Shape-Based Level Set Method for Image Segmentation

In this paper, a level set method with shape model is proposed for image segmentation. Because the level set model proposed by Chan and Vese can not work well on some specific shape, this paper adds the shape knowledge into the segmentation method. The Chan-Vese level set model is applied to get initial segmentation. And then the position and the size of the pre-segmented region will be calculated to establish the shape models. Finally the proposed method is applied to segment the region more correctly on the image with specific shape. In the last of this paper, we will show our experimental results. The proposed method is compared with the Chan-Vese model to prove that using the shape models to segment the image with specific shape will surely get the better results.