摘要:
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.
摘要:
A system and method for expansion and reduction of images uses a look-up table to define an arbitrary mapping of data (e.g., pixel values) representing an image to respective energy values. Each pixel value may represent an absolute color or intensity value, a difference in color or intensity values, or an average, derivative, minimum, or maximum of two or more pixel values. The energy values may then be used to determine one or more low-cost seams of the image to be removed for an image reduction operation or replicated for an image expansion operation, where the cost of each seam is dependent on the energy values of the pixels of the seam. The look-up table may be used to apply a threshold and/or cap on the energy values mapped to pixel values. The look-up table may also provide a mechanism for reconfiguring mappings, thresholds, and/or caps.
摘要:
A system and method for expansion and reduction of images uses a hybrid resizing technique that combines seam carving and image scaling techniques to reduce or expand an image. Seam carving techniques may be used to identify one or more low-cost seams of an input image, and these low-cost seams may be scaled up or down to expand or reduce the overall input image and produce a resized image. A different scaling factor may be applied to different ones of the low-cost seams, dependent on the average or total energy value of each of the seams. The scaling factor applied to each seam may be dependent on the number of low-cost seams identified for scaling, which may be configurable by a user. A configurable look-up table may map seam costs to scaling factors, and may be accessed to determine a respective scaling factor to be applied to each identified seam.
摘要:
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.
摘要:
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.
摘要:
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 ) = { α n x T y n > Θ n β n otherwise , α n , β n and Θn 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 Θn−bn, and returning a result of an+Sn, or βn+Sn; accumulating, by Alice, the result in cn. Then, apply the secure millionaire protocol to determine whether c = ∑ n = 1 N c n is larger than s = ∑ n = 1 N s n , and returning a positive sign if true, and a negative sign if false to classify the private data x.
摘要翻译:一种用于使用第二方Bob的分类器H(x)安全地分类第一方Alice的私有数据x的方法。 分类器是H(x)= sign-务(Σn = 1 N hn(x)),其中hn(x)= {αnx T yn>否则,αn,β n和Thetan是标量值,yn是存储分类器参数的向量。 Bob生成一组N个随机数S1。 。 。 ,SN,使得对于每个n = 1,s =Σn = 1 N s n。 。 。 ,N,执行以下子步骤:将安全点产品应用于xTyn以获得用于Bob的Alice和bn; 应用安全的百万富翁协议来确定a是否大于Thetan-bn,并返回+ Sn或betan + Sn的结果; 由爱丽丝积累,结果在cn。 然后,应用安全的百万富翁协议来确定c =Σn = 1 N cn是否大于s =Σn = 1 N sn,并且如果为真,则返回正号,如果为假,则将负号标记为私有 数据x。
摘要:
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.
摘要:
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.
摘要:
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.
摘要:
A method maximizes a candidate solution to a cardinality-constrained combinatorial optimization problem of sparse principal component analysis. An approximate method has as input a covariance matrix A, a candidate solution, and a sparsity parameter k. A variational renormalization for the candidate solution vector x with regards to the eigenvalue structure of the covariance matrix A and the sparsity parameter k is then performed by means of a sub-matrix eigenvalue decomposition of A to obtain a variance maximized k-sparse eigenvector x that is the best possible solution. Another method solves the problem by means of a nested greedy search technique that includes a forward and backward pass. An exact solution to the problem initializes a branch-and-bound search with an output of a greedy solution.