Unsupervised texture based image segmentation by simulated annealing using Markov random field and Potts models

Unsupervised segmentation of images which are composed of various textures is investigated. A coarse segmentation is achieved through a hierarchical self organizing map. This initial segmentation result is fed into a simulated annealing algorithm in which region and texture parameters are estimated using a maximum likelihood technique. Region geometries are modeled as Potts model while textures are modeled as Markov random fields. Tests are performed on artificial textured images