Invariant pattern recognition with eye movement: A neural network model

Citation
M. Kikuchi et K. Fukushima, Invariant pattern recognition with eye movement: A neural network model, NEUROCOMPUT, 38, 2001, pp. 1359-1365
Citations number
7
Language
INGLESE
art.tipo
Article
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
NEUROCOMPUTING
ISSN journal
0925-2312 → ACNP
Volume
38
Year of publication
2001
Pages
1359 - 1365
Database
ISI
SICI code
0925-2312(200106)38:<1359:IPRWEM>2.0.ZU;2-9
Abstract
We propose a neural network model of the 2D invariant pattern recognition i ncluding a mechanism of saccadic eye movement. The model extracts every spa tial relation between two primitive features (feature-relation) from a stim ulus. The mechanism of saccadic eye movement enables the network to obtain all feature-relations present in the stimulus. This set of feature-relation s describe uniquely the shape of pattern independent of position, scale, an d deformation. Recognition of the presented pattern is achieved by classify ing the obtained set of feature-relations. The ability of the model is conf irmed by computer-simulation. (C) 2001 Elsevier Science B.V. All rights res erved.