Title :
Neural networks for extracting features of objects in images as a pre-processing stage to pattern classification
Author :
Hoare, Frederick ; De Jager, Gerhard
Author_Institution :
Dept. of Electr. & Electron. Eng., Cape Town Univ., Rondebosch, South Africa
fDate :
9/11/1992 12:00:00 AM
Abstract :
The use of neural networks to implement the extraction of features of different objects in an image is investigated. In particular the self-organising map type of neural network is described and it is shown how this can be used for feature extraction
Keywords :
feature extraction; pattern recognition; self-organising feature maps; feature extraction; neural networks; pattern classification; self-organising map; Africa; Animals; Biological neural networks; Cities and towns; Data mining; Feature extraction; Intelligent networks; Neural networks; Neurons; Pattern classification;
Conference_Titel :
Communications and Signal Processing, 1992. COMSIG '92., Proceedings of the 1992 South African Symposium on
Conference_Location :
Cape Town
Print_ISBN :
0-7803-0807-7
DOI :
10.1109/COMSIG.1992.274277
