Split Bregman Method for Minimization of Modified Vese-Chan Model for Fast Image Segmentation

In this paper we present an modified active contour model for fast multiphase image segmentation based on the piecewise constant Vese-Chan model and the split Bregman method. By applying the globally convex image segmentation technique to the piecewise constant Vese-Chan energy functional, we first define a new biconvex energy functional to guarantee fast convergence. Then we incorporate the edge information into the new energy functional with a non-negative edge detector function. Finally, we apply the split Bregman method to fast minimize the new energy functional. Our modified model has been tested with synthetic and real images. Experimental results show that the modified model can obtain similar results to the Vese-Chan model but is much more efficient. Besides, the modified model is robust in the presence of noise.