Level Set Segmentation Algorithm Based on Image Entropy and Simulated Annealing

The Mumford-Shah model using level set method is more robust than other curve evolution models to detect discontinuities under noisy environment, which has been widely used in the field of image segmentation. However, its usefulness has been limited by several problems in iterative speed and termination. Consequently, a novel segmentation algorithm based on image entropy and simulated annealing is presented. First of all, techniques of curve evolution, level set method and Mumford-Shah functional for segmentation are discussed, followed by the numerical approximation of the model. Secondly, the concept of image entropy is introduced, as well as its application to our algorithm. Thirdly, the principle of simulated annealing and its inspiration to our algorithm is described. Finally, we perform experiments to test the performance of the algorithm using a variety of images and the results show that the proposed algorithm can improve the traditional Mumford-Shah model in iterative speed and termination.