Opacity Measurement Using A Global Pixel Set

Abstract

A computing device is described herein that is configured to select a pixel pair including a foreground pixel of an image and a background pixel of the image from a global set of pixels based at least on spatial distances from an unknown pixel and color distances from the unknown pixel. The computing device is further configured to determine an opacity measure for the unknown pixel based at least on the selected pixel pair.

We claim: 
     
         1 . A system comprising:
 a processor; and   a pair selection module configured to be operated by the processor to select a pixel pair including a foreground pixel of an image and a background pixel of the image based at least on a correspondence search in a search space that includes foreground and background pixels of the image, the correspondence search including at least one of a propagation operation or a random search operation; and   an opacity determination module configured to be operated by the processor to determine an opacity measure for the unknown pixel based at least on the selected pixel pair.   
     
     
         2 . The system of  claim 1 , wherein the pair selection module is further configured to separately order the foreground pixels and the background pixels in the search space based at least on color intensities of the foreground pixels and color intensities of the background pixels. 
     
     
         3 . The system of  claim 1 , wherein the pair selection module is further configured to assign a pixel pair to the unknown pixel as an initial operation of the correspondence search. 
     
     
         4 . The system of  claim 1 , wherein the propagation operation includes comparing a cost of a pixel pair currently assigned to the unknown pixel to costs of pixel pairs of neighboring pixels of the unknown pixel and updating the currently assigned pixel pair based on the comparison. 
     
     
         5 . The system of  claim 1 , wherein the random search operation comprises comparing a cost of a pixel pair currently assigned to the unknown pixel to a cost of a randomly selected pixel pair of the image and updating the currently assigned pixel pair based on the comparison. 
     
     
         6 . The system of  claim 5 , wherein the pair selection module is further configured to randomly select the randomly selected pixel pair by summing a pixel pair currently assigned to the unknown pixel with a product of a size of the search space, an exponential of a radio value, and a number in a defined range. 
     
     
         7 . The system of  claim 5 , wherein the pair selection module is further configured to perform a predetermined number of iterations of the correspondence search, each iteration including the propagation operation and the random search operation. 
     
     
         8 . A computer-implemented method comprising:
 selecting a pixel pair including a foreground pixel of an image and a background pixel of the image based at least on a correspondence search in a search space that includes foreground and background pixels of the image, the correspondence search including at least one of a propagation operation or a random search operation; and   determining an opacity measure for the unknown pixel based at least on the selected pixel pair.   
     
     
         9 . The computer-implemented method of  claim 8 , further comprising separately ordering the foreground pixels and the background pixels in the search space based at least on color intensities of the foreground pixels and color intensities of the background pixels. 
     
     
         10 . The computer-implemented method of  claim 8 , further comprising assigning a pixel pair to the unknown pixel as an initial operation of the correspondence search. 
     
     
         11 . The computer-implemented method of  claim 8 , wherein the propagation operation includes comparing a cost of a pixel pair currently assigned to the unknown pixel to costs of pixel pairs of neighboring pixels of the unknown pixel and updating the currently assigned pixel pair based on the comparison. 
     
     
         12 . The computer-implemented method of  claim 8 , wherein the random search operation comprises comparing a cost of a pixel pair currently assigned to the unknown pixel to a cost of a randomly selected pixel pair of the image and updating the currently assigned pixel pair based on the comparison. 
     
     
         13 . The computer-implemented method of  claim 12 , further comprising randomly selecting the randomly selected pixel pair by summing a pixel pair currently assigned to the unknown pixel with a product of a size of the search space, an exponential of a radio value, and a number in a defined range. 
     
     
         14 . The computer-implemented method of  claim 12 , further comprising performing a predetermined number of iterations of the correspondence search, each iteration including the propagation operation and the random search operation. 
     
     
         15 . One or more computer storage media having computer-executable instructions stored thereon which, when executed by a computing device, cause the computing device to perform operations comprising:
 selecting a pixel pair including a foreground pixel of an image and a background pixel of the image based at least on a correspondence search in a search space that includes foreground and background pixels of the image, the correspondence search including at least one of a propagation operation or a random search operation; and   determining an opacity measure for the unknown pixel based at least on the selected pixel pair.   
     
     
         16 . The one or more computer storage media of  claim 15 , further comprising separately ordering the foreground pixels and the background pixels in the search space based at least on color intensities of the foreground pixels and color intensities of the background pixels. 
     
     
         17 . The one or more computer storage media of  claim 15 , further comprising assigning a pixel pair to the unknown pixel as an initial operation of the correspondence search. 
     
     
         18 . The one or more computer storage media of  claim 15 , wherein the propagation operation includes comparing a cost of a pixel pair currently assigned to the unknown pixel to costs of pixel pairs of neighboring pixels of the unknown pixel and updating the currently assigned pixel pair based on the comparison. 
     
     
         19 . The one or more computer storage media of  claim 15 , wherein the random search operation comprises comparing a cost of a pixel pair currently assigned to the unknown pixel to a cost of a randomly selected pixel pair of the image and updating the currently assigned pixel pair based on the comparison. 
     
     
         20 . The one or more computer storage media of  claim 19 , further comprising performing a predetermined number of iterations of the correspondence search, each iteration including the propagation operation and the random search operation.