Images partitioning method based on M-S model with the parameters of adaptive

The hierarchical Mumford-Shah model can segment the optic cup and disk of optic nerve head images very well get from Color fundus imaging. But, because of Poor illumination and contrast small, the images have many unwanted noise, so, segmentation of images base on The hierarchical Mumford-Shah model need different length parameters. To solve this problem, this paper presents an adaptive model based on the parameter estimation. Vascular occlusion will also make cup and disk of edge Cave and Part. This paper use a method combination of prior knowledge of the constraint method to extract the effective edge curve, then, get the complete edge of optic cup and disk by using curve fitting. This method can effectively solve the above Problem of segmentation of optic cup and disk of optic nerve head images by the experimental results show.