Abstract: A computer system that execute a method to stitch satellite images into a wide-angle image. The method includes dividing each of the satellite images into plural subimages, determining whether the subimages include an overlap area that overlaps with adjacent subimages, obtaining cropped subimages by removing the overlap area from the subimages, generating preprocessed satellite images each including the cropped subimages, selecting a reference image and a target image from the preprocessed satellite images, determining plural correspondent pairs in an overlap region between the reference and target images based on a feature matching algorithm, obtaining a transformation matrix by a least-squares algorithm and based on coordinates of the correspondent pairs, obtaining calibrated coordinates for each pixel of the target image by applying the transformation matrix, and stitching the target images into the wide-angle image based on the calibrated coordinates of the target image.

Abstract: In a fingerprint data registering method, a blurred pseudo image is displayed and, when a fingerprint image for authentication registration is acquired, a fingerprint position of the acquired fingerprint image is extracted. A position in the pseudo image, which corresponds to the extracted fingerprint position, is determined. A part of the blurred pseudo image at the determined corresponding position is converted to a clear partial pseudo-image having a higher resolution than that of the blurred pseudo image and the clear partial pseudo-image is displayed. The acquired fingerprint image is registered as an authentication-purpose fingerprint image in association with the converting and outputting process.

Abstract: A computer-implemented system and method for cluster spine group arrangement is provided. A set of spine groups each having one or more spines of clusters and at least one singleton cluster is obtained. Unique spine groups are identified within the set and placed in a center of a display. At least a portion of the remaining spine groups in the set are placed to extend radially from the unique spine groups in the display center.

Abstract: A method and apparatus for providing authentication using an adaptive liquid lens are disclosed. For example, in one embodiment, the method receives a request for authentication from a mobile endpoint device of a user, wherein the request comprises a first retinal image of the user captured using an adaptive liquid lens of the mobile endpoint device. The method obtains a second retinal image of the user, wherein the second retinal image is a stored retinal image of the user. The method authenticates the first retinal image against the second retinal image. In another embodiment, the method captures a first retinal image of a user via a mobile endpoint device of the user, wherein the mobile endpoint device comprises an adaptive liquid lens. The method then sends a request for authentication from the mobile endpoint device over a network, wherein the request comprises the first retinal image.

Abstract: An image comparison device includes: a storage in which a model image is stored, the model image including a position of a feature point of a comparison object and a luminance gradient direction at the position of the feature point; a feature amount acquisition unit configured to acquire the position of the feature point and the luminance gradient direction at the position of the feature point from an input image; and an image comparison unit configured to compare the model image and the input image. The image comparison unit performs image comparison by providing an allowable range in both the position of the feature point and the luminance gradient direction at the position of the feature point position.

Abstract: Embodiments of the present invention are directed to optimizing image cropping. In accordance with some embodiments of the present invention, an image and an indication of an area of interest within the image are obtained. Thereafter, an amount to scale the image is determined based on a size of a container into which the image is to be placed for display. The amount to scale the image is greater for containers of a smaller size to focus on the area of interest within the image than the amount to scale the image for containers of a larger size. The image can be scaled in accordance with the determined amount to scale the image, and thereafter cropped to fit within the boundaries of the container.

Abstract: A fingerprint image acquisition device includes: a light source, a finger touching surface, a convex lens, an image sensor and a grating. The light source is a surface light source, and the grating is disposed on a light output surface of the light source. The light source is configured to emit a light beam, the grating is configured to change a propagation direction of the light beam to form a detection light beam, the finger touching surface is configured for a user to place a finger thereon to reflect the detection light beam and thereby obtain a reflected light beam, the convex lens is configured to focus the reflected light beam on the image sensor, and the image sensor is configured to generate a fingerprint image based on the focused reflected light beam. Accordingly, the invention can make the structure of the fingerprint image acquisition device be more compact.

Abstract: The inventive concepts provide a method for inspecting a pattern, a method for manufacturing a semiconductor device, and an apparatus used according to the methods. The method for inspecting a pattern includes detecting a measured image corresponding to a pattern formed on a substrate, detecting a first hot spot corresponding to a ghost image of the measured image, with the first hot spot representing a defect of the pattern, and detecting a second hot spot that has an area that is wider than that of the first hot spot.

Abstract: At least one example embodiment discloses a method of converting a vector corresponding to an input image. The method includes receiving first-dimensional vector data associated with an input image, the input image including an object and converting the received first-dimensional vector data to second-dimensional vector data based on a projection matrix with an associated rank. A first dimension of the first-dimensional vector data is higher than a second dimension of the second-dimensional vector data.

Abstract: The present disclosure relates to processing images representing a real scene, the images comprising at least two images obtained from at least two sources of images, a sub-image of each of the at least two images representing an overlapping area of the real scene. A role map comprising a plurality of parts, all the points of each part of the role map being associated with a single identifier of a source of images, is generated during a training phase. To process the images, parts of the role map are selected as a function of an identifier of a considered source of images, and sub-images of an image obtained from the considered source of images are processed, the processed sub-images corresponding to the selected parts of the role map.

