Abstract: A computer-implemented method for detecting a copy of a reference video, comprises segmenting respective ones of multiple frames of the reference video into multiple regions, determining sets of image features appearing in respective ones of the multiple frames, determining a measure for the relative number of image features for a given region across the multiple frames, generating a spatio-temporal signature for the reference video using the determined measures, and comparing the signature for the reference video against a spatio-temporal signature of a query video to determine a likelihood of a match.

Abstract: Systems and methods are provided for smoothing paths in a graphical interface generated by drawing inputs. One embodiment involves determining a value of a motion attribute associated with a drawing input to a graphical interface. The embodiment also involves modifying a value of a smoothing parameter for a smoothing operation based on the determined value of the motion attribute. The smoothing parameter at least partially determines an amount of smoothing performed by a smoothing operation on input points generated by the drawing input. The embodiment also involves generating a path for rendering in the graphical interface. The path can be generated by applying the smoothing operation to the input points using the determined value of the smoothing parameter.

Abstract: The present invention relates to differential phase-contrast imaging of an object (108). When reconstructing image information from differential phase-contrast image data, streak- like artefacts (502) may occur. The artefacts (502) may substantially reduce legibility of reconstructed image data. Accordingly, it may be beneficial for removing or at least suppressing said artefacts (502). Thus, a method (400) for regularized phase retrieval in phase-contrast imaging is provided comprising receiving (402) differential phase-contrast image data of an object (108); generating (404) reconstructed image data of an object (108) and presenting (406) reconstructed image data of the object (108). The differential phase-contrast image and the reconstructed image data comprise a two-dimensional data structure having a first dimension and a second dimension. Generating reconstructed image data comprises integration of image data in one of the first dimension and the second dimension of the data structure.

Abstract: A coordinate system particular to a subject's tissue, such as a subject's brain, is provided. Furthermore, a system and method for multi-dimensional, interrelated tractography is provided. Images of the subject are acquired that include diffusion information and tracts and/or vectors potentially associated with tracts are determined therefrom. With respect to the coordinate system, this information is used along with an basis that the tracts and/or vectors generally conform to a substantially orthogonal grid, such that white matter tissue fibers are arranged as one of substantially parallel or substantially orthogonal to other fibers. This coordinate system may be provided to a user along with reconstructed images, or may be used to process images. Similarly, in multi-dimensional, interrelated tractography, a new predictive ability and new metrics are provided along with an improved ability to reconstructed or process images.

Abstract: Embodiments of apparatus and methods for voice based user enrollment with video assistance are described. In embodiments, an apparatus may include a face recognition module to identify a user from a first plurality of images and a lip motion detection module to detect the lip motion of the user from a second plurality of images. The apparatus may also include a recording module to activate a recording of the user. The apparatus may further include a user enrollment module, coupled with the recording module and the lip motion detection module, to establish a speaker model of the user based at least in part on the recording and the lip motion of the user. Other embodiments may be described and/or claimed.

Abstract: Methods and apparatuses for tracking and correlating particles include an optical detector that captures a first and a second image of the particles. A video detector is used to capture a plurality of video frames of the particles. The video detector captures the video frames of the particles at a rate faster than the rate at which images are captured by the optical detector to track the movement of particles. A first image position of a particle in the first image of the particles is identified, and then the first image position of the particle is correlated to a second image position of the particle in the second image using the plurality of video frames.

Abstract: A first size adjusting unit adjusts a size of a first clothing image which is an image of a first piece of clothing worn on an upper half of a body based on a width of a shoulder part of the first piece of clothing in the first clothing image. A second size adjusting unit adjusts a size of a second clothing image which is an image of a second piece of clothing worn on a lower half of a body based on a width of a waist part of the second piece of clothing in the second clothing image. A display control unit causes a display to display a screen on which the first piece of clothing and the second piece of clothing are vertically displayed, based on the first clothing image and the second clothing image.

Abstract: The diagnostic vector classification support system and method disclosed herein may both reduce the time and effort required to train radiologists to interpret medical images, and provide a decision support system for trained radiologists who, regardless of training, have the potential to miss relevant findings. In an embodiment, a morphological image is used to identify a zone of interest in a co-registered functional image. An operator's grading of a feature at least partially contained within the zone of interest is compared to one or more computer-generated grades for the feature. Where the operator and computer-generated grades differ, diagnostic support can be provided such as displaying additional images, revising the zone of interest, annotating one or more displayed images, displaying a computer-generated feature grade, among other possibilities disclosed herein.

Abstract: A method for recognizing and locating an object includes an offline mode process and an online mode process. In the offline mode process, plural sampled edge points of a template image of the object and respective gradient angles and a gravity position of the plural sampled edge points are obtained, and plural similarity score tables are obtained according to the plural sampled edge points, a predetermined detecting distance range and a predetermined gradient angle difference range. In the online mode process, plural edge points of a live image and respective gradient angles are obtained, plural predictive gravity positions are calculated, and plural similarity scores corresponding to the plural predictive gravity positions are summed up. The predictive gravity position with the local maximum of the similarity scores higher than a threshold value is correlated with the gravity position of the template image so as to recognize and locate the object.

