Дослідження нечітких нейронних мереж у задачах розпізнавання об’єктів електрооптичних зображень

The problem of object recognition in electrooptical images obtained using multispectral optical systems is considered. A fuzzy neural network is suggested for the solution of this problem. Different training algorithms for fuzzy neural network are considered, and the results of experimental investig...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Datum:2009
Hauptverfasser: Zaychenko, Yu. P., Petrosiuk, I. M., Yaroshenko, M. S.
Format: Artikel
Sprache:Russisch
Veröffentlicht: The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" 2009
Online Zugang:http://journal.iasa.kpi.ua/article/view/107271
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Назва журналу:System research and information technologies

Institution

System research and information technologies
Beschreibung
Zusammenfassung:The problem of object recognition in electrooptical images obtained using multispectral optical systems is considered. A fuzzy neural network is suggested for the solution of this problem. Different training algorithms for fuzzy neural network are considered, and the results of experimental investigations of their efficiency on the basis of real data are presented.