Title :
Identification of complex shapes using a self organizing neural system
Author :
Sabisch, Theo ; Ferguson, Alistair ; Bolouri, Hamid
Author_Institution :
Eng. Res. & Dev. Centre, Hertfordshire Univ., Hatfield, UK
fDate :
7/1/2000 12:00:00 AM
Abstract :
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
Keywords :
edge detection; feature extraction; feedforward neural nets; pattern classification; self-organising feature maps; complex shape recognition; contour recognition; feature extraction; multilayer hierarchical neural network; pattern classification; self organizing maps; Anatomical structure; Artificial neural networks; Face recognition; Feature extraction; Multi-layer neural network; Multilayer perceptrons; Organizing; Pattern recognition; Shape; Visual system;
Journal_Title :
Neural Networks, IEEE Transactions on
