An RBF Network that Learns Some Aspects of Perceptual Organization Thomas M. Breuel IDIAP C.P. 609, 1920 Martigny, Switzerland tmb@idiap.ch This paper describes a simple Radial Basis Function network (RBF network) that captures some of the higher order statistical properties important for certain kinds of perceptual organization. Data is presented that demonstrates that the proposed RBF network has a smaller probability of false positive matches than more commonly used functions for evaluating the quality of match between an object model and an image.