Title :
Extending information sent to the input of a neural network
Author :
Autret, Yvon ; Solaiman, Easel
Author_Institution :
Univ. de Bretagne Occidentale, Brest, France
Abstract :
A solution for integrating two pattern recognition methods is proposed. The first method is a neural network method and the second method is a structural method. The authors propose sending structural information to the neural network to take advantage of both methods. The aim is to let the neural network analyze the global pattern and take local ambiguities into account
Keywords :
neural nets; pattern recognition; neural network; pattern recognition methods; structural method; Failure analysis; Handwriting recognition; Image analysis; Image processing; Image recognition; Neural networks; Pattern analysis; Pattern recognition; Performance analysis; Spectrogram;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.226066
