Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Neuronal networks for pattern recognition

: Rueff, M.; Schmutz, M.

Braggins, D.W. ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Industrial Inspection II. Proceedings
Bellingham/Wash.: SPIE, 1990 (SPIE Proceedings Series 1265)
ISBN: 0-8194-0312-1
European Congress on Optics (ECO) <3, 1990, The Hague>
Conference Paper
Fraunhofer IPA ()
Mustererkennung; Netzwerk; neuronal network; neuronales Netzwerk; pattern recognition; Rechnerverbundsystem

To make efficient practical use of the attractive properties of standard neural network models it seems reasonable to combine a recognition network with appropiate conventional preprocessing. In this contribution we describe the current research at IPA concerning such a hybrid approach to acoustic pattern recognition. the inputs of the recongition network are feature vectors consisting of local frequency characteristics extracted from the Wigner representation of the patterns. Simulations show that the system is capable to recognize individually learned objects in a scene.