Realization of handwritten numeral character recognition by supervised locally linear embedding

YANG Xiao-min; WU Wei; HE Xiao-hai; CHEN Mo

doi:null

您当前的位置：

首页 >

文章列表页 >

Realization of handwritten numeral character recognition by supervised locally linear embedding

Article | 更新时间：2020-08-12

- Realization of handwritten numeral character recognition by supervised locally linear embedding
- Optics and Precision Engineering Vol. 17, Issue 3, Pages: 641-647(2009)
- 作者机构：
  
  四川大学电子信息学院图像信息研究所,四川成都,610064
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.43
- Received：22 April 2008，
  
  Revised：10 July 2008，
  
  Published Online：25 March 2009，
  
  Published：25 March 2009
- 稿件说明：
移动端阅览
杨晓敏, 吴炜, 何小海, 陈默. 应用SLLE实现手写体数字识别[J]. 光学精密工程, 2009,17(3): 641-647

YANG Xiao-min, WU Wei, HE Xiao-hai, CHEN Mo. Realization of handwritten numeral character recognition by supervised locally linear embedding[J]. Editorial Office of Optics and Precision Engineering, 2009,17(3): 641-647
杨晓敏, 吴炜, 何小海, 陈默. 应用SLLE实现手写体数字识别[J]. 光学精密工程, 2009,17(3): 641-647 DOI：

YANG Xiao-min, WU Wei, HE Xiao-hai, CHEN Mo. Realization of handwritten numeral character recognition by supervised locally linear embedding[J]. Editorial Office of Optics and Precision Engineering, 2009,17(3): 641-647 DOI：

摘要

针对在手写字符识别中由于书写习惯和风格的不同而造成的字符模式不稳定问题

提出了一种基于流形学习的手写体数字识别方法。在流形学习非监督的基础上引入了监督信息

从而保证高维到低维的映射在保留流形某些结构的同时也可进一步分离不同类别的流形。算法首先利用基于监督的局部线性嵌入(SLLE)对手写体数字图像进行字符特征的降维

然后再对降维后的特征进行分类识别。对MINST库中手写体数字数据库进行了实验

实验结果表明

利用SLLE降维以后的特征能够有效地区分字符

识别率可达到93.27％;由于具有较好的识别率

能够发现高维空间的低维嵌入流形。

Abstract

In order to improve the instability of handwritten character pattern caused by different writing styles

a novel handwritten numeral character recognition approach based on manifold learning is proposed in this paper.Based on non-supervised manifold learning

a supervised information is induced to the algorithm to ensure the map from high dimension to low dimension to retain some manifold structures and also to seperate different kinds of manifolds. By proposed method

Supervised Locally Linear Embedding (SLLE) algorithm is used to reduce the dimensionality of input feature.Then

the reduced feature is classified by simple classifier.Finally

the proposed algorithm is tested on the characters in MINST character database. The experimental results demonstrate that the method can effectively improve the recognition rate to 93.27% and can provide a new approach to the research of handwritten numeral character recognition.

关键词

Keywords

references

PANG Y W,LIU ZH K,YU N H.A new nonlinear feature extraction method for face recognition[J].Neurocomputing,2006,69:949-953.[2] YEASIN M,BULLOT B.Comparison of linear and non-linear data projection techniques in recognizing universal facial expressions[J].Neural Networks,2005(5):3087-3092.[3] WU Y M,CHAN K L,WANG L.Face recognition based on discriminative manifold learnings[J].Pattern Recognition,2004(4):171-174.[4] 聂祥飞,郭军. 利用Gabor小波变换解决人脸识别中的小样本问题[J]. 光学精密工程,2007,15(6):973-977. NIE X F,GUO J.Solution of small sample size problem in face recognition using Gabor wavelet transform[J].Opt. Precision Eng., 2007,15(6):973-977.(in Chinese)[5] 李粉兰, 唐文彦,段海峰,等. 分数次幂多项式核函数在核直接判别式分析中的应用[J]. 光学精密工程, 2007,15(9):1410-1414. LI F L, TANG W Y,DUAN H F, et al..Application of fractional power polynomial kernel function to kernel direct discriminant analysis[J].Opt. Precision Eng.,2007,15(9):1410-1414. (in Chinese)[6] SOUVENIR R,PLESS R.Manifold clustering .In:Proc of the 21st Int’1 Conf on Computer Vision(ICCV’05),Los Alamitos:IEEE Computer Society Press,2005:648-653.[7] ROWEIS S T.Nonlinear dimensionality reduction by locally linear embedding [J].Science,2000,290(5500):2323-2326.[8] SAUL L K,ROWEIS S T.Think globally,fit locally:unsupervised learning of nonlinear manifolds[J].Journal of Machine Learning Research,2003,4(6):119-155.[9] DICK D R,ROBERTP W.Locally linear embedding for classification .http://www.ph.tn tudelft.nl/~dick/ph 2002 01.pdf,2002-1[10] LAWRENCE K S,SAM T R.An introduction to locally linear embedding .http://www.cs.to ronto/~roweis /lle/,2001-06-10.[11] 徐志节,杨杰,王猛. 一种新的彩色图像降维方法[J]. 上海交通大学学报,2004,38(12):2063-2067. XU ZH J,YANG J,WANG M.A new nonlinear dimensionality reduction for color image .Journal of Shanghai Jiaotong University,2004,38(12):2063-2067.(in Chinese)[12] 吴炜,杨晓敏,陈默,等. 一种新颖的人脸图像超分辩率技术[J]. 光学精密工程,2008,16(5):815-821. WU W,YANG X M,CHEN M, et al.. Novel method of face hallucination[J].Opt. Precision Eng.,2008,16(5):815-821.(in Chinese)[13] DUDA R O, HART P E, STORK D G. Pattern Classification(Second Edition)[M]. New York: John Wiley & Sons, 2001.[14] 姜铮铟,丁晓青. 基于MQDF的英文OCR多模板分类器[J]. 计算机工程.2005,31(15):56-58. JIANG ZH Y,DING X Q.English OCR multi-template classification based on modified quadratic discriminant function[J].Computer Engineering, 2005,31(15):56-58.(in Chinese)[15] 王和勇,郑杰,姚正安,等. 基于聚类和改进距离的LLE方法在数据降维中的应用[J]. 计算机研究与发展.2006,43(8):1485-1490. WANG H Y,ZHENG J,YAO ZH A, et al..Application of dimension reduction on using improved LLE based on clustering[J].Journal of Computer Research and Development ,2006,43(8):1485-1490.(in Chinese)

Views

480

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Semi-supervised dual path network for hyperspectral image classification

Deep manifold reconstruction belief network for hyperspectral remote sensing image classification

Multi-features manifold discriminant embedding for hyperspectral image classification

Hyper-spectral image classification using spatial-spectral manifold reconstruction

Classification of Hyperspectral remote sensing images using correlation neighbor LLE

Related Author

Zhengying LI

Ling JI

Zhen ZHANG

Hong HUANG

Zheng-ying LI

Hong HUANG

Zheng-ying LI

Guang-yao SHI

Related Institution

Key Laboratory of Optoelectronic Technology and System， Ministry of Education， Chongqing University

The 34th Research Institute of China Electronics Technology Group Corporation

Key Laboratory of Optoelectronic Technique System of the Ministry of Education, Chongqing University

Key Laboratory of Opto-electronic Technique of the Ministry of Education, Chongqing University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