An Improved Image Segmentation Method Based on Fast Level Set Combining with C-V Model

Aim at the high computational complexity of level set methods has excluded themselves from many real-time applications. An improved image segmentation method using the fast level set algorithm is proposed in this paper. The algorithm adopts improved fast level set base on single list to realize the curve evolution, which simplifies the fast level set method. Avoiding the traditional level set methods need to re-initialize the level set function and the processes of solving partial differential equations, accelerating the velocity of segmentation. And the algorithm uses the binary fitting terms of C-V model to design the speed function of curve evolution, it preserves the global optimization characteristic of C-V model. In addition, a termination criterion based on the number change of contour points in the single list is proposed to ensure that the evolving curve can automatically stop on the true boundaries of objects. The experiments show that the algorithm which is proposed in this paper can significantly improve the segmentation velocity and efficiently segment the noise images.