计算机科学 ›› 2019, Vol. 46 ›› Issue (6A): 274-278.

• 模式识别与图像处理 • 上一篇    下一篇

基于SPCA和HOG的单样本人脸识别算法

韩旭1, 谌海云1, 王溢2, 许瑾1   

  1. 西南石油大学电气信息学院 四川 南充6370011;
    辽宁工程技术大学电子与信息工程学院 辽宁 葫芦岛1251052
  • 出版日期:2019-06-14 发布日期:2019-07-02
  • 作者简介:韩 旭(1991-),男,硕士生,主要研究方向为计算机视觉、模式识别;谌海云(1967-),男,硕士,教授,主要研究方向为机器人自动化控制,E-mail:1921600392@qq.com;王 溢(1997-),女,主要研究方向为电路与系统、模式识别;许 瑾(1980-),女,硕士,讲师,主要研究方向为智能控制。
  • 基金资助:
    本文受南充市校科技战略合作专项项目(NC17SY4011)资助。

Face Recognition Using SPCA and HOG with Single Training Image Per Person

HAN Xu1, CHEN Hai-yun1, WANG Yi2, XU Jin1   

  1. School of Electrical Engineering and Information,Southwest Petroleum University,Nanchong,Sichuan 637001,China1;
    School of Electronic and Information Engineering,Liaoning University of Engineering and Technology,Huludao,Liaoning 125105,China2
  • Online:2019-06-14 Published:2019-07-02

摘要: 基于单样本的人脸识别是一项充满挑战性的任务。文中结合Similar Principal Component Analysis(SPCA)算法与Histograms of Oriented Gradients(HOG)算法,利用SPCA筛选出图像类的相似信息,用HOG算法对相似的信息块进行特征量化,使二者优势互补。最后利用Pearson correlation(PC)进行相似性判别,在数据库Extended Yale B database上进行实验,结果表明,在光照变化的情况下,该算法对人脸正面图像的识别性能比传统算法好。

关键词: 人脸识别, SPCA, HOG, Pearsoncorrelation(PC)

Abstract: Face recognition based on single sample is a challenging task.This paper combined the Similar Principal Component Analysis (SPCA) algorithm and Histograms of Oriented Gradients (HOG) algorithm,and used SPCA to screen out the similar information of the image class,and quantified the similar information blocks with HOG algorithm to make the two advantages complementary.Finally,we used Pearson correlation (PC) to identify similarity and conduct experiments on the Extended Yale B database.Experimental results show that the proposed algorithm has better recognition performance than traditional algorithm when the illumination of the face image changes.

Key words: Face recognition, Similar principal component analysis (SPCA), Histograms of oriented gradients(HOG), Pearson correlation (PC)

中图分类号: 

