Semi-Huber potential function for image segmentation

Abstract

In this work, a novel model of Markov random field is presented, named Semi-Huber potential function, applied to image segmentation in presence of noise. The main difference with respect to other models that have been taken as a reference, is that the number of parameters in the proposed model is significatively smaller. The idea is to choose adequate parameter values heuristically for a good segmentation of the image. In that sense, experiment results show that the proposed model allows a faster and easier parameter adjustment with razonable computation times.