A Variational Level Set Method for Image Segmentation on Implicit Surfaces
隐式曲面上两相图像分割的变分水平集方法

The classic Chan-Vese model for two-phases segmentation of planar images is extended to image segmentation on implicit surfaces. The zero level set of a static level set function is used to express the surface on which images to be segmented are defined. Its intersection with another zero level set of a dynamic level set function is used to express spatial active contours for image segmentation. The novel energy functional includes three parts, the first one is the sum of square of the difference between pixel intensity and mean values in two regions on the surface. The second one is the length of spatial contour, and the third one is a penalty term to enforce the dynamic level set function to be a signed distance function. The evolution equation of the dynamic level set function is obtained using variation technique and is discretized with a simple explicit finite difference method. Experimental results validate the capacity of the proposed model in two phase image segmentation on implicit surfaces.