Abstract: This disclosure relates generally to correlation filters, and more particularly to designing of correlation filter. In one embodiment, a system for designing a correlation filter in a multi-processor system includes a multi-core processor coupled to a first memory and one or more co-processors coupled to one or more respective second memories. The multi-core processor partitions each of a plurality of frames associated with media content into a plurality of pixel-columns, and systematically stores said pixel-columns width-wise in a plurality of temporary matrices by a plurality of threads of the multi-core processor. The plurality of temporary matrices are transferred by the multi-core processor to one or more respective second memories in a plurality of streams simultaneously in an asynchronous mode. A plurality of filter harmonics of the correlation filter are computed by performing compute operations involving at least the plurality of temporary matrices, to obtain the correlation filter.

Abstract: A method of generating a reliable image of an iris for subsequent optical analysis leading to identification or authentication of a mammal. The method comprises directing point light sources towards the iris, capturing a gray scale image of the iris and reflections of the point light sources, deriving a two tone image from the gray scale image, generating an image containing the true boundaries of the pupil, determining boundaries of the iris and generating an image containing the true boundaries of the iris, and generating a final image of the iris from the image containing the true boundaries of the iris. This establishes a reliable image of the iris. The process may further comprise conducting an identification or authentication process based on optical analysis of the final image of the iris and comparison with a pre-established data corresponding to a person whose identity has been confirmed.

Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.

Abstract: According to an embodiment, an image processing apparatus includes an interface that receives a first image and a second image. A processor extracts a first character string appearing on the first image, and a second character string appearing on the second image. The processor determines that both the first character string and the second character string correspond to a photographed subject in the first image and second image. The processor cuts out each of the characters constituting the first character string, in units of a character. The processor cuts out each of the characters constituting the second character string, in units of a character. The processor calculates a first similarity degree group and a second similarity degree group. The processor recognizes a character string of the subject, based on the first similarity degree group and the second similarity degree group.

Abstract: A computer program product includes program instructions configured to cause a processor, to: perform optical character recognition (OCR) on an image of a document; extract an identifier of the document from the image based at least in part on the OCR; compare at least portions of the identifier with content from one or more reference data sources; and determine whether the identifier is valid based at least in part on the comparison. The content comprises global address information; while the content from the reference is derived from geographic information. Deriving the content from the geographic information includes: obtaining the geographic information; and parsing the geographic information according to a set of predefined heuristic rules, where the heuristic rules are configured to normalize the global address information obtained from the one or more sources according to a single convention for representing address information.

Abstract: A method for cropping photos images captured by a user from an image of a page of a photo album is described. Corners in the page image are detected using corner detection algorithm or by detecting intersections of line-segments (and their extensions) in the image using edge, corner, or line detection techniques. Pairs of the detected corners are used to define all potential quads, which are then are qualified according to various criteria. A correlation matrix is generated for each potential pair of the qualified quads, and candidate quads are selected based on the Eigenvector of the correlation matrix. The content of the selected quads is checked using a salience map that may be based on a trained neuron network, and the resulting photos images are extracted as individual files for further handling or manipulation by the user.

Abstract: This invention decodes image data without overwriting the decompression result of the first image data by that of the second image data when the first image data compressed by the first method and the second image data compressed by the second method coexist. To do this, when decoding the image data in which the first image data compressed by the first method and the second image data compressed by the second method different from the first method coexist, a lossy-decoding unit decodes the first image data. Based on boundary information indicating a compression region compressed by the second method, a lossless-decoding unit selectively outputs pixel data decoded by the lossy-decoding unit or pixel data obtained by decoding the second image data of the compression region.

Abstract: An image correction apparatus generates, for each pixel of a reduced image generated from an input image, a first smoothed image using each reference pixel in a filter area in which a difference obtained by subtracting a luminance value of the pixel from a luminance value of the reference pixel becomes less than a predetermined value, generates a second smoothed image using each reference pixel in the filter area in which the difference obtained by subtracting the luminance value of the reference pixel from the luminance value of the pixel becomes less than the predetermined value, and generates a smoothed image for correction of the input image based on the first smoothed image and the second smoothed image.

Abstract: A method of extracting a static pattern from an output of an event-based sensor. The method may include receiving an event signal from the event-based sensor in response to dynamic input, and extracting a static pattern associated with the dynamic input based on an identifier and time included in the event signal. The static pattern may be extracted from a map generated based on the identifier and time.

Abstract: A device (1) for determining image quality of a radiogram image includes: an acquiring module (10), which is configured to acquire the radiogram image; a segmentation module (20), which is configured to segment a thoracic bone structure on the acquired radiogram image into segmented thoracic bone structure contours and a tissue structure on the acquired radiogram image into segmented tissue structure contours; and a quality-determination module (30), which is configured to determine a image quality coefficient for the acquired radiogram image based on a comparison of a first position of the segmented thoracic bone structure contours with a second position of the segmented tissue structure contours.