MRMRF Texture Classi cation and MCMC Parameter Estimation

Texture classiication is an important area in the eld of texture analysis. In this paper, we propose a novel stochastic approach{multiresolution Markov Random Field (MRMRF) model to represent textures and a parameter estimation method based on Markov chain Monte Carlo method is proposed. The parameters estimated from the decomposed sub-bands can be used as features to classify textures. The classiier used here is nearest linear combina-tion(NLC) which uses the combination of the features of several prototypes of an original texture to t the features of the query texture. This method is better than NN(nearest neighbor) classiier. The experiment results illustrate the eeectiveness of our method.