Abstract: A system and method for expansion and reduction of images may apply resizing techniques independently to different regions of an input image to produce a resized version of the image having a specified target size and/or ratio. A content-aware resizing technique may be applied to some regions of the image. Each region may be reduced or expanded by the same amount based on local content, or different regions may be resized by different amounts to meet a resizing target for the input image. The same resizing technique may be applied to each region, or different resizing techniques may be applied to different regions. A given region or unselected portion of the image may not be resized at all. The techniques may be implemented by program instructions of an image editing application, and the definition of the regions and/or the selection of locally applied techniques may be configurable by a user.

Abstract: A method resizes input images by first constructing a grid graph. The grid graph includes one node for each pixel in the input image, and adjacent nodes in the grid graph are connected by arcs. Each arc is directed and has an associated cost. A cut is applied to the arcs of the grid graph using a cost function. A seam of pixels is determined from the cut so that coordinates of the pixels in the seam enforce monotonicity and connectivity constraints. Then, the input image is resized according to the seam to produce an output image while minimizing a change of energy in the output image when compared with the input image.

Abstract: A computer implemented method tracks 3D positions of an object moving in a scene. A sequence of images is acquired of the scene with a set of cameras such that each time instant a set of images are acquired of the scene, in which each image includes pixels. Each set of images is aggregated into a synthetic aperture image including the pixels, and the pixels in each the set of images are matched corresponding to multiple locations and multiple depths of a target window with an appearance model to determine scores for the multiple locations and multiple depths. A particular location and a particular depth having a maximal score is selected as the 3D position of the moving object.

Abstract: A method for content-aware image retargeting generates an energy image from a source image according to an energy function. From the energy image, one or more seams are determined according to a minimizing function such that each seam has a minimal energy. Each seam is applied to the source image to obtain a target image that preserves content and a rectangular shape of the source image.

Abstract: A computer implemented method classifies securely a private query sample using exact k-nn classification. A secure dot product protocol is applied to determine securely distances between a private query sample and a plurality of private labeled samples. A secure k-rank protocol is applied to the distances to determine a nearest distance of a kth nearest labeled sample having a particular label. Then, a secure Parzen protocol is applied to the nearest distance to label the private query sample according to the particular label.

Abstract: A system and method for expansion and reduction of images uses an absolute value associated with each pixel of an input image (e.g., a color and/or intensity value) to determine a respective energy value for each pixel. For example, a given color or range of colors (e.g., skin tones, or other high-priority colors) may be assigned higher energy values than other colors and/or color ranges, and may be protected during image reduction and/or expansion. These energy values may be used to determine a cost associated with various seams of the image, which may represent the priority of the seams in the image. One or more low-cost seams may be identified for removal or replication to produce a resized image. The methods may be used in conjunction with an automated skin tone detector or a user interface that allows selection of one or more high priority colors or color ranges.

Abstract: A method for securely classifying private data x of a first party Alice using a classifier H(x) of a second party Bob. The classifier is H ? ( x ) = sign ? ? ( ? n = 1 N ? h n ? ( x ) ) , where h n ? ( x ) = { ? n x T ? y n > ? n ? n otherwise , ? n , ? n and ?n are scalar values and yn is a vector storing parameters of the classifier. Bob generates a set of N random numbers, S1, . . . , SN, such that s = ? n = 1 N ? s n , for each n=1, . . . , N, the following substeps are performed: applying a secure dot product to xTyn to obtain an for Alice and bn for Bob; applying a secure millionaire protocol to determine whether an is larger than ?n?bn, and returning a result of an+Sn, or ?n+Sn; accumulating, by Alice, the result in cn.

Abstract: A method extracts an alpha matte from images acquired of a scene by cameras. A depth plane is selected for a foreground in the scene. A trimap is determined from a set of images acquired of the scene. An epipolar plane image is constructed from the set of images and the trimap, the epipolar plane image including scan lines. Variances of intensities are measured along the scan lines in the epipolar image, and an alpha matte is extracted according to the variances.

Abstract: The present invention is embodied in a system and method for extracting structure from multiple images of a scene by representing the scene as a group of image layers, including reflection and transparency layers. In general, the present invention performs layer extraction from multiple images containing reflections and transparencies. The present invention includes an optimal approach for recovering layer images and their associated motions from an arbitrary number of composite images. The present invention includes image formation equations, the constrained least squares technique used to recover the component images, a novel method to estimate upper and lower bounds on the solution using min- and max-composites, and a motion refinement method.

