Local stereovision matching through the ADALINE neural network

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 ma...

Descripción completa

Detalles Bibliográficos
Autores: Pajares Martínsanz, Gonzalo, Cruz García, Jesús Manuel de la
Tipo de recurso: artículo
Fecha de publicación:2001
País:España
Institución:Universidad Complutense de Madrid (UCM)
Repositorio:Docta Complutense
Idioma:inglés
OAI Identifier:oai:docta.ucm.es:20.500.14352/59146
Acceso en línea:https://hdl.handle.net/20.500.14352/59146
Access Level:acceso abierto
Palabra clave:004
Images
Relaxation
Criterion
Algorithm.
Informática (Informática)
1203.17 Informática
Descripción
Sumario: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.