Edge preserving image smoothing based on self avoiding random walk

In this paper a novel approach to the problem of image enhancement and restoration has been presented. The described filtering technique enables the suppression of different kinds of noise, while preserving the image edges. The algorithm is based on a concept of a virtual particle, which performs a special kind of random walk - the so called self-avoiding random walk. Segmentation effect obtained using this method, together with the ability of the algorithm to eliminate impulse and Gaussian noise makes the new method an interesting pre-processing tool for image segmentation.