Image recovery and segmentation using competitive learning in a computational network

In this study, the principle of competitive learning is used to develop an iterative algorithm for image recovery and segmentation, within the framework of Markov Random Fields (MRF). the image recovery problem is transformed to the problem of minimization of an energy function. A local update rule for each pixel point is then developed in a stepwise fashion and is shown to be a gradient descent rule for an associated global energy function. Relationship of the update rule to Kohonens update rule is shown. Quantitative measures of edge preservation and edge enhancement for synthetic images are introduced. Simulation experiments using this algorithm on real and synthetic images show promising results on smoothing within regions and also on enhancing the boundaries.

Restoration results are compared with recently published results using the mean field approximation. Segmentation results using the proposed approach are compared with edge detection using fractal dimension, edge detection using mean field approximation, and edge detection using the Sobel operator. Edge points obtained by using these techniques are combined to produce edge maps which include both hard and soft edges.