Proceedings ArticleDOI
Handwritten character recognition based on hybrid neural networks
Peng Wang,Guangmin Sun,Xinming Zhang +2 more
- Vol. 4555, pp 65-70
TLDR
A hybrid neural network system for the recognition of handwritten character using SOFM,BP and Fuzzy network is presented and the recognition rate is improved visibly.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.read more
Citations
More filters
Bibliography of Self-Organizing Map SOM) Papers: 1998-2001 Addendum
TL;DR: This work has provided a keyword index to help finding articles of interest, and additionally a modern automatically constructed variant of a thematic index: a WEBSOM interface to the whole article collection of years 1981-2000.
References
More filters
Journal ArticleDOI
Adaptive normalization of handwritten characters using global/local affine transformation
Toru Wakahara,Kazumi Odaka +1 more
TL;DR: Experiments show that the proposed adaptive or category-dependent normalization method can absorb a fairly large amount of handwriting fluctuation within the same category, but the discrimination ability is greatly improved by the suppression of excessive normalization against similarly shaped but different categories.
Proceedings ArticleDOI
Handwritten digits recognition with neural networks and fuzzy logic
Wei Lu,Zhijian Li,Bingxue Shi +2 more
TL;DR: Experiments show that the handwriting recognition system based on neural networks and fuzzy logic has large ability to deal with distortion and shift variations in handwriting characters.
Related Papers (5)
Handwritten character recognition by extended loop neural networks
Miao Zhenjiang,Yuan Baozong +1 more