Affinity based seeded region growing algorithm for medical image segmentation

We present seeded region growing algorithm using notion of `affinity´ as region growth mechanism for segmentation of medical images. Affinity between pair of pixels captures the idea of nearness in location and similarity between their gray scale values. Affinity has the capability to separate different segments of the images depending upon its functional definition. Our experiments reveal that when seeded region growing is used with affinity as the measure of similarity the segmentation is better than traditional methods.