Introduction
Image segmentation is a key step in image analysis and computer vision that is also the basis of the further image understanding, the purpose of which is based on certain characteristics and features to separate the image into several meaningful areas to make these characteristics consistent performance in a certain area with satisfactory similarity [1]. Since 20th century generation, image segmentation has been attached great importance by the people and thousands of the segmentation algorithms have been proposed. However, because there is no general theory of segmentation, existing algorithms are mostly aimed at the specific problems, instead of analyzing from a general perspective.