Textured Image Synthesis and Segmentation via Neural Network Probabilistic Modeling

It has been shown that a trained back-propagation neural network (BPNN) classi er with Kullback-Leibler criterion produces outputs which can be interpreted as estimates of Bayesian a posteriori probabilities. Based on this interpretation, we propose a back-propagation neural network (BPNN) approach for the estimation of the local conditional distributions of textured images, which are commonly represented by a Markov random eld (MRF) formulation. The proposed BPNN approach overcomes many of the di culties encountered in using MRF formulation. In particular our approach does not require the trial-and-error selection of clique functions or the subsequent laborious and unreliable estimation of clique parameters. Simulations show that the images synthesized using BPNN modeling produced desired arti cial/real textures more consistently than MRF based methods. Application of the proposed BPNN approach to segmentation of arti cial and real-world textures is also presented.