A probabilistic neural network for attribute selection in stereovision matching

Abstract

The key step in stereovision is image matching. This is carried out on the basis of selecting features, edge points, edge segments, regions, corners, etc. Once the features have been selected, a set of attributes (properties) for matching is chosen. This is a key issue in stereovision matching. This paper presents an approach for attribute selection in stereovision matching tasks based on a Probabilistic Neural Network, which allows the computation of a mean vector and a covariance matrix from which the relative importance of attributes for matching and the attribute interdependence can be derived. This is possible because the matching problem focuses on a pattern classification problem. The performance of the method is verified with a set of stereovision images and the results contrasted with a classical attribute selection method and also with the relevance concept.