基于2DPCA+PCA与SVM的人脸识别

详细信息    查看全文 | 推荐本文 |

英文篇名：Face recognition based on 2DPCA + PCA and SVM 作者：杨梅芳 ; 石义龙 英文作者：YANG Mei-fang;SHI Yi-long;School of Computer Science and Technology,Wuhan University of Technology; 关键词：人脸识别 ; 主成分分析 ; 支持向量机 ; 遗传算法 ; 2DPCA 英文关键词：face recognition;;PCA;;SVM;;GA;;2DPCA 中文刊名：HDZJ 英文刊名：Information Technology 机构：武汉理工大学计算机科学与技术学院; 出版日期：2018-02-25 出版单位：信息技术 年：2018 基金：湖北省自然科学基金项目资助(2013CFB351) 语种：中文; 页：HDZJ201802008 页数：5 CN：02 ISSN：23-1557/TN 分类号：40-44

摘要

为了提高传统PCA与SVM相结合的人脸识别算法的性能,文中提出了一种基于双向压缩的2DPCA+PCA与遗传算法SVM相结合的人脸识别算法。该算法采用双向压缩的2DPCA与PCA相结合的算法来进行人脸特征提取,有效地减少了特征数量和PCA模型的计算时间;在与SVM相结合时,其训练时间和识别时间都有所降低,且提高了识别率;同时为了进一步提高SVM的性能,文中采用遗传算法来进行SVM参数寻优,并使用交叉测试识别率来作为适应度函数。在ORL人脸库上的实验表明,该算法的性能明显高于传统PCA与SVM相结合的人脸识别算法。
        To improve the performance of the face recognition algorithm based on PCA and SVM,this paper puts forward a novel method based on bi-directional compression 2 DPCA + PCA and GA-based SVM,which uses bi-directional compression 2 DPCA combined with PCA for facial feature extraction,effectively reducing the number of features and the computation time of PCA model. It combined with SVM,the training and recognition time are reduced,and the recognition rate is improved. Meanwhile,in order to further improve the performance of SVM,it uses genetic algorithm( GA) to optimize SVM parameters,and apply the cross-test results for a fitness function. The experiments on ORL face database show that the performance of the algorithm is significantly higher than the traditional face recognition algorithm based on PCA and SVM.

引文

[1]ZHANG Cui-ping,SU Guang-da.Human Face Recognition:A Survey[J].JOURNAL OF IMAGE AND GRAPHICS,2000,5(11):885-894.
    [2]Faruqe M O,Hasan M A M.Face recognition using PCA and SVM[C]∥Anti-counterfeiting,Security,and Identification in Communication,2009.ASID 2009.3rd International Conference on IEEE,2009:97-101.
    [3]LI Juan,HE Wei,ZHANG Ling,et al.Face recognition combined bidirectional 2DPCA with PCA[J].Journal of Computer Applications,2009,29(z1):245-246.
    [4]ZHang Yan-kun,Du Ping,Liu Chong-qing.A Face Recognition Method Based on Principal Component Analysis and Support Vector Machine[J].Journal ofshanghai Jiaotong University,2002,36(6):884-886.
    [5]Wang Hong-man,Ou Zhong-yin.Face Recognition Based on Features by PCA/ICA and Classification with SVM[J].Journal of Computeraided Design&Computer Graphics,2003,15(4):416-420.
    [6]ZHANG Sheng-liang,YANG Jing-yu.Face Recognition of Combining Two Dimensional Projection with PCA[J].Computer Engineering,2006,32(16):165-166.
    [7]ZHU Lei,ZHU Shan-an.Face recognition based on two-dimensional image principal component analysis[J].Journal of Zhejiang University-Science,2007,41(2):264-267.
    [8]Yang J,Zhang D,Frangi A F,et al.Two-dimensional PCA:a new approach to appearance-based face representation and recognition[J].Pattern Analysis&Machine Intelligence IEEE Transactions on,2004,26(1):131-137.
    [9]XIA Yong-quan,JO Kang-hyun,GAN Yong,et al.Review of intelligent transportation system based on computer vision[J].Journal of Zhengzhou University of Light Industry(Natural Science Edition),2014,(6):52-60.
    [10]Wang H J,Jia-Qiang E,Deng F Q.A novel adaptive mutative scale optimization algorithm based on chaos genetic method and its optimization efficiency evaluation[J].Journal of Central South University,2012,19(9):2554-2560.
    [11]Adin Ramirez R,Jorge Rojas C,Oksam C.Local Directional Number Pattern for Face Analysis:Face and Expression Recognition[J].Image Processing IEEE Transactions on,2013,22(5):1740-1752.
    [12]Hung Chi-cheng,Li Cheng-huan,Jin-Shiuh Taur,et al.A KernelBased Feature Selection Method for SVM With RBF Kernel for Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(1):317-326.
    [13]Karim T F,Lipu M S H,Rahman M L,et al.Face recognition using PCA-based method[J].Advanced Management Science IEEE International Conference,2010,3:158-162.