Abstract: A search object and m-number of first local features respectively constituted by a feature vector of 1 to i dimensions of local areas of m-number of feature points in an image of the search object are stored, feature points are extracted from the image, second local features respectively constituted by a feature vector of 1 dimension to j dimensions are generated with respect to local areas of n-number of feature points, a smaller number of dimensions among the number of dimensions i of the first local features and the number of dimensions j of the second local features is selected, and an existence of the search object in the image in the video is recognized when a prescribed ratio of the m-number of first local features up to the selected number of dimensions corresponds to the n-number of second local features up to the selected number of dimensions.

Abstract: A device for measuring the characteristic angles and dimensions of wheels, steering system and chassis of vehicles in general, comprising a plurality of three-dimensional optical readers which are functionally connected to a computer and can be arranged peripherally to a vehicle whose dimensions and characteristic angles of wheels, steering system and chassis are to be measured in such a manner that each one frames at least one wheel of the vehicle for the three-dimensional acquisition of an image of the wheel, each three-dimensional optical reader being provided with at least one fixed target for the setting and calibration of the measurement device, at least one camera of each three-dimensional optical reader being arranged in such a manner as to frame clearly and directly at least one fixed target of another three-dimensional optical reader for the setting and calibration of the measurement device by three-dimensional acquisitions of the fixed targets.

Abstract: A video analyzing device according to the present invention specifies an object-related section from video. The object-related section being related to a specific object appearing in the video. The video analyzing device includes an object-related section specifier that specifies a non-detected section as the object-related section when a predetermined condition is satisfied and does not specify the non-detected section as the object-related section when the predetermined condition is not satisfied. The object-detected section is a section in which the specific object is detected. The non-detected section is a section in which the specific object is not detected and which is in a consecutive relation with the object-detected section.

Abstract: Region of interest detection in raw time of flight images is described. For example, a computing device receives at least one raw image captured for a single frame by a time of flight camera. The raw image depicts one or more objects in an environment of the time of flight camera (such as human hands, bodies or any other objects). The raw image is input to a trained region detector and in response one or more regions of interest in the raw image are received. A received region of interest comprises image elements of the raw image which are predicted to depict at least part of one of the objects. A depth computation logic computes depth from the one or more regions of interest of the raw image.

Abstract: Methods and devices are disclosed for aligning a lens assembly and a sensor assembly of an optical system during assembly of the optical system. For example, one method includes positioning the sensor assembly, having at least an image sensor, at the focal plane of the lens assembly and directing light through an alignment optic and lens assembly onto the image sensor. The method further includes producing multiple images from the light received through the lens assembly and alignment optic, the images having multiple alignment features based on the light received through the alignment optic, and the alignment features having multiple sections. The method then measures at least one performance indicator corresponding to each of multiple sections, and adjusts the position of the image sensor based on an optimization of the performance indicators, while the sensor assembly is being attached to the lens assembly.

Abstract: There is provided an image processing apparatus that includes a coefficient setting section, and a processing section. The coefficient setting section is configured to set a filter coefficient based on a correlation value in a color image. The processing section is configured to perform filter processing on a disparity image of the color image for correction of the disparity image, the filter processing being performed using the filter coefficient set by the coefficient setting section.

Abstract: A calculation unit generates a depth image corresponding to a first three-dimensional image with respect to a region of interest and sets a first image region based on a depth gradient of the depth image. The calculation unit moves the origin of a projection line to the near side or far side in the projection line direction by an amount of movement B for a pixel in the first image region, constructs a depth image based on the moved origin of the projection line in the first image region, sets a second image region based on the depth gradient of the depth image based on the moved origin of the projection line in the first image region, sets the second image region as the first image region, and repeats these processes. Once end conditions are satisfied, the calculation unit constructs a second three-dimensional image based on the moved origin of the projection line.

Abstract: A computing system for realizing visual content of an image collection executes feature detection algorithms and semantic reasoning techniques on the images in the collection to elicit a number of different types of visual features of the images. The computing system indexes the visual features and provides technologies for multi-dimensional content-based clustering, searching, and iterative exploration of the image collection using the visual features and/or the visual feature indices.

Abstract: A method for segmenting a mesh, the method may include receiving or generating the mesh, wherein the mesh is a three dimensional surface mesh that represents a three dimensional object and comprises vertexes, edges and faces; finding, by a computerized search module, first edges of the mesh that have an edge angle below an edge angle threshold; wherein each first edge is a border of a pair of faces of the mesh and wherein an edge angle of a first edge is an angle between normals to the pair of faces; finding, by the computerized search module, first vertices of the mesh that have a negative angular defect that is below a negative angular defect threshold and have exactly one neighboring first edge; wherein each first vertex is shared by multiple faces of the mesh; wherein an angular defect of a first vertex is responsive to angles between all pairs of neighboring faces of the edges that share one of the multiple faces; finding, by the computerized search module, second edges of the mesh that link the first ve

Abstract: The present invention describes a method and the system for matching fingerprint images obtained from different fingerprint image capturing devices and implemented in an electronic device. Specifically, the method has steps of identifying minutiae and then identifying core point of the fingerprint images. Thereafter, a line of symmetry is determined and minutiae are identified by matching ridge count, location angle and orientation angle of a first image of the fingerprint images with a second image of the fingerprint images is identified. Thereafter, prominent minutiae from the candidate minutiae having three adjacent minutiae with same local structure are identified. Out of scope minutiae are eliminated by non-linear registration of fingerprint images based on ridge-count and position angle.

