Universidad Complutense de Madrid
E-Prints Complutense

Local stereovision matching through the ADALINE neural network

Impacto

Downloads

Downloads per month over past year

Pajares Martinsanz, Gonzalo and Cruz García, Jesús Manuel de la (2001) Local stereovision matching through the ADALINE neural network. Pattern Recognition Letters, 22 (14). pp. 1457-1473. ISSN 0167-8655

[thumbnail of cruzgarcia60.pdf]
Preview
PDF
543kB

Official URL: http://dx.doi.org/10.1016/S0167-8655(01)00097-6




Abstract

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.


Item Type:Article
Additional Information:

Part of the work has been performed under project CICYT TAP94-0832-C02-01. The constructive recommendations provided by the reviewers are also gratefully acknowledged.

Uncontrolled Keywords:Images, Relaxation, Criterion, Algorithm.
Subjects:Sciences > Computer science
ID Code:26379
Deposited On:25 Aug 2014 12:51
Last Modified:31 Dec 2020 00:03

Origin of downloads

Repository Staff Only: item control page