Fast image segmentation based on two-dimensional minimum Tsallis-cross entropy

Image segmentation based on 2-D (two dimensional) histogram is an effective method because the structure information is taken into account in image. However, it always is on the assumption that partial region of 2-D histogram equals to zero, while utilizing Shannon entropy as optimization function. As a result, the efficiency of image segmentation is degraded seriously. In this paper, we proposed a fast thresholding segmentation based on two-dimensional minimum Tsallis-cross entropy and PSO, which utilizes minimum Tsallis-cross entropy as optimization function which is non-extensive and calculates optimal threshold in improved gray level-gradient histogram which cancels previous hypothesis that partial region value equals to zero in histogram. At the same time, the improved 2-D histogram is clustered before searching optimal threshold value to shorten the time. Experiment results show that the proposed algorithm achieves a better segmentation quality and computation efficiency.