Abstract: After selecting two or more image series for comparison, images of the image series are interleaved so that they are alternatively displayed in a comparison pane on a display device. In one embodiment, after one or more image series are selected for comparison, an interleaved image series is created containing each of the images of the one or more selected image series, or, alternatively, the interleaved image series comprises links to the images arranged in the interleaved pattern. If differences exist in the images of the multiple image series, these differences may be more easily detectable as the display device cycles between the images. Comparison of images in an interleaved image series may be more advantageous if the images of each selected image series are of a common anatomical area, common image size, and the images are in the same order.

Abstract: An object-image alignment data generating method for use in an object recognition system is presented. The method obtains a 3D model and a set of 2D images of the object. Each 2D image from the set is captured based on a particular camera point of view. The method then uses the 3D model of the object to generate multiple silhouettes of the object according to different camera point of views. Each silhouette is then matched and aligned with a 2D image based on the corresponding camera point of view. The method also derives at least one descriptor from the 2D images and compiles feature points that correspond to the descriptors. Each feature point includes a 2D location and a 3D location. The method then generates an object-image alignment packet by packaging the 2D images, the descriptors, and the feature points.

Abstract: An electronic device and an image processing method are provided. The method acquires image detailed information of an image, detects an edge region and a texture region from the image detail information, and corrects the image detail information by applying different gain values to image signals corresponding to different regions.

Abstract: An ultrasound imaging system provides for defining a VOI in an ultrasound imaging space. The system defines an initial frame of the VOI in the ultrasound imaging space, receives a selection of at least one reference point at an arbitrary location in the ultrasound imaging space, creates at least one curved surface using at least one element of the initial frame and the at least one reference point, and then creates VOI based on the curved surface in the ultrasound imaging space.

Abstract: Biometric enrollment and verification techniques for ocular-vascular, periocular, and facial regions are described. Periocular image regions can be defined based on the dimensions of an ocular region identified in an image of a facial region. Feature descriptors can be generated for interest points in the ocular and periocular regions using a combination of patterned histogram feature descriptors. Quality metrics for the regions can be determined based on region value scores calculated based on texture surrounding the interest points. A biometric matching process for calculating a match score based on the ocular and periocular regions can progressively include additional periocular regions to obtain a greater match confidence.

Abstract: The present invention provides a biometric notification system for selectively sending messages to interested recipients. In various embodiments, message trigger criteria, interested recipients, and message content may vary depending upon, among other things, the service being provided.

Abstract: A wrist-worn apparatus control with fingerprint data includes a physical activity-related measurement sensor interface, a fingerprint sensor, one or more processors, and one or more memories including computer program code. The one or more memories and the computer program code are configured to, with the one or more processors, cause the apparatus at least to receive fingerprint data from a user with the fingerprint sensor, identify the fingerprint data as matching with one finger of the user on the basis of a comparison between the fingerprint data and reference data of a plurality of fingers of the user stored in the memory, and select a function of a physical activity-related measurement on the basis of the identified finger.

Abstract: A boundary line recognition apparatus receives detection results transmitted from camera devices and a laser radar device performing different optical detection methods. These detection results indicate information regarding a lane boundary line of a vehicle lane on a roadway on which an own vehicle drives. The apparatus further obtains surrounding environmental information of the own vehicle on the roadway, and selects at least one of the camera devices and the laser radar device suitable for correctly recognizing the lane boundary line on the basis of the environmental information. The apparatus finally recognizes the lane boundary line with high accuracy on the basis of the detection result transmitted form one or more devices selected based on the environment information.

Abstract: A method is provided, which comprises generating at least three images of an area of interest from at least one imaging system, the generated images being provided from at least three different angles, establishing point correspondence between the provided images. The method further involves generating at least two sets of three-dimensional information based on the provided images, wherein the at least two sets of three-dimensional information are generated based on at least two different combinations of at least two of the at least three provided images of the area of interest. The method further includes comparing the at least two sets of three-dimensional information so as to determine discrepancies, and providing information related to the imaging system or errors in the images based on the determined discrepancies.

Abstract: Technologies are generally described to identify foreground motion detection in compressed video data. In some examples, a foreground motion detection module may determine transform-coefficient-magnitude sums and motion-vector-magnitude sums associated with block coding units (BCUs) in compressed video data without decompressing the video data. The foreground motion detection module may also determine a background mean and a background co-variance associated with the compressed video data. To determine whether the BCU(s) contain foreground motion, the foreground motion detection module may determine a statistic based on the transform-coefficient-magnitude sums, the motion-vector magnitude sums, the background mean, and the background co-variance and compare the statistic to a threshold.