Local and distance regularized Chan-Vese image target segmentation algorithm

This text proposed the target segmentation algorithm that combined local energy information with improved signed distance regularization term. The algorithm adds local information energy, curve length constraint and signed distance regularization term to the global image information of traditional C-V model. The new algorithm inherits advantages of global and local energy functional adequately, and accurately drives the level set evolution to the target contour. It effectively realized uneven color image segmentation in less iteration. On the other hand, the improved signed distance regularization term avoids re-initialization of level set function, increases the computational efficiency, and maintains stability in the evolution process. Experiments show that the proposed algorithm has higher segmentation accuracy and robust than C-V model and other similar models.