Abstract: A method processes an input image securely. An input image I is acquired in a client. A set of m random images, H1, . . . , Hm, and a coefficient vector, a=[a1, . . . , am], are generated such that the input image I is I=?i=1m?iHj. The set of the random images is transferred to a server including a weak classifier. In the server, a set of m convolved random images H? are determined, such that {H1?=?1(H1*y}i,1m, where * is a convolution operator and ?1 is a first random pixel permutation. The set of convolved images is transferred to the client. In the client, a set of m permuted images I? is determined, such that I?=?2(?i=1m?iH1?), where ?2 is a second random pixel permutation. The set of permuted image is transferred to the server.

Abstract: A method locates an object in a sequence of frames of a video. A feature vector is constructed for every pixel in each frame. The feature vector is used to training the weak classifiers. The weak classifiers separate pixels that are associated with the object from pixels that are associated with the background. The set of weak classifiers are combined into a strong classifier. The strong classifier labels pixels in a frame to generate a confidence map. A ‘peak’ in the confidence is located using a mean-shift operation. The peak indicates a location of the object in the frame. That is, the confidence map distinguishes the object from the background in the video.

Abstract: A computer implemented method tracks 3D positions of an object moving in a scene. A sequence of images is acquired of the scene with a set of cameras such that each time instant a set of images are acquired of the scene, in which each image includes pixels. Each set of images is aggregated into a synthetic aperture image including the pixels, and the pixels in each the set of images are matched corresponding to multiple locations and multiple depths of a target window with an appearance model to determine scores for the multiple locations and multiple depths. A particular location and a particular depth having a maximal score is selected as the 3D position of the moving object.

Abstract: A method for content-aware image retargeting generates an energy image from a source image according to an energy function. From the energy image, one or more seams are determined according to a minimizing function such that each seam has a minimal energy. Each seam is applied to the source image to obtain a target image that preserves content and a rectangular shape of the source image.

Abstract: A method for content-aware image retargeting generates an energy image from a source image according to an energy function. From the energy image, one or more seams are determined according to a minimizing function such that each seam has a minimal energy. Each seam is applied to the source image to obtain a target image that preserves content and a rectangular shape of the source image.

Abstract: A method represents a class of objects by first acquiring a set of positive training images of the class of objects. A matrix A is constructed from the set of positive training images. Each row in the matrix A corresponds to a vector of intensities of pixels of one positive training image. Correlated intensities are grouped into a set of segments of a feature mask image. Each segment includes a set of pixels with correlated intensities. From each segment, a subset of representative pixels is selected. A set of features is assigned to each pixel in each subset of representative pixels of each segment of the feature mask image to represent the class of objects.

Abstract: A method for content-aware image retargeting generates an energy image from a source image according to an energy function. From the energy image, one or more seams are determined according to a minimizing function such that each seam has a minimal energy. Each seam is applied to the source image to obtain a target image that preserves content and a rectangular shape of the source image.

Abstract: A method and system for determining an alpha matte for a video is presented. A set of videos is acquired by an array of cameras. A centrally located camera in the array is designated as a reference camera and acquires a reference video. A foreground depth plane is selected from the set of videos. A trimap is determined from variances of pixel intensities in each image. Variances of the intensities of pixels labeled as background and pixels labeled as foreground are extrapolated to the pixels labeled as unknown in the trimap. Means of the intensities of the pixels labeled as background are extrapolated to the pixels labeled as unknown to determine an alpha matte for the reference video.

Abstract: A method processes an input image securely. An input image is acquired in a client and partitioned into a set of overlapping tiles. The set of overlapping tiles is transferred to a server. In the server, motion pixels in each tile that are immediately adjacent to other motions pixels in the tile are labeled locally to generate a set of locally labeled tiles. The set of locally labeled tiles is transferred to the client. In the client, the set of locally labeled tiles is labeled globally to generate a list of pairs of unique global labels. The list of pairs of unique global labels is transferred to the server. In the server, the pairs of unique global labels are classified into equivalence classes. The equivalence classes are transferred to the client and the motion pixels are relabeled in the client according to the equivalence classes to form connected components in the input image.

Abstract: A method processes a sequence of input images securely. A sequence of input images are acquired in a client. Pixels in each input image are permuted randomly according to a permutation ? to generate a permuted image for each input image. Each permuted image is transferred to a server, which maintains a background image from the permuted images. In the server, each permuted image is combined with the background image to generate a corresponding permuted motion image for each permuted image. Each permuted motion image is transferred to the client and the pixels in each permuted motion image are reordered according to an inverse permutation ??1 to recover a corresponding motion image for each input image.

Abstract: A computer implemented method models a background in a sequence of frames of a video. For each frame, the method detects static corners using an array of pixels of the frame, and extracts, for each static corner, features from a window of pixels around the static corner. For each static corner, a descriptor is determined from the corresponding features. Each static corner and corresponding descriptor is stored in a memory, and each static corner is classified as a background or foreground according to the descriptor to model a background in the video.