基于二维主成分分析与卷积神经网络的手写体汉字识别

doi:10.11772/j.issn.1001-9081.2020010081

计算机应用 ›› 2020, Vol. 40 ›› Issue (8): 2465-2471.DOI: 10.11772/j.issn.1001-9081.2020010081

• 应用前沿、交叉与综合 • 上一篇下一篇

基于二维主成分分析与卷积神经网络的手写体汉字识别

郑延斌^1,2, 韩梦云¹, 樊文鑫¹

1. 河南师范大学计算机与信息工程学院, 河南新乡 453007;
2. 智慧商务与物联网技术河南省工程实验室(河南师范大学), 河南新乡 453007

收稿日期:2020-02-04 修回日期:2020-03-23 出版日期:2020-08-10 发布日期:2020-03-28
通讯作者: 韩梦云(1992-),女,河南安阳人,硕士研究生,主要研究方向:虚拟现实、汉字识别,1142767966@qq.com
作者简介:郑延斌(1964-),男,河南内乡人,教授,博士,CCF会员,主要研究方向:虚拟现实、多智能体系统、对策论;樊文鑫(1994-),男,河南郑州人,硕士研究生,主要研究方向:虚拟现实、多智能体系统。
基金资助:
国家自然科学基金资助项目（U1604156）；河南师范大学青年基金资助项目（2017QK20）。

Handwritten Chinese character recognition based on two dimensional principal component analysis and convolutional neural network

ZHENG Yanbin^1,2, HAN Mengyun¹, FAN Wenxin¹

1. College of Computer and Information Engineering, Henan Normal University, Xinxiang Henan 453007, China;
2. Henan Engineering Laboratory of Intellectual Business and Internet of Things Technologies(Henan Normal University), Xinxiang Henan 453007, China

Received:2020-02-04 Revised:2020-03-23 Online:2020-08-10 Published:2020-03-28
Supported by:
This work is partially supported by the National Natural Science Foundation of China (U1604156), the Henan Normal University Youth Fund (2017QK20).

摘要/Abstract

摘要： 随着计算能力的飞速增长、训练数据的不断积累以及非线性激活函数的不断完善，卷积神经网络（CNN）在手写体汉字识别中表现出较好的识别性能。针对CNN识别手写体汉字识别速度慢的问题，将二维主成分分析（2DPCA）与CNN相结合识别手写体汉字。首先，利用2DPCA提取手写体汉字的投影特征向量；然后，将得到的投影特征向量组成特征矩阵；其次，用组成的特征矩阵作为CNN的输入；最后，用Softmax函数进行分类。与基于AlexNet的CNN模型相比，所提方法的运行时间降低了78%，与基于ACNN与DCNN的模型相比，所提方法的运行时间分别降低了80%与73%。实验结果表明，该方法在不降低识别精度的同时，可以减少识别手写体汉字的运行时间。

关键词: 手写体汉字识别, 深度学习, 卷积神经网络, 二维主成分分析, 图像分类

Abstract: With the rapid growth of computing power, the accumulation of training data and the improvement of nonlinear activation function, Convolutional Neural Network (CNN) has a good recognition performance in handwritten Chinese character recognition. To solve the problem of slow speed of CNN for handwritten Chinese character recognition, Two Dimensional Principal Component Analysis (2DPCA) and CNN were combined to identify handwritten Chinese characters. Firstly, 2DPCA was used to extract the projection eigenvectors of handwritten Chinese characters. Secondly, the obtained projection eigenvectors were formed into an eigenmatrix. Thirdly, the formed eigenmatrix was used as the input of CNN. Finally, the softmax function was used for classification. Compared with the model based on AlexNet, the proposed method has the running time reduced by 78%; and compared with the model based on ACNN and DCNN, the proposed method has the running time reduced by 80% and 73%, respectively. Experimental results show that the proposed method can reduce the running time of handwritten Chinese character recognition without reducing the recognition accuracy.

Key words: handwritten Chinese character recognition, deep learning, Convolutional Neural Network (CNN), Two Dimensional Principal Component Analysis (2DPCA), image classification

中图分类号:

TP391

郑延斌, 韩梦云, 樊文鑫. 基于二维主成分分析与卷积神经网络的手写体汉字识别[J]. 计算机应用, 2020, 40(8): 2465-2471.

ZHENG Yanbin, HAN Mengyun, FAN Wenxin. Handwritten Chinese character recognition based on two dimensional principal component analysis and convolutional neural network[J]. Journal of Computer Applications, 2020, 40(8): 2465-2471.