  • TP391
[1] 左腾.人脸识别技术综述[J].软件导刊,2017(2):182-185.
[2] 肖梦佳.基于图像识别的施工现场智能监控系统的相关技术研究与实现[D].成都:电子科技大学,2016.
[3] 马园园.人脸识别技术与考勤系统应用研究[D].南京:南京邮电大学,2017.
[4] 何志威,李军.基于人脸识别的移动终端考勤系统的设计[J].福建电脑,2018,34(3):19-20.
[5] 杨秀坤,岳新启,汲清波.基于HOG和DMMA的单样本人脸识别[J].计算机应用研究,2015(2):627-629.
[6] 杨恢先,翟云龙,蔡勇勇,等.基于中心对称梯度幅值相位模式的单样本人脸识别[J].光电子·激光,2015(5):969-977.
[7] 覃磊,李德华,周康.基于QR分解与2DLDA的单样本人脸识别[J].微电子学与计算机,2015(2):65-68.
[8] YANG M,VAN L,ZHANG L.Sparse Variation Dictionary Learning for Face Recognition with a Single Training Sample per Person[C]∥2013 IEEE International Conference on Computer Vision(ICCV).IEEE,2013:689-696.
[9] 韩旭,刘强,许瑾,谌海云.基于伪PCA的手写数字识别算法[J].计算机科学,2018,45(S2):278-281,307.
[10] DALAL,NAVNEET,TRIGGS,et al.Histograms of Oriented Gradients for Human Detection[C]∥IEEE International Conference on Computer Vision and Pattern Recognition,CVPR 2005.2005:886-893.
[11] RAHMAN N A.A course in theoretical statistics for sixth forms,technical colleges,colleges of education,universities[M].Charles Griffin & Company Limited,1969.
[12] BUDA A,JARYNOWSKI A.Life time of correlations and its applications[M].ABRASCO-Associação Brasileira de Saúde Coletiva,2010:459-470.
[13] https://en.wikipedia.org/wiki/Pearson_correlation_coefficient.
[14] http://www.realstatistics.com/correlation/basic-concepts-correlation.
[15] JR J S.The Relationship between the Coefficient of Correlation and the Angle included between Regression Lines[J].Journal of Educational Research,1947,41(4):311-313.
[16] http://www.hawaii.edu/powerkills/UC.HTM.
[17] LEE K C,HO J,KRIEGMAN D J.Acquiring Linear Subspaces for Face Recognition under Variable Lighting[J].IEEE Tran-sactions on Pattern Analysis & Machine Intelligence,2005,27(5):684-698.
[18] GEORGHIADES A S,BELHUMEUR P N,KRIEGMAN D J.From few to many:illumination cone models for face recognition under variable lighting and pose[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2002,23(6):643-660.
[19] CORTES C,VAPNIK V.Support vector machines[J].Machine Learning,1995,20:273-293.
[20] COVER T,HART P.Nearest neighbor pattern classification [J].IEEE Trans.inf.theory,1967,13(1):21-27.
[21] WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2008,31(2):210-227.
[22] LOUGHERY J.Making FLDA applicable to face recognition with one sample per person[J].Pattern Recognition,2004,37(7):1553-1555.
[23] ZHANG L,YANG M,FENG X.Sparse representation or collaborative representation:Which helps face recognition?[C]∥IEEE International Conference on Computer Vision(ICCV 2011).Bacelona,Spain:IEEE,2011:471-478.
[24] SU Y,SHAN S,CHEN X,et al.Adaptive generic learning for face recognition from a single sample per person[C]∥Computer Vision and Pattern Recognition.IEEE,2010:2699-2706.
[25] LU J,TAN Y P,WANG G.Discriminative Multimanifold Ana-lysis for Face Recognition from a Single Training Sample per Person[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,35(1):39-51.
[26] KUMAR R,BANERJEE A,VEMURI B C,et al.Maximizing all margins:Pushing face recognition with Kernel Plurality[C]∥International Conference on Computer Vision.IEEE,2011:2375-2382.
[27] DENG W,HU J,GUO J.Extended SRC:Undersampled Face Recognition via Intraclass Variant Dictionary[J].IEEE Tran-sactions on Pattern Analysis & Machine Intelligence,2012,34(9):1864-1870.
[28] ZHU P,ZHANG L,HU Q,et al.Multi-scale Patch Based Collaborative Representation for Face Recognition with Margin Distribution Optimization[C]∥European Conference on Computer Vision.IEEE,2012:822-835.
[29] ZHU P,YANG M,ZHANG L,et al.Local Generic Representation for Face Recognition with Single Sample per Person[M].Springer International Publishing,2014:41-50.
[1] 吴庆洪, 高晓东. 稀疏表示和支持向量机相融合的非理想环境人脸识别[J]. 计算机科学, 2020, 47(6): 121-125.
[2] 李新豆,高陈强,周风顺,韩慧,汤林. 基于图像扩散速度模型和纹理信息的人脸活体检测[J]. 计算机科学, 2020, 47(2): 112-117.
[3] 金堃, 陈少昌. 步态识别现状与发展[J]. 计算机科学, 2019, 46(6A): 30-34.
[4] 陈晋音, 王桢, 陈劲聿, 陈治清, 郑海斌. 基于深度学习的智能教学系统的设计与研究[J]. 计算机科学, 2019, 46(6A): 550-554.
[5] 李梦潇, 姚仕元. 基于PCA的人脸识别系统的设计与改进[J]. 计算机科学, 2019, 46(6A): 577-579.
[6] 杨柳, 陈丽敏, 易玉根. 基于自适应加权子模式判别邻域投影的人脸识别方法[J]. 计算机科学, 2019, 46(10): 307-310.
[7] 包晓安, 林晓东, 张娜, 徐璐, 吴彪. 应用色彩纹理特征的人脸防欺骗算法[J]. 计算机科学, 2019, 46(10): 180-185.
[8] 王燕, 王双印. 基于卷积神经网络的人脸信息增强识别研究[J]. 计算机科学, 2018, 45(8): 268-271.
[9] 严娇娇,种兰祥,李婷. 一种人手背静脉特征识别方法[J]. 计算机科学, 2018, 45(6A): 206-209.
[10] 王雪峤,齐华山,袁家政,梁爱华,孙力红. 二维Gabor特征与三维NP-3DHOG特征融合的人脸识别算法[J]. 计算机科学, 2018, 45(6A): 247-251.
[11] 娄雪, 闫德勤, 王博林, 王族. 一种改进的邻域保持嵌入算法[J]. 计算机科学, 2018, 45(6A): 255-258.
[12] 李小薪,吴克宋,齐盼盼,周旋,刘志勇. 局部球面规范化嵌入:PCANet的一种改进方案[J]. 计算机科学, 2018, 45(5): 238-242.
[13] 李小薪,李晶晶,贺霖,刘志勇. 基于噪声空间结构嵌入和高维梯度方向嵌入的鲁棒人脸识别方法[J]. 计算机科学, 2018, 45(4): 285-290.
[14] 卢涛,管英杰,潘兰兰,张彦铎. 基于低秩约束的极限学习机高效人脸识别算法[J]. 计算机科学, 2018, 45(3): 294-299.
[15] 高放,黄樟钦. 基于异构多核并行加速的嵌入式神经网络人脸识别方法[J]. 计算机科学, 2018, 45(3): 288-293.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[2] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[3] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[4] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[5] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[6] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[7] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[8] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[9] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .
[10] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .