Abstract: The invention relates to a method and a system for recording biometric data, especially for recording the features of the fingers or faces of persons, wherein an object is recorded by optically scanning it and evaluated by digital image processing. The inventive method is characterized in that the object is recorded simultaneously or almost simultaneously by at least two different recording devices, whereby all pixels of the surface to be imaged are imaged in at least two different directions in at least one digital two-dimensional image each and a three-dimensional model of the viewed object is calculated from at least two images.

Abstract: A multimodal biometric identification or authentication system includes a plurality of biometric clients. Each of the biometric clients may include devices for capturing biometric images of a plurality of types. The system includes a router in communication with the biometric clients. The router receives biometric images from, and returns biometric scores or results to, the biometric clients. The system includes a plurality of biometric matching engines in communication with the router. Each biometric matching engine includes multiple biometric processors. Each biometric processor is adapted to process biometric data of a particular type. The biometric matching engines transmit and receive biometric data to and from the router.

Abstract: In consideration of N-dimensional similarity, a multiparameter high precision concurrent estimation method and a multiparameter high precision concurrent estimation program in image subpixel matching, which can estimate a correspondence parameter between images precisely, concurrently, and stably with a small amount of computation at high speed.

Abstract: The invention provides an apparatus by which organism characteristic data included in an entire image can be acquired without producing the entire image from a plurality of partial images. The apparatus detects, every time a partial image is sampled, a relative positional relationship between the partial image and a different partial image sampled already, and extracts characteristic portion data including characteristic information unique to the organism portion from the partial image. Then, the apparatus synthesizes the extracted characteristic portion data of the partial image and characteristic portion data of the different partial image based on the detected relative positional relationship of the partial image. The apparatus can be applied, for example, to an authentication apparatus which uses a sweep type fingerprint sensor.

Abstract: A method for acquiring biometric data of a finger a surface to be imaged includes touchlessly and simultaneously imaging a finger surface to be imaged along at least three different directions into digital images, wherein each point of the surface to be imaged is imaged along at least two of the directions and wherein the surface to be imaged extends from a first nail edge across a finger-ball to a second nail edge. Subsequently, a geometric basic model for at least a part of the finger is determined using at least one of the digital images. Pre-warped images are calculated by geometrically pre-warping the digital images using the geometric basic model. Additionally, a three-dimensional model of the surface to be imaged is reconstructed using a stereoscopic analysis of the pre-warped images and at least one finger characteristic is determined using the three-dimensional model.

Abstract: A data processing apparatus and method, where the apparatus includes a region selecting unit configured to select a region corresponding to a pixel of interest, a frequency detector configured to detect a frequency corresponding to pixels belonging to the region, a continuity detector configured to detect data continuity of the image data, and a real world estimating unit configured to estimate the light signals by estimating the continuity of the real world light signals which have been lost.

Abstract: A multimodal biometric identification or authentication system includes a plurality of biometric clients. Each of the biometric clients may include devices for capturing biometric images of a plurality of types. The system includes a router in communication with the biometric clients. The router receives biometric images from, and returns biometric scores or results to, the biometric clients. The system includes a plurality of biometric matching engines in communication with the router. Each biometric matching engine includes multiple biometric processors. Each biometric processor is adapted to process biometric data of a particular type. The biometric matching engines transmit and receive biometric data to and from the router.

Abstract: A system for detecting and counting individuals in a stationary or moving crowd based on a digital or digitized image captured from a single camera. Initial information is assumed based on a foot-to-head plane homology, where a geometric construct is developed to best enclose image features with a high probability of being an individual within a crowd. These geometric constructs are then subjected to further probabilistic analysis to determine individuals. The vector track of each individual is determined to validate the determination of a group of features as individuals, thereby compensating for occlusion of an individual within any given frame image. A virtual gate is then employed to count the individuals moving past the virtual gate. Also, by weighting portions of the individual, events near the gate can be predicted.

Abstract: The present invention enables processing results which are more accurate and which have higher precision as to events of the real world to be obtained. A non-continuity component extracting unit 201 detects discontinuity portions of pixel values of multiple pixels in an input image. A peak detecting unit 202 detects a peak of change of pixel values from a discontinuity portion. A monotonous increase/decrease detecting unit 203 detects monotonous increase/decrease regions wherein pixel values increase or decrease monotonously from the peak. A continuousness detecting unit 204 detects a monotonous increase/decrease region where another monotonous increase/decrease region of the monotonous increase/decrease regions exists at an adjacent position on the screen, as a continuity region having data continuity. A data continuity direction detecting unit 301 detects the direction of continuousness of the continuity region.

Abstract: An article of commerce comprising an edible substrate having an image disposed thereon, and a method for making edible substrates having a variety of different images.

Abstract: Local data maps of an optical imaging system are stitched together into a composite global data map based on a merit function supporting closed-form processing. Overlapping regions of the local data maps are defined as difference maps that are given a parametric description. Corrective orientations of the local data maps are derived by collectively matching parametric descriptions of the corrective orientations for the overlapping local data maps to the parametric descriptions of the corresponding difference maps.

Abstract: A system and method for automatically segmenting bone regions from Computed Tomography Angiography (CTA) volume data is disclosed. A locally operated bone detector distinguishes between bone regions and contrast agent filled vessels. A filtering operator removes small noise from the detected bone regions. A dilator expands the filtered detected bone regions to adjacent trabecular bones. A processor applies the dilated detected bone regions to the CTA volume data. A display shows the applied CTA volume data.

Abstract: A digital camera that automatically corrects dust artifact regions within acquired images by compiling a dust map includes an optical system for acquiring an image with a corresponding dust calibration table for such optical system, including a lens assembly and an aperture stop, in which the corresponding dust calibration map can reside. A transformation between the dust map and the specific lens calibration table, enables the use for a single dust map in multiple instances of lenses and focal length, without the need to recalibrate the digital camera for each instance.

Abstract: Described is an active learning system for fingerprinting an object identified in an image frame. The active learning system comprises a flow-based object segmentation module for segmenting a potential object candidate from a video sequence, a fixed-basis function decomposition module using Haar wavelets to extract a relevant feature set from the potential object candidate, a static classifier for initial classification of the potential object candidate, an incremental learning module for predicting a general class of the potential object candidate, an oriented localized filter module to extract features from the potential object candidate, and a learning-feature graph-fingerprinting module configured to receive the features and build a fingerprint of the object for tracking the object.

Abstract: The present invention provides a system and/or method that facilitates inspecting and/or measuring within manufacturing lines by employing an image retention user interface that displays a failed image from a low end vision system. The image retention user interface can display at least one thumbnail associated to a failed image wherein the failed image can be annotated indicating a failure. Furthermore, the image retention user interface can provide adjustments to equipment related to a low end vision system and/or manufacturing lines. The image retention user interface can also utilize editing techniques to edit failed images. Additionally, the image retention user interface transmits the failed images to a remote system and/or location.

Abstract: The coefficients of a chamfer mask are, to within a multiplicative scale factor making it possible to give them an integer value, approximations of the Euclidian distances separating the pixels covered by the mask, from the pixel under analysis placed at the center of the mask. As there are at least two possible integer values for each coefficient, the over- and the under-approximation, one is rapidly faced with a considerable number of possible combinations. The method proposed allows progressive selection of the possible integer values, firstly at the level of each coefficient by virtue of an axis error rate criterion, then at the level of the coefficients considered by binomials by virtue of a sector error rate criterion, which considerably reduces the number of combinations to be analyzed to arrive at an optimal combination from the point of view of the error rate obtained in the distance estimations.

Abstract: A texture image compressing device includes a separating unit configured to separate intensity maps that include intensity values and light source-independent texture images, those images including color components from a plurality of texture images corresponding to a plurality of different light source directions and a plurality of different viewpoint directions.

Abstract: A method, computer readable medium and apparatus for converting color image resolution include inputting an image enlarging ratio, inputting target pixel data of an image in a first color space to be enlarged in a sequence, sampling reference pixels including the target pixel and pixels at least one of which links to the target pixel, and converting the reference pixel data into a second color space data. Other functions include extracting image feature quantities from the reference pixel data, selecting one of a plurality of pixel multiplying methods according to the extracted image feature quantities, multiplying the target pixel by the selected image multiplying method with an integer value based on the input image enlarging ratio, and outputting pixel data that have been generated by the target pixel multiplying step in a sequence.

Abstract: The present invention provides a computer system and user interface that allows a user to readily view and analyze two-dimensional and three-dimensional in vivo images and imaging data. The user interface is well-suited for one or more of the following actions pertinent to in vivo light imaging: investigation and control of three-dimensional imaging data and reconstruction algorithms; control of topographic reconstruction algorithms; tomographic spectral imaging and analysis; and comparison of two-dimensional or three-dimensional imaging data obtained at different times.

Abstract: At least one kind of control signal concerning control of contents, added to specific locations inside contents data, is detected as first control information, and at the same time, at least one kind of control information concerning control of contents, embedded inside the contents data by a digital watermark, is detected as second control information. Consistency between the first control information as detected, and the second control information as detected is determined and on the basis of results of the determination, the control of the contents is executed. Thus, it is possible to reduce a possibility of the contents being improperly copied, thereby enabling the control with assurance of still higher safety.