixels in the new image are assigned a second value to represent both background and internal areas of the features. Area recognition is then performed to distinguish internal feature areas from background areas. The method further includes detecting edge lines from the edge regions that separate features from background and internal feature areas.

Abstract: Systems and methods for triage of passages of text output from an OCR system by use of trainable models of the accuracy of the OCR system based on attributes of individual characters. The systems and methods according to this invention automatically triage an OCR-output text passage by determining at least one OCR-output character attribute for each OCR-output character, determining an error rate for the OCR-output text passage using a triage model and the determined at least one OCR-output character attribute, and comparing the determined error rate for the OCR-output text passage with an OCR-output text passage threshold error rate to perform an OCR-output text passage triage decision. Triage decision includes for example, sending OCR results directly to an end user without any post-OCR processing, sending the OCR results through a post-OCR inspection and processing stage, sending the original document image to be completely keyed in manually, and a combination thereof.

Abstract: The present application describes systems and methods for composing documents using a digital pointing instrument. In further configurations, a user utilizes a pen to partially fill in a form and provide destination data whereby a forms processor adds additionally required information to the form in order to compose a complete form that is sent to the destination.

Abstract: Methods and systems for document image decoding incorporating a Stack algorithm improve document image decoding. The application of the Stack algorithm is iterated to improve decoding. A provisional weight is determined for a partial path to reduce template matching. In addition, semantically equivalent hypotheses are identified to reduce redundant hypotheses.

Abstract: A three dimensional (3-D) image is generated from a plurality of portions of an image of an object, each captured portion of the image is based on a scan width of an image capture device. A range finding device obtains at least one range data value for each captured portion of the image as at least one corresponding position in each captured portions of the image, and a base to which the image capture device and the range finding device are mounted moves in increments based on the scan width of the image capture device.

Abstract: Systems and methods for performing clustering of a document image are disclosed. A property of an extracted mark from a document is compared to the properties of the existing clusters. If the property of the mark fails to match any of the properties of the existing clusters, the mark is added as a new cluster to the existing cluster. One property that can be utilized is x size and y size, which is the width and height, of the existing clusters. Another property that can be employed is ink size, which refers to the ratio of black pixels to total pixels in a cluster. Yet another property that can be utilized is a reduced mark or image, which is a pixel size reduced version the bitmap of the mark and/or cluster. The above properties can be employed to identify mismatches and reduce the number of bit by bit comparisons performed.