Abstract: A number of images of an environment may be obtained over time by a number of sensors. The data obtained by the sensors may be used to generate contours of objects in the environment. In some cases, hands with pointing fingers in the environment may be identified based on the contours of the objects in the environment. In particular, contours having a palm segment and a pointing finger segment may be identified as hands with pointing fingers. In an implementation, 1-dimensional curvature and distance information may be used to identify contours having a palm segment and a pointing finger segment.

Abstract: A blurred image having a spatially invariant motion blur resulting from camera motion during image capture is deblurred based on one or more light streaks identified and extracted from the blurred image. A blur kernel for the blurred image is estimated by performing an optimization procedure having a blur kernel constraint based at least in part on the light streak. One or more light streaks can in some embodiments be posed as the blur kernel constraint. A modeled light streak may be defined as a convolution between the blur kernel and a simulated light source, with the optimization procedure being to minimize a distance between the modeled light streak and the corresponding identified light streak from the blurred image.

Abstract: The invention relates to a method for assessing the presence of a watermark in a video wherein the video comprises at least a sequence of frames. The method comprises for at least one frame among one of the sequences of frames the steps of computing a set of axial cross-correlation values, wherein each axial cross-correlation value corresponds to a correlation between the frame and a reference watermark shifted along a spatial horizontal axis; obtaining a detection score by computing a weighted sum of values output by a function applied to said axial cross-correlation values; assessing the presence of a watermark according to the detection score. Such method is particularly well adapted to the detection of disparity coherent watermark but is compliant with any watermarking technique. A device implementing the method is further disclosed.

Abstract: The present invention includes an automated method for grading the blurring of ocular fundus images to permit automated grading of severity of vitritis. Standard fundoscopic images are converted to gray-scale images. The gray-scale images are processed through a low-pass filter to eliminate high frequency components. The low pass image is subtracted from the corresponding original image, producing the difference image. The difference image is converted to the final entropy image. The entropy image is processed using Fast Fourier Transform to calculate its power. The final blur score is calculated.

Abstract: A method using optical coherence tomography to capture the microvascular network of the superficial layer of the finger skin for the purpose of fingerprint authentication and liveness detection. At the dermal papilla region, the vascular pattern follows the same pattern of the fingerprint and this vascular pattern forms a live vascular fingerprint. This live vascular fingerprint provides for ultrahigh security and a unique way for fingerprint-based personal verification. Because the system is based on blood flow, which only exists in a living person, the technique is robust against spoof attaching. After performing non-contact in-vivo imaging of a human fingertip, a three dimensional vasculature image is reconstructed from a plurality of vasculature tomography images and at least one vasculature fingerprint image which corresponds to the fingertip is extracted from the three dimensional vasculature image.

Abstract: Disclosed are various embodiments for controlling access to resources by a client device. Methods may include receiving a user request to access a resource on the device and determining whether the resource requires a facial capture. If the resource requires a facial capture, a camera of the device may be automatically activated to capture an image and the resource may be rendered on the device. In some cases, access to the resource may be limited based on whether the image includes a face or not. A record associating the image and the requested resource may be stored, for example, on the device or on a remote server.

Abstract: A method for sending a screen image by a computing device is described. A modification image representing a modified region of the screen image is determined. The modification image has a lossless format. Location information is encoded in one or more alpha channels of the modification image. The modification image is sent.

Abstract: Systems and methods are disclosed for integrating imaging data from multiple sources to create a single, accurate model of a patient's anatomy. One method includes receiving a representation of a target object for modeling; determining one or more first anatomical parameters of the target anatomical object from at least one of one or more first images of the target anatomical object; determining one or more second anatomical parameters of the target anatomical object from at least one of one or more second images of the target anatomical object; updating the one or more first anatomical parameters based at least on the one or more second anatomical parameters; and generating a model of the target anatomical object based on the updated first anatomical parameters.

Abstract: The present invention relates to a method of processing seismic image of the subsurface. The method comprises determining two surfaces in the seismic image, the two surfaces being extracted from well data from at least on well in the subsurface; determining the dip components the first surface and the second surface; determining interpolated dip components based on dip components of the two surfaces; determining an interpolated surface based on at least the interpolated dip components; determining a density value based on a number of intersections of the determined surfaces with a column comprising said current pixel; determining a geological-time image, columns of said geological-time image are computed based on the density values of pixels of a corresponding column of the seismic image; and on the color value of pixels of the corresponding column of the seismic image.

Abstract: Disclosed are a system and a method for compositing various images that minimize a brightness difference in connection areas of various images by using a clustering technique at the time of compositing various images. The method for compositing various images may include receiving two or more input images; compositing the two or more input images into one composite image; calculating a brightness distribution degree; calculating representative brightness values; determining clustering; calculating a correction target value; and calculating a correction value of an increase/decrease curve.

Abstract: A counterfeit identification performance attribute (CIPA) sensitivity to changes in resolution of the image for features of an image is determined (102). The CIPA sensitivity for the features is used to choose at least one feature to determine whether the image on a sample is a counterfeit (106).