Identification of complex shapes using a self organizing neural system

We present a multilayer hierarchical neural system for automatic classification of complex contour patterns. The system consists of a neocognitron-like network structure combined with self-organizing maps to automatically determine feature classes. We present results showing that multilayer hierarch...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2000-07, Vol.11 (4), p.921-934
Hauptverfasser:	Sabisch, T., Ferguson, A., Bolouri, H.
Format:	Artikel
Sprache:	eng
Schlagworte:	Anatomical structure Artificial neural networks Classification Distortion Face recognition Feature extraction Multi-layer neural network Multilayer perceptrons Multilayers Networks Neural networks Organizing Pattern recognition Shape Visual system
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	We present a multilayer hierarchical neural system for automatic classification of complex contour patterns. The system consists of a neocognitron-like network structure combined with self-organizing maps to automatically determine feature classes. We present results showing that multilayer hierarchical networks are able to tolerate pattern distortion considerably better than standard neural network implementations.
ISSN:	1045-9227 2162-237X 1941-0093 2162-2388
DOI:	10.1109/72.857772