Classification Of SAR Image Based On Pairwise Markov Random Field Model

Markov random field (MRF) theory provides a convenient and consistent way of modeling context dependent entities such as image pixels and other spatially correlated features. This is achieved through characterizing mutual influences among such entities using Gibbs probabilities. The interest in MRF modeling in computer vision is still increasing, as reflected by books as well as journals and conference papers published in recent years. Synthetic aperture radar (SAR) image segmentation is a key technique of automatic target recognition (ATR) and SAR image information processing. The presence of speckle on SAR images not only reduces the interpreter's ability to resolve fine detail, but also makes automatic segmentation of such images difficult. In this paper, we solved the problem of how to determine the number of image classes by using Minimum Description Length (MDL) principia, and prove the consistency of this method in pair-wise Markov Model. In addition, we gave an unsupervised segmentation method for textured SAR images. The details are as follows:Firstly, we summarized some criteria of model selection, especially illustrated the meaning of MDL principia and its application in image processing. We gave the formulation of image MDL in pair-wise Markov model, and prove the consistency of the MDL principal when use the formulation to determine the number of image classes. Experimental Results show that the proposed method can estimate the number of image classes well. Be different from the previously method which chosen the number of image classes by subjective ways, the method proposed by this paper was reasonable and precise.Secondly, unlike previously proposed Bayesian segmentation approaches in pair-wise Markov random field (MRF) model for synthetic aperture radar (SAR) images, which have either assumed the parameters of the Gibbs distribution in...