An Adaptive Markov Model-Based Method to Cluster Validation in Image Segmentation

Abstract

The number of class should be detected as part of the parameter estimation procedure prior to image segmentation for segmentation algorithms. It is very important in theory and application for estimating the class number correctly. In this paper, an adaptive total energy criterion (ATEC) to cluster validation is proposed based on the Markov random field (MRF) in the image segmentation. The criterion is composed of two parts: one part is inner-energy, which describes the difference of data in the same class; another is inter-class energy, which describes the edge information. The correct class number can be obtained by minimizing the ATEC. The parameters are estimated by expectation maximum (EM) algorithm and maximum psedu-likelihood (MPL) algorithm. The complex computation is optimized by the mixture of simulated algorithm (SA) and iterated conditional mode (ICM). The experiments show that the class number can be automatically detected by adjusting the hyper-parameter in MRF. As a by-product, the segmentation can be obtained by the maximum a posteriori (MAP).