Handwritten Character Recognition Research Based on Adaptive Minimum Distance Classifiers Integration

Abstract:

It is difficulty to gain completely satisfactory effect if a single classification is used to check a complicated recognition classification problem. Using the complementarities between the different classify method, integrating many classifiers, it can reduce the identification mistake and strengthen recognition robustness. Taking a offline handwritten number recognition system as an example, adopting Bayesian discriminate function based on minimal mistake rate, uniting recognition algorithm of RBF kernel function, using Bagging technology, adaptive minimum distance classifiers integration is designed in which there is minimal mistake rate. Furthermore, an offline handwritten number recognition system in high accuracy is exploited in which there is adaptive and self-learning function. It can be used for important economic fields such as financial statement and bank paper.

• Periodical: Applied Mechanics and Materials (Volumes 44-47)
• Pages: 3388-3392
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.44-47.3388
• Online since: December 2010
• Authors: Zhao Ping Tang, Jian Ping Sun, Lu Sheng Zhong
• Keywords: Character Recognition, Classifiers Integration, Minimal Mistake Rate, RBF Kernel Function, Recognition System

References

[1] Yang Shuying: Image pattern recognition- Vc++ technical implementation (Tsinghua University press, Beijing 2005), in Chinese.

[2] JING Zhong, HE Ming. Bayes Decision for Minimum Errors Applied in Recognition of Handwritten English Letters. Journal of Liaoning University of Technology (Natural Science Edition) Vol. 2(2009), pp.98-107, in Chinese.

[3] Li Xiaorun. Research on Kernel Methods for Pattern Recognition. Zhejiang: Zhejiang University Vol. 11(2007), pp.75-78, in Chinese.