4 March 1996 Hierarchical multilayer perceptron neural network for the recognition of the automobile license plate number
Author Affiliations +
Abstract
This paper proposes a new hierarchical multilayer perceptron (HMLP) network as an improved classifier for alpha-numeric character recognition from the automobile license plates. HMLP is built up by hierarchically stacking the small MLP subnetworks that work as local classifiers in the feature space. Each subnetwork is trained not to cause overtraining. The generalization and overtraining problem of neural networks was reduced by this method. The classification performance of HMLP was compared with the conventional single stage MLP, and HMLP showed better performance especially for the large sized classification problem.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Joongho Chang, Joongho Chang, Norman C. Griswold, Norman C. Griswold, } "Hierarchical multilayer perceptron neural network for the recognition of the automobile license plate number", Proc. SPIE 2664, Applications of Artificial Neural Networks in Image Processing, (4 March 1996); doi: 10.1117/12.234249; https://doi.org/10.1117/12.234249
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT

A real-time marking defect inspection method for IC chips
Proceedings of SPIE (December 09 2015)
Neural network approach to adaptive image enhancement
Proceedings of SPIE (April 01 1992)
Mathematical morphology and higher-order neural networks
Proceedings of SPIE (August 11 1995)
Study of lip-reading detecting and locating technique
Proceedings of SPIE (November 29 2007)

Back to Top