参考文献

[1] 赵继印,郑蕊蕊,吴宝春,等. 脱机手写体汉字识别综述[J]. 电子学报, 2010, 38(2):405-415. (ZHAO J Y, ZHENG R R, WU B C, et al. A review of off-line handwritten Chinese character recognition[J]. Acta Electronica Sinica, 2010, 38(2):405-415.)
[2] ZHOU M, ZHANG X, YIN F, et al. Discriminative quadratic feature learning for handwritten Chinese character recognition[J]. Pattern Recognition, 2016, 49:7-18.
[3] 毛晓波,程志远,周晓东. 基于特征图叠加的脱机手写体汉字识别[J].郑州大学学报(理学版), 2018, 50(3):78-82. (MAO X B, CHENG Z Y, ZHOU X D. Offline handwritten Chinese character recognition based on feature map superposition[J]. Journal of Zhengzhou University (Natural Science Edition), 2018, 50(3):78-82.)
[4] XIAO X, JIN L, YANG Y, et al. Building fast and compact convolutional neural networks for offline handwritten Chinese character recognition[J]. Pattern Recognition, 2017, 72:72-81.
[5] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[6] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Red Hook:Curran Associates, Inc, 2012:1097-1105.
[7] CIREŞAN D, MEIER U. Multi-column deep neural networks for offline handwritten Chinese character classification[C]//Proceedings of the 2015 International Joint Conference on Neural Networks. Piscataway:IEEE, 2015:1-6.
[8] 柴伟佳,王连明. 卷积神经网络的多字体汉字识别[J]. 中国图象图形学报, 2018, 23(3):410-417. (CHAI W J, WANG L M. Recognition of Chinese characters using deep convolutional neural network[J]. Journal of Image and Graphics, 2008, 23(3):410-417.)
[9] ZHONG Z, JIN L, XIE Z. High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps[C]//Proceedings of the 13th International Conference on Document Analysis and Recognition. Piscataway:IEEE, 2015:846-850.
[10] ZHANG X, BENGIO Y, LIU C. Online and offline handwritten Chinese character recognition:a comprehensive study and new benchmark[J]. Pattern Recognition, 2017, 61:348-360.
[11] LI Z, TENG N, JIN M, et al. Building efficient CNN architecture for offline handwritten Chinese character recognition[J]. International Journal on Document Analysis and Recognition, 2018, 21(4):233-240.
[12] 赵秀红. 基于主成分分析的特征提取的研究[D]. 西安:西安电子科技大学, 2016:23-25. (ZHAO X H. Research on feature extraction based on principal component analysis[D]. Xi'an:Xidian University, 2016:23-25.)
[13] HE Z, ZHONG Y, CAO Y. High accuracy handwritten Chinese character recognition based on support vector machine and independent component analysis[M]//DU W. Informatics and Management Science V, LNEE 208. London:Springer, 2013:725-733.
[14] 徐久成,黄方舟,穆辉宇,等. 基于PCA和信息增益的肿瘤特征基因选择方法[J]. 河南师范大学学报(自然科学版), 2018, 46(2):104-112. (XU J C, HUANG F Z, MU H Y, et al. Tumor feature gene selection method based on PCA and information gain[J]. Journal of Henan Normal University (Natural Science Edition), 2018, 46(2):104-112.)
[15] 张成,李娜,李元,等. 核参数判别选择方法在核主元分析中的应用[J]. 计算机应用, 2014, 34(10):2895-2898. (ZHANG C, LI N, LI Y, et al. Application of kernel parameter discriminant method in kernel principal component analysis[J]. Journal of Computer Applications, 2014, 34(10):2895-2898.)
[16] 陈伏兵,陈秀宏,张生亮,等. 基于模块2DPCA的人脸识别方法[J]. 中国图象图形学报, 2006, 11(4):580-585. (CHEN F B, CHEN X H, ZHANG S L, et al. A human face recognition method based on modular 2DPCA[J]. Journal of Image and Graphics, 2006, 11(4):580-585.)
[17] YANG J, ZHANG D, FRANGI A F, et al. Two-dimensional PCA:a new approach to appearance-based face representation and recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1):131-137.
[18] LIU K, CHENG Y, YANG J. Algebraic feature extraction for image recognition based on an optimal discriminant criterion[J]. Pattern Recognition, 1993, 26(6):903-911.
[19] YANG J, YANG J. From image vector to matrix:a straightforward image projection technique-IMPCA vs. PCA[J]. Pattern Recognition, 2002, 35(9):1997-1999.
[20] 孙瑞霞,汪亚明,黄文清. 基于GA的2DPCA在人脸识别中的应用[J].计算机工程与设计, 2007, 28(10):2398-2400. (SUN R X, WANG Y M, HUANG W Q. Application of 2DPCA in face recognition based on GA[J]. Computer Engineering and Design, 2007, 28(10):2398-2400.)
[21] 陈伏兵,陈秀宏,高秀梅,等. 二维主成分分析方法的推广及其在人脸识别中的应用[J]. 计算机应用, 2005, 25(8):1767-1770. (CHEN F B, CHEN X H, GAO X M, et al. Generalization of 2DPCA and its application in face recognition[J]. Journal of Computer Applications, 2005, 25(8):1767-1770.)
[22] 胡娜,马慧,湛涛. 融合LBP纹理特征与B2DPCA技术的手指静脉识别方法[J]. 智能系统学报, 2019, 14(3):533-540. (HU N, MA H, ZHAN T. Finger vein recognition method combining LBP texture feature and B2DPCA technology[J]. CAAI Transactions on Intelligent Systems, 2019, 14(3):533-540.)
[23] 闫荣华,彭进业,汶德胜. PCA与2DPCA的关系[J]. 计算机科学, 2017, 44(11A):202-206, 216. (YAN R H, PENG J Y, WEN D S. Relationship between PCA and 2DPCA[J]. Computer Science, 2017, 44(11A):202-206, 216.)
[24] GAO X, WEN W, JIN L. A new feature optimization method based on two-directional 2DLDA for handwritten Chinese character recognition[C]//Proceedings of the 2011 International Conference on Document Analysis and Recognition. Piscataway:IEEE, 2011:232-236.

基于二维主成分分析与卷积神经网络的手写体汉字识别

Handwritten Chinese character recognition based on two dimensional principal component analysis and convolutional neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[2]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[3]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[4]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[5]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[8]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[9]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[10]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[11]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[12]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[13]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[14]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[15]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.