Unsupervised Color Image Segmentation using MRF Models to Preserve Weak Edges

In this paper, an unsupervised color image segmentation scheme is proposed using homotopy continuation method. Different variants of MRF model is used to preserve both strong and weak edges. A Compound Markov Random Field (COMRF) model with Bi-level Binary Line Fields is proposed. The scheme is specifically meant to preserve weak edges besides the well defined strong edges.The proposed scheme is recursive in nature where model parameter estimation and the image label estimation are alternated. Ohta ) , , ( 3 2 1 I I I model is used as the color model for image segmentation and we propose a compound MRF model taking care of intra-color and inter-color plane interactions. The COMRF model parameters are estimated using Maximum Conditional Pseudo Likelihood (MCPL) criterion and the MCPL estimates are obtained using homotopy continuation method. The image label estimation is formulated using Maximum a Posteriori criterion and the MAP estimates are obtained using hybrid algorithm. In the context of misclassification error, the proposed unsupervised scheme with COMRF model exhibited improved segmentation accuracy as compared to Yu and Clausi ’s method. Keywords— Color Image,Color Model,Segmentation,Simulated Annealing and MRF model