Pajares Martínsanz, GonzaloCruz García, Jesús Manuel de la2023-06-202023-06-202001-120167-865510.1016/S0167-8655(01)00097-6https://hdl.handle.net/20.500.14352/59146Part of the work has been performed under project CICYT TAP94-0832-C02-01. The constructive recommendations provided by the reviewers are also gratefully acknowledged.This paper presents an approach to the local stereovision matching problem using edge segments as features with four attributes. Based on these attributes we compute a matching probability between pairs of features of the stereo images. A correspondence is said to be true when this probability is maximum. The probability value is a weighted sum of the attributes. We use two combined ADALINE neural networks to compute the weight for each attribute. A comparative analysis among other recent matching methods is illustrated.engjournal articlehttp://dx.doi.org/10.1016/S0167-8655(01)00097-6http://www.sciencedirect.com/open access004ImagesRelaxationCriterionAlgorithm.Informática (Informática)1203.17 Informática