A Fast Image Segmentation Approach based on Level Set Method

All level set based image segmentation methods are based on an assumption that the level set function is or close to a signed distance function (SDF). Small time step and costly reinitialization procedure must be applied to guarantee this assumption, and this will do slow down the segmentation process. In this article, we propose a fast image segmentation approach based level set method, we use an external energy term based on Mumford-Shah functional model (1989) and Chan-Vese model (2001) that drives the motion of the zero level set toward the desired image features, such as object boundaries, while an internal energy term to keep the level set function to a SDF. Experiments results show that our approach can use a large time step to speed up the segmentation process and achieve good results both on synthetic and real images and medical images