A New Approach for Gray Image Segmentation Using Level Set Method

The techniques and the processes to divide the image into several parts which have different features and to pick up foreground are called image segmentation. In this work, we propose a new approach for gray scale image segmentation based on level set method. At first, every pixel on the image is divided into either similar-property class or dissimilar-property class based on the variance of a small area centered at the pixel. Then, the velocity of curve evolution for these two classes is defined respectively. It is determined by a value called the dissimilarity of the area. Experimental results show that this approach can obtain good segmentation results of artificial images and real medical images fast and accurately.