Abstract: Methods and apparatuses for performing biometric determinations using optical spectroscopy of tissue. The biometric determinations that are disclosed include determination or verifications of identity, estimation of age, estimation of sex, determination of sample liveness and sample authenticity. The apparatuses disclosed are based upon discrete light sources such as light emitting diodes, laser diodes, vertical cavity surface emitting lasers, and broadband sources with multiple narrow-band optical filters. The multiple light sources are encoded in a manner that the tissue response for each source can be efficiently measured. The light sources are spaced at multiple distances from a detector to contribute differing information to the biometric determination task as do light sources with different wavelength characteristics.

Abstract: A computing device segments an image into a plurality of segments, wherein each segment of the plurality of segments has a segment location and a set of pixels that share visual characteristics. The computing device determines an initial set of bounding boxes for the image based on the plurality of segments. The computing device determines a reduced set of bounding boxes based on combining bounding boxes of the initial set of bounding boxes, the reduced set of bounding boxes corresponding to one or more objects in the image, each of the one or more objects having an object class and an object location.

Abstract: Based on a long diameter of a set specific region, a first region estimated as the specific region and a second region estimated as a background region are set within an input image. Based on a density histogram of each pixel in the first region and a density histogram of each pixel in the second region, a first evaluation value which indicates a likelihood that a density value represents the specific region is calculated for each density value. For each pair of two adjacent pixels within the input image, based on the first evaluation values, a second evaluation value which indicates a likelihood that the two adjacent pixels represent a contour is calculated. Based on the second evaluation value, connection costs between a plurality of nodes respectively representing each pair of the two adjacent pixels are set. The plurality of nodes are connected based on the connection costs.

Abstract: An image recognizing apparatus comprises: an extracting unit extracting a partial feature quantity from an object in each of a registration image and an input image; a compressing unit reducing a dimension of the extracted partial feature quantity; a storing unit storing the partial feature quantity of the object in the registration image of which the dimension has been reduced; and a calculating unit calculating similarity between the object in the input image and the object in the registration image, using the partial feature quantity of the object in the input image of which the dimension has been reduced and the partial feature quantity of the object in the stored registration image. The compressing unit switches the reduction of the dimension of the partial feature quantity using a preset dimension compression parameter and the reduction of the dimension of the partial feature quantity by dynamically generating a dimension compression parameter.

Abstract: A solder print inspecting device includes three-dimensional measurement lighting unit that directs a specific light at a printed substrate, a CCD camera for imaging the printed substrate that is illuminated by the light, three-dimensional calculating unit that performs a three-dimensional measurement of cream solder based on image data, etc., and displaying unit that displays a three-dimensional image showing a three-dimensional shape of the cream solder, along with displaying an arrow image showing an operating direction of a squeegee in a solder printing machine, an arrow image showing a conveying direction of the printed substrate, etc.

Abstract: A feeling monitoring system includes a facial image acquisition portion, a feeling information acquisition section, and a feeling display generation section. The facial image acquisition portion is capable of acquiring a facial image of an occupant individually sitting in each seating position of two or more seating positions in a vehicle. The feeling information acquisition section acquires feeling information representing the feeling of the occupant based on the facial image acquired from the facial image acquisition portion. The feeling display generation section generates a feeling display corresponding to the feeling information acquired by the feeling information acquisition section.

Abstract: A three-dimensional image processing apparatus which obtains a three-dimensional image from a plurality of images from different projection views of a patient which have been obtained by carrying out multiple imaging while rotating around the patient, includes a locating unit to specify a point of one of the plurality of images from different projection views. A searching unit searches a point corresponding to the specified point in the plurality of images from different projection views, on the basis of the specified point. A reconstruction region identification unit identifies a region of a part of a region which can be reconstructed, as a reconstruction region by using the specified point and the searched point. A reconstruction unit obtains a three-dimensional image by reconstructing an image in the identified reconstruction region.

Abstract: Methods, systems and apparatus for refining image relevance models. In general, one aspect includes receiving a trained image relevance model that generates relevance measures of content feature values of images to a query, identifying a first threshold number of common content feature values for the set of training images, the common content feature values being identified as a set of content feature values that are each shared by at least a portion of the training images, identifying a subset of the set of training images having a quantity of the common content feature values greater than a second threshold number of content features values, and generating a re-trained image relevance model based on content feature values of the set of training images, wherein content feature values of the subset of training images are weighted higher than content feature values of the training images not in the subset.

Abstract: An estimator training method and a pose estimating method using a depth image are disclosed, in which the estimator training method may train an estimator configured to estimate a pose of an object, based on an association between synthetic data and real data, and the pose estimating method may estimate the pose of the object using the trained estimator.

Abstract: To make it possible to significantly reduce a burden on a user at a time of a classification of image files added or updated, for example, and thus facilitate association with other content data. An image detector/register (20) detects an image file that is unregistered or updated, and structures and manages a list of the image files. A face rectangular detector (21) detects a face rectangle in the image files detected, associates information on the face rectangle with the image file, and stores the information. A similar face classification section (22) calculates an amount of feature of the face rectangle, compares the amount of feature calculated with amounts of feature of different face rectangles already calculated and classified into groups, calculates a similarity between the face rectangle and the face rectangles of the different face rectangles in the respective groups, and classifies and manages the face rectangles in accordance with a result of the similarity calculation.

Abstract: Propagating object selection across multiple images is described. In one or more embodiments, an object is selected from a first image according to selection inputs. Features that are representative of the selected object are then ascertained. To propagate selection of the object to the second image, a determination is made as to whether the second image includes features that resemble those ascertained from the first image. Once a determination is made as to the features of the second image that resemble the features of the first image, the second image is divided into regions. Each of the regions includes pixels that are similar within the region, one pixel to another. The regions of the second image that include the features resembling those ascertained from the first image are then combined. The combined regions are used to select the object from the second image without receiving selection inputs to do so.

Abstract: Systems and methods are provided for data reconstruction. In accordance with one aspect, data interpolation is performed on a time-varying three-dimensional (3D) image dataset of one or more vessel-like structures to generate at least one interpolated voxel value. The interpolated voxel value is used to correct at least one value of a vessel voxel representing the one or more vessel-like structures in the time-varying 3D dataset.

Abstract: This disclosure provides techniques for assessing quality of a deposited film layer of an organic light emitting diode (“OLED”) device. An image is captured and filtered to identify a deposited layer that is to be analyzed. Image data representing this layer can be optionally converted to brightness (grayscale) data. A gradient function is then applied to emphasize discontinuities in the deposited layer. Discontinuities are then compared to one or more thresholds and used to ascertain quality of the deposited layer, with optional remedial measures then being applied. The disclosed techniques can be applied in situ, to quickly identify potential defects such as delamination before ensuing manufacturing steps are applied. In optional embodiments, remedial measures can be taken dependent on whether defects are determined to exist.

Abstract: An ultrasound diagnosis apparatus according to an embodiment includes a decomposing unit, a diffusion filter unit, an adjusting unit, and a reconstructing unit. The decomposing unit decomposes ultrasound image data into low-frequency and high-frequency decomposed image data at each of a predetermined number of levels, by a multi-resolution analysis. The diffusion filter unit applies a diffusion filter to the low-frequency and high-frequency decomposed image data at the lowest level and applies, at each of the levels other than the lowest, a diffusion filter to data output from the level immediately underneath and to the high-frequency decomposed image data, and also generates edge information for each of the levels. The adjusting unit adjusts a signal level of the high-frequency decomposed image data for each of the levels, based on the edge information. The reconstructing unit obtains corrected data of the ultrasound image data by performing a multi-resolution synthesis.

Abstract: Methods, systems, and apparatus, including computer program products, for ranking search results for queries. The method includes calculating a visual similarity score for one or more pairs of images in a plurality of images based on visual features of images in each of the one or more pairs; building a graph of images by linking each of one or more images in the plurality of images to one or more nearest neighbor images based on the visual similarity scores; associating a respective score with each of one or more images in the graph based on data indicative of user behavior relative to the image as a search result for a query; and determining a new score for each of one or more images in the graph based on the respective score of the image, and the respective scores of one or more nearest neighbors to the image.

Abstract: A method for automatically tracking multiple objects from a sequence of video images that may extract raw data about participating elements in a sporting, or other event, in a way that does not interfere with the actual participating elements in the event. The raw data may include the position and velocity of the players, the referees, and the puck, as well as the team affiliation of the players. These data may be collected in real time and may include accounting for players moving fast and unpredictably, colliding with and occluding each other, and getting in and out of the playing field. The video sequence, captured by a suitable sensor, may be processed by a suitably programmed general purpose computing device.

Abstract: An example is an image processing method including a step of acquiring data containing an image, an extraction step of extracting a first image region from the acquired data based on the type of software for generating the acquired data, an extraction step of extracting a second image region the same as or similar to each of images held in a storage unit from the acquired data by comparing the acquired data and each of the images, an extraction step of extracting a third image region the same as or similar to each of the images from the acquired data by comparing the image feature amount of the acquired data and the image feature amount of each of the images, and a step of identifying an image in the acquired data to be stored in the storage unit based on the image regions and reliabilities of the extraction steps.

Abstract: Apparatus and methods for inspecting a photolithographic reticle are disclosed. A reticle inspection tool is used at one or more operating modes to obtain images of a plurality of training regions of a reticle, and the training regions are identified as defect-free. Three or more basis training images are derived from the images of the training regions. A classifier is formed based on the three or more basis training images. The inspection system is used at the one or more operating modes to obtain images of a plurality of test regions of a reticle. Three or more basis test images are derived from to the test regions. The classifier is applied to the three or more basis test images to find defects in the test regions.

Abstract: A fingerprint minutia display input device includes: an image output controller for displaying a fingerprint image and a pointer for designating a minutia; and a minutia input setting unit for displaying a minutia display mark on the minutia; wherein the fingerprint minutia display input device includes a gray-scale value adjustment unit for setting the gray-scale intensity of the entire fingerprint image on which the pointer is positioned, the setting being performed within a range of a display gray-scale width constituted with upper-limit and lower-limit gray-scale values. The screen output controller includes a gray-scale width update function for displaying an updated output display of the fingerprint image in the set display gray-scale width, and a gray-scale width fixing/holding function for fixedly holding the set display gray-scale width as a set display gray-scale width for the minutia display input when there is no new setting information regarding the display gray-scale width.

Abstract: Apparatus, systems, and methods fusing material classification with spatio-spectral edge detection in spectral imagery can be used in a variety of applications. In various embodiments, a classifier can be applied to neighboring pixels in data for an image to determine, based on material changes, if the neighboring pixels are correlated to two different materials with respect to a candidate location for an edge. Results of the classification can be used with a spatio-spectral mask to accept or reject the candidate location as an edge. Additional apparatus, systems, and methods are disclosed.