全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于非线性PCA神经网络的手写体字符识别

Keywords: 文字识别,主分量分析,神经网络

Full-Text   Cite this paper   Add to My Lib

Abstract:

非线性主分量分析PCA算法与子空间模式识别方法相结合,提出了一种应用于手写体字符识别的基于非线性PCA神经网络的信号重构模型,并与BP网络模型进行了比较实验,结果表明,本文提出的方法,对于0~9手写体数字识别,正确识别率达到了94.74%,而对于a~z手写体字符识别,正确识别率达到了91.03%.

References

[1]  芮挺,沈春林,丁健,等.基于主分量分析的手写数字字符识别[J].小型微型计算机系统,2005,26(2):289-292.RUI Ting,SHEN Chun-lin,DING Jian,et al.Handwritten character recognition using principal component analysis[J]. MINI-MICRO Systems,2005,26(2):289-292.(in Chinese)
[2]  WANG Peng,SUN Guang-min,ZHANG Xin-ming.Handwritten character recognition based on hybrid neural networks[C] //Proceedings of SPIE.USA:SPIE-Int Soc Opt Eng,2001,4555:65-70.
[3]  LIU Cheng-lin,KIM In-jung,KIM Jin-H.Model-based stroke extraction and matching for handwritten Chinese character recognition[J].Pattern Recognition,2001,34:2339-2352.
[4]  LIU C L,NAKAGAWA M.Precise candidate selection for large character set recognition by confidence evaluation[J].IEEE Trans Pattern Anal Mach Intell,2000,22(6):636-642.
[5]  NISHIDA H.Model-based shape matching with structural feature grouping[J].IEEE Trans Pattern Anal Mach Intell, 1995,17(3):315-320.
[6]  ZHANG Bai-ling,FU Min-yue,YAN Hong.A nonlinear neural network model of mixture of local principal component anal- ysis:application to handwritten digits recognition[J].Pattern Recognition,2001,34(2):203-214.
[7]  姜来,张力,张基宏.基于ICA和神经网络的手写体字符识别系统[J].深圳大学学报(理工版),2004,2l(1):61-65.JIANG Lai,ZHANG Li,ZHANG Ji-hong.A handwriting character recognition system based on ICA and neural network [J].Journal of Shenzhen University(Science and Engineering),2004,21(1):61-65.( in Chinese)
[8]  KARHUNEN J,JOUTSENSALO J.Representation and separation of signals using nonlinear PCA type leaning[J ].Neural Networks,1994,7(1):113-127.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133