From local features to global perception - A perspective of Gestalt psychology from Markov random field theory

In this paper, we present a mathematical theory for the Gestalt psychology from the perspective of a Markov random field (MRF) theory. We demonstrate how global perception of textures and shapes are sufficiently characterized by the propagation of local features. Unlike traditional MRF theory that s tudies the interactions within small cliques, the structures of the random fields studied in this paper are the biologically relevant local features, such as Gabor filters at various frequencies and orientations, and Gestalt rules grouping local edge fragments. Our MRF models are learnt from the sta tistics in natural textures and shapes. We demonstrate three experiments in this paper: the modeling and computation of texture, shape, and medial axi s in the random fields. (C) 1999 Elsevier Science B.V. All rights reserved.