TY - CONF
T1 - Stochastic completion fields: a neural model of illusory contour shape and salience
T2 - Computer Vision, 1995. Proceedings., Fifth International Conference on
Y1 - 1995
A1 - Williams,L. R
A1 - Jacobs, David W.
KW - boundary
KW - completion
KW - computational
KW - Computer
KW - contour
KW - contours;
KW - convolutions;
KW - cortex;
KW - curves
KW - detection;
KW - distribution;
KW - edge
KW - energy;
KW - estimation;
KW - fields;
KW - fragments;
KW - geometry;
KW - illusory
KW - image
KW - lattice;
KW - least
KW - likelihood
KW - mammalian
KW - maximum
KW - model;
KW - nets;
KW - neural
KW - of
KW - paths;
KW - plane;
KW - probability
KW - probability;
KW - random
KW - recognition;
KW - shape;
KW - stimuli;
KW - Stochastic
KW - vector-field
KW - visual
KW - walk;
AB - We describe an algorithm and representation level theory of illusory contour shape and salience. Unlike previous theories, our model is derived from a single assumption-namely, that the prior probability distribution of boundary completion shape can be modeled by a random walk in a lattice whose points are positions and orientations in the image plane (i.e. the space which one can reasonably assume is represented by neurons 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 will pass through a given position and orientation on a path joining two boundary fragments can be computed directly as the product of two vector-field convolutions. We show that for the random walk we define, the maximum likelihood paths are curves of least energy, that is, on average, random walks follow paths commonly assumed to model the shape of illusory contours. A computer model is demonstrated on numerous illusory contour stimuli from the literature
JA - Computer Vision, 1995. Proceedings., Fifth International Conference on
M3 - 10.1109/ICCV.1995.466910
ER -