Share Email Print
cover

Proceedings Paper

Handwritten character recognition based on hybrid neural networks
Author(s): Peng Wang; Guangmin Sun; Xinming Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A hybrid neural network system for the recognition of handwritten character using SOFM,BP and Fuzzy network is presented. The horizontal and vertical project of preprocessed character and 4_directional edge project are used as feature vectors. In order to improve the recognition effect, the GAT algorithm is applied. Through the hybrid neural network system, the recognition rate is improved visibly.

Paper Details

Date Published: 20 September 2001
PDF: 6 pages
Proc. SPIE 4555, Neural Network and Distributed Processing, (20 September 2001); doi: 10.1117/12.441669
Show Author Affiliations
Peng Wang, Beijing Polytechnic Univ. (China)
Guangmin Sun, Beijing Polytechnic Univ. (China)
Xinming Zhang, Beijing Polytechnic Univ. (China)


Published in SPIE Proceedings Vol. 4555:
Neural Network and Distributed Processing

© SPIE. Terms of Use
Back to Top