A neural network model in stereovision matching

Cruz García, Jesús Manuel de la, Pajares, Gonzalo y Aranda Almansa, Joaquín . (1995) A neural network model in stereovision matching. Pergamon, Neural Networks, (v.8, n.5), p. 805-813


Título A neural network model in stereovision matching
Autor(es) Cruz García, Jesús Manuel de la
Pajares, Gonzalo
Aranda Almansa, Joaquín
Materia(s) Informática
Resumen The paper outlines a method for solving the stereovision matching problem through a Neural Network approach based on self-organizing technique. 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 fanctions, representing both classes and drawn as Normal densities, are to be estimated by using an unsupervised learning method. A three layer neural network topology implements the mixture denMty fanction and Bayes's rule, all required computations are realized with the simple "'sam of product'" units commonly used in connectionist models. The unsupervised learning method leads to a learning rule, while all applicable constraints from stereovision field yield an activation rule. A training process receives the samples to learn, and a matching process classifies the pairs. The method is illustrated with two images from an indoor scene.
Palabras clave neural network
unsupervised learning
training
stereovision
matching
self-organizing
Bayes strategy
probability density function
Editor(es) Elsevier
Fecha 1995-01-01
Formato application/pdf
Identificador bibliuned:642
Publicado en la Revista Pergamon, Neural Networks, (v.8, n.5), p. 805-813
Idioma eng
Versión de la publicación publishedVersion
Tipo de recurso Article
Derechos de acceso y licencia http://creativecommons.org/licenses/by-nc-nd/4.0
info:eu-repo/semantics/openAccess
Tipo de acceso Acceso abierto

 
Versiones
Versión Tipo de filtro
Contador de citas: Google Scholar Search Google Scholar
Estadísticas de acceso: 401 Visitas  -  Estadísticas en detalle
Creado: Fri, 16 Nov 2007, 10:27:29 CET