Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (15): 212-214.

• 工程与应用 • Previous Articles     Next Articles

Off-line handwritten amount Chinese characters recognition based on multiple classifiers combination

YU Ying1,2,YANG Yang1,DONG Cai-lin3,HE Xiu-ling1,3,CHEN Zeng-zhao1,3   

  1. 1.School of Information Engineering,University of Science & Technology Beijing,Beijing 100083,China
    2.Department of Computer Science,Central China Normal University,Wuhan 430079,China
    3.The Center for Optimal Control & Discrete Mathematics of Central China Normal University,Wuhan 430079,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-05-21 Published:2007-05-21
  • Contact: YU Ying

基于多分类器集成的手写体金融汉字识别

喻 莹1,2,杨 扬1,董才林3,何秀玲1,3,陈增照1,3   

  1. 1.北京科技大学 信息工程学院,北京 100083
    2.华中师范大学 计算机科学系,武汉 430079
    3.华中师范大学 最优控制与离散数学重点实验室,武汉 430079
  • 通讯作者: 喻 莹

Abstract: We introduce a system that incorporates a global optimization technique based on a genetic algorithm for dynamically selecting the set of classifiers and combination rules to use in the multiple classifiers combination method so as to integrate different classifiers’ superiority and complementarities and improve the classification performance.To this end we test the proposed system on amount Chinese character recognition and investigate the performance of our system in comparison to a number of alternative combination strategies,the results indicate that significant gains can be obtained by integrating genetic algorithm into the multiple classifier systems.

Key words: multiple classifiers combination, genetic algorithm, amount Chinese character

摘要: 用基于遗传算法的全局优化技术动态地选择一组分类器,并根据应用的背景,采用合适的集成规则进行集成,从而综合了不同分类器的优势和互补性,提高了分类性能。实验结果表明,通过将遗传算法引入到多分类器集成系统的设计过程,其分类性能明显优于传统的单分类器的分类方法。

关键词: 多分类器集成, 遗传算法, 金融汉字