Accurate segmentation of magnetic resonance images (MRI) corrupted by intensity in homogeneity is a challenging problem and has received an enormous amount of attention lately. On the basis of the local image model, we propose a different segmentation method for MR brain images without estimation and correction for intensity heterogeneity. Firstly, we obtain clustering context which size is optimized by a minimum entropy criterion. Then, each context is segmented by affinity propagation (AP) algorithm. The proposed methodology has been evaluated for simulated images and shown the better results.
