A NEURAL-NETWORK MODEL IN STEREOVISION MATCHING

The paper outlines a method for solving the stereovision matching prob lem through a Neural Network approach based on self-organizing techniq ue. The goal is to classify pairs of features (edge segments) as true or false matches; giving rise to two classes. Thus, the corresponding parameter vector from two component density functions, representing bo th classes and drawn as Normal densities, are to be estimated by using an unsupervised learning method. A three layer neural network topolog y implements the mixture density function and Bayes's rule, all requir ed computations are realized with the simple ''sum of product'' units commonly used in connectionist models. The unsupervised learning metho d leads to a learning rule, while all applicable constraints from ster eovision field yield an activation rule. A training process receives t he samples to learn, and a matching process classifies the pairs. The method is illustrated with two images from an indoor scene.