Abstract: Image labeling is described, for example, to recognize body organs in a medical image, to label body parts in a depth image of a game player, to label objects in a video of a scene. In various embodiments an automated classifier uses geodesic features of an image, and optionally other types of features, to semantically segment an image. For example, the geodesic features relate to a distance between image elements, the distance taking into account information about image content between the image elements. In some examples the automated classifier is an entangled random decision forest in which data accumulated at earlier tree levels is used to make decisions at later tree levels. In some examples the automated classifier has auto-context by comprising two or more random decision forests. In various examples parallel processing and look up procedures are used.

Abstract: A system and method for restricting the number of layout patterns by pattern identification, matching and classification, includes decomposing the pattern windows into a low frequency component and a high frequency component using a wavelet analysis for an integrated circuit layout having a plurality of pattern windows. Using the low frequency component as an approximation, a plurality of moments is computed for each pattern window. The pattern windows are classified using a distance computation for respective moments of the pattern windows by comparing the distance computation to an error value to determine similarities between the pattern windows.

Abstract: A method and apparatus for measuring a distance to an object using a device (100) having at least two cameras (104, 106) is described. One or more first images including the object are acquired by a first camera of the device and one or more first reference images are acquired by a second camera of the device, while the device is in a first position. One or more second images including the object and one or more second reference images are acquired by cameras of the device, while the device is in a second position, different from the first position. Based on the first and second reference images, information of the displacement of at least one camera of the device between the first and second positions are determined. The distance from the device to the object is calculated based on the first and second images including the object and the determined information on the displacement of the at least one camera.

Abstract: A vehicular image processing system and a vehicular image processing apparatus are provided which combine an image from a photographing device for detection of an object forward of a vehicle and an image from a photographing device for parking assistance, thereby enabling detection, in a synthesized image, of an obstacle of which the entirety cannot be captured by each photographing device since the object is located in a region where detection is difficult in the conventional art, for example, the object is located at a short distance from the own-vehicle.

Abstract: A method of determining the identity of a subject while the subject is walking or being transported in an essentially straight direction is disclosed, the two dimensional profile of the subject walking or being transported along forming a three dimensional swept volume, without requiring the subject to change direction to avoid any part of the system, comprising acquiring data related to one or more biometrics of the subject with the camera(s), processing the acquired biometrics data, and determining if the acquired biometric data match corresponding biometric data stored in the system, positioning camera(s) and strobed or scanned infrared illuminator(s) above, next to, or below the swept volume. A system for carrying out the method is also disclosed.

Abstract: A method of determining the identity of a subject while the subject is walking or being transported in an essentially straight direction is disclosed, the two dimensional profile of the subject walking or being transported along forming a three dimensional swept volume, without requiring the subject to change direction to avoid any part of the system, comprising acquiring data related to one or more biometrics of the subject with the camera(s), processing the acquired biometrics data, and determining if the acquired biometric data match corresponding biometric data stored in the system, positioning camera(s) and strobed or scanned infrared illuminator(s) above, next to, or below the swept volume. A system for carrying out the method is also disclosed.

Abstract: A disclosed image processing apparatus detects a motion vector between a first image and a second image based on the correlation between the first image and the second image. When the degree of reliability of the detected motion vector is determined based on an evaluation value regarding the correlation, a difference in amount of bokeh between the first image and the second image is considered to improve accuracy of the degree of reliability of the motion vector.

Abstract: Accurate localization of isolated particles is important in single particle based super-resolution microscopy. It allows the imaging of biological samples with nanometer-scale resolution using a simple fluorescence microscopy setup. Nevertheless, conventional techniques for localizing single particles can take minutes to hours of computation time because they require up to a million localizations to form an image. In contrast, the present particle localization techniques use wavelet-based image decomposition and image segmentation to achieve nanometer-scale resolution in two dimensions within seconds to minutes. This two-dimensional localization can be augmented with localization in a third dimension based on a fit to the imaging system's point-spread function (PSF), which may be asymmetric along the optical axis. For an astigmatic imaging system, the PSF is an ellipse whose eccentricity and orientation varies along the optical axis.

Abstract: In one aspect, a method of detecting at least on feature associated with a blood vessel in at least one image of at least one blood vessel using a matched filter adapted to respond to the at least one feature is provided. The method comprises applying a scale detection filter to selected voxels in the at least one image to determine a scale for the matched filter at each of the selected voxels, determining an orientation for the matched filter at each of the selected voxels, wherein determining the orientation is assisted by using the scale determined at each of the selected voxels, applying the matched filter at each of the selected voxels at the scale and the orientation determined at each of the selected voxels to obtain a filter response at each of the selected voxels, and analyzing the filter response at each of the selected voxels to determine if the respective voxel corresponds to the at least one feature.

Abstract: System, processes and devices for monitoring betting activities using bet recognition devices and a server. Each bet recognition device has an imaging component for capturing image data for a gaming table surface. The bet recognition device receives calibration data for calibrating the bet recognition device. A server processor coupled to a data store processes the image data received from the bet recognition devices over the network to detect, for each betting area, a number of chips and a final bet value for the chips.

