A fast segmentation algorithm for images with intensity in-homogeneity

A novel fast method based on local region active contour model is proposed to overcome the difficult and ineffective segmentation of in-homogenous images. A new energy function is defined by combining kernel function and cut metric. On one hand，kernel function is favor of computing the in-homogenous distribution of local regions effectively；on the other hand，better approximation of the curve length by cut metric can help contours to quickly evolve into the object’s boundary. In addition，in the evolving process of contours，a max-flow method is adopted，instead of traditional computational level set method. Experimental results of synthetic and real images show that the proposed method can effectively segment objects with weak boundary in in-homogenous images，as well as the complex structure objects with multi-gray levels. At the same time，it is robust to noise and the initial contours.

Project Supported:

Clc Number: