Image Segmentation Based on Evidential Markov Random Field Model

Image segmentation is a classical problem in computer vision and has been widely used in many fields. Due to the uncertainty in images, it is difficult to obtain a precise segmentation result. To deal with the problem of uncertainty encountered in the image segmentation, an evidential Markov random field (EMRF) model is designed, based on which a novel image segmentation algorithm is proposed in this paper. The credal partition based on the evidence theory is used to define the label field. The iterated conditional modes (ICM) algorithm is used for the optimization in EMRF. Experimental results show that our proposed algorithm can provide a better segmentation result against the traditional MRF, the Fuzzy MRF (FMRF) and the traditonal evidential approaches.