31 30 4 Experimental Results

The general problem of unsupervised textured image segmentation remains a fundamental but not entirely solved issue in image analysis. Many studies have proven that statistical model-based texture segmentation algorithms yield good results provided that the model parameters and the number of regions be known a priori. In this paper, we present an unsupervised texture segmentation method which does not require a priori knowledge about the di erent texture regions, their parameters, or the number of available texture classes. The proposed algorithm relies on the analysis of local and global second and higher order spatial statistics of the original images. The segmentation map is modeled using an augmented-state Markov Random Field, including an outlier class which enables dynamic creation of new regions during the optimization process. A bayesian estimate of this map is computed using a deterministic relaxation algorithm. The whole segmentation procedure is controlled by one single parameter. Results on mosaics of natural textures and real-world textured images show the ability of the model to yield relevant and robust segmentations when the number of regions and the di erent texture classes are not known a priori. Key-words: image analysis, non-supervised texture segmentation, statistical models, Markov Random Field models