STOCHASTIC COMPLETION FIELDS - A NEURAL MODEL OF ILLUSORY CONTOUR SHAPE AND SALIENCE

We describe an algorithm- and representation-level theory of illusory contour shape and salience. Unlike previous theories, our model is der ived from a single assumption: that the prior probability distribution of boundary completion shape can be modeled by a random walk in a lat tice whose points are positions and orientations in the image plane (i .e., the space that one can reasonably assume is represented by neuron s of the mammalian visual cortex). Our model does not employ numerical relaxation or other explicit minimization, but. instead relies on the fact that the probability that a particle following a random walk wil l pass through a given position and orientation on a path joining two boundary fragments can be computed directly as the product of two vect or-field convolutions. We show that for the random walk we define, the maximum likelihood paths are curves of least energy, that is, on aver age, random walks follow paths commonly assumed to model the shape of illusory contours. A computer model is demonstrated on numerous illuso ry contour stimuli from the literature.