Simulated annealing for texture segmentation with Markov models

Abstract

Binary textured images are segmented into regions of different textures. The binary Markov model is used, and model parameters are assumed to be unknown prior to segmentation. The parameters are estimated using a weighted-least-squares method, while segmentation is performed iteratively using simulated annealing. To speed up the annealing process, an initial coarse segmentation algorithm that quickly determines the approximate region categories using k-means clustering algorithm is used. The results look promising, and the computational costs can be reduced further by optimization of the computations.