Abstract: The present invention discloses apparatuses and methods for simultaneous viewing and reading top and bottom images from a workpiece. The present ID reader can comprise an enclosure covering a top and bottom section of the workpiece with optical elements to guide the light from the workpiece images to a camera. The optical element can be disposed to receive images from a high angle with respect to the surface of the workpiece. The present ID reader can further comprise a light source assembly to illuminate the image. The light source assembly can utilize a coaxial light path with the images, preferably for bright field illumination. The light source assembly can also utilize a non-coaxial light path, preferably for dark field illumination.

Abstract: This application is directed to dynamic control for data capture. A device may comprise a capture logic module to receive at least one of biometric data from a biometric sensing module, context data from a context sensing module or content data from a content sensing module. The capture logic module may determine if a capture scenario exists based on at least one of the biometric data and context data. The determination may be weighted based on an operational mode. If a capture scenario is determined to exist, the capture logic module may then determine whether to capture data based on at least the content data. Captured data may be stored in a capture database in the device (e.g., along with enhanced metadata based on at least one of the biometric data, the context data or the content data). The device may also comprise a feedback database including feedback data.

Abstract: A method and apparatus for tracking an object, and a method and apparatus for calculating object pose information are provided. The method of tracking the object obtains object feature point candidates by using a difference between pixel values of neighboring frames. A template matching process is performed in a predetermined region having the object feature point candidates as the center. Accordingly, it is possible to reduce a processing time needed for the template matching process. The method of tracking the object is robust in terms of sudden changes in lighting and partial occlusion. In addition, it is possible to track the object in real time. In addition, since the pose of the object, the pattern of the object, and the occlusion of the object are determined, detailed information on action patterns of the object can be obtained in real time.

Abstract: Methods, systems, and products index digital scenes in digital media. A uniform resource locator is assigned to each different digital scene within the digital media. The uniform resource locator uniquely identifies a resource from which each different digital scene may be retrieved. Individual scenes may thus be retrieved, thus conserving bandwidth and memory.

Abstract: Aspects of the disclosure relate to detecting vehicle movement. For example, one or more computing devices may receive first image data representative of a vehicle's wheel and second image data representative of the wheel captured subsequent to the capture of the first image data. The one or more computing devices may determine a first location of a first portion of the wheel based on the first image data, and a second location of the first portion of the wheel based on the second image data. The one or more computing devices may calculate a value based on the angular distance between the first location and the second location of the first portion, and based on the value, determine whether the vehicle is in motion. Upon determining the vehicle is in motion the one or more computing devices may provide a signal that the vehicle is in motion.

Abstract: Systems and methods for correcting errors in a depth map generated by a structured light system are disclosed. In one aspect, a method includes dividing a depth map into segments and calculating a density distribution of the depth values for each segment. The method includes detecting error (or “outlier”) values by determining the depth values that fall outside of a range of depth values, the range of depth values representative of the highest density depth values for a given segment. The method includes detecting error values in the depth map as a whole based on the density distribution values for each segment.

Abstract: A method of determining the identity of a subject while the subject is walking or being transported in an essentially straight direction is disclosed, the two dimensional profile of the subject walking or being transported along forming a three dimensional swept volume, without requiring the subject to change direction to avoid any part of the system, comprising acquiring data related to one or more biometrics of the subject with the camera(s), processing the acquired biometrics data, and determining if the acquired biometric data match corresponding biometric data stored in the system, positioning camera(s) and strobed or scanned infrared illuminator(s) above, next to, or below the swept volume. A system for carrying out the method is also disclosed.

Abstract: Techniques and tools for high dynamic range (HDR) image rendering and generation. An HDR image generating system performs motion analysis on a set of lower dynamic range (LDR) images and derives relative exposure levels for the images based on information obtained in the motion analysis. These relative exposure levels are used when integrating the LDR images to form an HDR image. An HDR image rendering system tone maps sample values in an HDR image to a respective lower dynamic range value, and calculates local contrast values. Residual signals are derived based on local contrast, and sample values for an LDR image are calculated based on the tone-mapped sample values and the residual signals. User preference information can be used during various stages of HDR image generation or rendering.

Abstract: Currency bills are transported past an image scanner to one or more output receptacles. Each of the bills is imaged to produce image data from which a visually readable image of each bill can be reproduced. The serial number, denomination, and/or secondary identifiers of a bill is attempted to be extracted and/or determined from the image data associated with the bill. The serial number of the bill has an integer number, X, of characters. One or more of the X characters of the serial number of the currency bill is not extracted with a predetermined confidence. In response to failing to extract all of the X characters of the serial number of the bill with the predetermined confidence, a serial number field in an electronic record associated with the bill is populated with a serial number snippet image. The electronic record is stored in a non-transitory memory.

Abstract: Currency bills are transported past an image scanner to one or more output receptacles. Each of the bills is imaged to produce image data from which a visually readable image of each bill can be reproduced. The serial number, denomination, and/or secondary identifiers of a bill is attempted to be extracted and/or determined from the image data associated with the bill. The serial number of the bill has an integer number, X, of characters. One or more of the X characters of the serial number of the currency bill is not extracted with a predetermined confidence. In response to failing to extract all of the X characters of the serial number of the bill with the predetermined confidence, a serial number field in an electronic record associated with the bill is populated with a serial number snippet image. The electronic record is stored in a non-transitory memory.