Co-histogram and its application in video analysis

The tool for video analysis addressed in this paper is called co-histogram, which is a statistic graph generated by counting the corresponding pixel pairs of two images. A co-histogram shows how the pixels are distributed among combinations of two image pixel values. By means of the co-histogram, we can have a visual perception of a widely used metric, peak signal-to-noise ratio (PSNR), and the symmetry (or weighted symmetry) of a co-histogram is also good for video shot boundary detection and object entering-exiting detection. Co-histogram symmetry is insensitive to camera zooming, which is good for reducing false detection. Co-histogram symmetry is also easily computable and directly intercomparable