关键词: 图像处理, 图像分割, 交叉熵, 直方图重构, 虚拟图像

Abstract: Concerning the thresholds selection in image segmentation, this paper proposed a method that used dynamic threshold to divide the histogram of original image into two new independent histograms. The two new histograms correspond to two fictitious images whose sizes are the same to original one，and pixels of the same probability are similar pixels of original image. The cross entropy can be assembled and calculated between probability distribution of the two new histograms. By analyzing the relationship between peak and valley of the maximum of entropy functional curve,the best multi-thresholds for segmentation image can be achieved. This method is simple and clear, and the experiment shows this method is effective.

Key words: image processing, image segmentation, cross entropy, histogram reconstruction, fictitious image