The Diversity of Classifiers and Its Applications to Combination

The Diversity of Classifiers and Its Applications to Combination

下载PDF

导出

摘要 In various application areas of pattern recognition, combing multiple classifiers is regarded as a new method for achieving a substantial gain in performance of systems. This paper discusses the properties of the diversity of classifiers and its applications. At the same time, the paper presents a novel method for combining multiple classifiers based on the diversity. Fusion strategies are discussed for providing a basis for combing classifiers. These combination strategies are experimentally tested on online handwritten Chinese character recognition system and their effectiveness is considered. In various application areas of pattern recognition, combing multiple classifiers is regarded as a new method for achieving a substantial gain in performance of systems. This paper discusses the properties of the diversity of classifiers and its applications. At the same time, the paper presents a novel method for combining multiple classifiers based on the diversity. Fusion strategies are discussed for providing a basis for combing classifiers. These combination strategies are experimentally tested on online handwritten Chinese character recognition system and their effectiveness is considered.

作者林磊 Wang Xiaolong Liu Jiafeng

机构地区 Department of Computer Science and Engineering Department of Computer Science and Engineering

出处《High Technology Letters》 EI CAS 2002年第4期33-36,共4页 高技术通讯（英文版）

基金 SupportedbytheNationalNaturalScienceFoundationofChinaandtheScientificResearchFoundationofHarbinInstituteofTechnology

关键词 COMBING multiple classifiers diversity FUSION strategies handwritten Chinese CHARACTER recognition combing multiple classifiers, diversity, fusion strategies, handwritten Chinese character recognition

分类号 TP391.41 [自动化与计算机技术—计算机应用技术]

引文网络
相关文献

参考文献8

1[1]Suen C Y, Nadal C, Mai T A, et al. Recognition of totally unconstrained handwritten numerals based on the concept of multiple experts, Frontiers in Handwriting Recognition.In:Suen C Y, ed., Proc. Int. Workshop on Frontiers in Handwriting Recognition, Montreal, Canada, Apr.1990.131
2[2]Ho T K, Hull J, Srihari S N. Combination of structural classifiers.In:Proc. 1990 IAPR Workshop Syntactic and Structural Patter Recog.,1990,6:123
3[3]Kittler J, Hatef M, Duin R P W. Combining classifiers.In:ICP96, 1996,2:897
4[4]Kittler J, Hatef M, Duin R P W, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(3):226[5] Cho S B, Kim J H. IEEE Trans Neural Network, 1995,6(2):497
5[5]Kimura F and Shridhar M. Pattern Recognition, 1991,24(10):969
6[6]Rogova G. Neural Networks, 1994,7(5):777
7[7]Kittler J, Hojjatoleslami S A. A weighted combination of classifiers employing shared and distinct representations. In: Proc. Conference on CVPR, 1998.924
8[8]Kittler J, Hatef M, Duin R P W, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998,20(3):226

1刘家锋,唐降龙,舒文豪.A Structure Similarity Analysis Method for On－Line Recognition of Handwritten Chinese Characters[J].Journal of Harbin Institute of Technology(New Series),1994,1(1):51-54.
2郝红卫,戴汝为.An integration approach to handwritten Chinese character recognition system[J].Science China(Technological Sciences),1998,41(1):101-105. 被引量：1
3钱国良,王亚东,舒文豪.A 4-Corner Codes Classifier Based on Decision Tree Inductive Learning for Handwritten Chinese Characters[J].Journal of Harbin Institute of Technology(New Series),1998,5(2):26-31.
4Xiaofan Lin,Xiaoqing Ding,Youshou Wu.Theoretical analysis of the confidence metrics for nearestneighbor classifier[J].Chinese Science Bulletin,1998,43(6):464-467.
5唐降龙,舒文豪,刘家锋,李铁才.Data　Pre－processing　and　Stroke　Segment　Extraction　for　On－line　Handwritten　Chinese　Character　Recognition[J].Journal of Harbin Institute of Technology(New Series),1996,3(3):76-81.
6石大明,唐降龙,刘家锋,舒文豪.Two Types of Features and Their Extractions in Handwritten Chinese Character Recognition[J].Journal of Harbin Institute of Technology(New Series),1997,4(2):39-42.
7模式识别[J].电子科技文摘,2002,0(5):145-146.
8AbbasH Xiang-LongTang Jia-FengLiu WeiZhao.基于HMM的印刷体阿拉伯文字符识别[J].Journal of Computer Science & Technology,2004,19(C00):61-61.
9廖湖声.An Action Analysis for Combining Partial Evaluation[J].Journal of Computer Science & Technology,2000,15(2):196-200.
10ZHANG Guangyuan,LI jingjiao,WANG Aixia.Wavelet Neural Network for Handwritten Manchu Character Unit Recognition[J].现代电子技术,2007,30(1):118-120.

High Technology Letters

2002年第4期

浏览历史

内容加载中请稍等...

The Diversity of Classifiers and Its Applications to Combination

参考文献8

相关作者

相关机构

相关主题

浏览历史