RT Journal Article
T1 Local stereovision matching through the ADALINE neural network
A1 Pajares Martínsanz, Gonzalo
A1 Cruz García, Jesús Manuel de la
AB 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.
PB Elsevier Science BV
SN 0167-8655
YR 2001
FD 2001-12
LK https://hdl.handle.net/20.500.14352/59146
UL https://hdl.handle.net/20.500.14352/59146
LA eng
NO 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.
NO CICYT
DS Docta Complutense
RD 10 abr 2025