Two-dimensional Tsallis entropy threshold segmentation based on decomposition

Two-dimensional Tsallis cross entropy method taking into account the gray levels, the average gray level of the neighborhood, and the correlation between the target and background gradation and other information. In this paper, we improve the traditional two-dimensional Tsallis cross entropy method, calculate the information which fall on the area which away from the diagonal in the histogram. This method can achieve better results to the actual images, especially the images that has a large number edge points and noise points. In addition, the proposed algorithm uses a decomposition recursive algorithm. It will reduce the computational complexity from O(L4) to O(L), and improve the performance of real-time. The experimental results show that the proposed method has better performance and running speed on segmentation. © 2013 by Binary Information Press.