A fast and fully unsupervised scheme for model-based image segmentation

A numerically efficient approach to the problem of automatically segmenting images into regions of statistical stationarity (i.e. homogeneous texture) is proposed in this paper. The technique is fully unsupervised, in that no prior knowledge of the number of regions, or their attributes, is required. Instead, this knowledge is inferred via a dynamic learning phase. Specifically, image features are extracted from windows forming a tesselation of the image, by fitting the realization in each window with a Gaussian Markov Random Field (GMRF). An approach to cluster formation in feature space is described, based on a finite Gaussian mixture model. This phase of the algorithm permits a threshold parameter-and, subsequently, the number of texture classes and their parameters-to be inferred. A very fast approach to fine segmentation-which uses the results of the clustering phase as inputs-is then implemented, yielding a class label inference for a dynamically-chosen sparse set of pixel sites. The scheme is iterated to convergence, yielding a label realization for all pixel sites. To further enhance the identification of textural borders, a post-processing algorithm, using ICM-based estimation, is activated in areas of high edge activity, using the results of the previous stages as estimates of the label realizations in such areas. The performance of the scheme in synthetic and real image contexts is considered.