您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报(工学版) ›› 2015, Vol. 45 ›› Issue (1): 9-12.doi: 10.6040/j.issn.1672-3961.2.2014.091

• 机器学习与数据挖掘 • 上一篇    下一篇

一种改进的协方差鉴别学习方法

任捷怡, 吴小俊   

  1. 江南大学物联网工程学院, 江苏 无锡 214122
  • 收稿日期:2015-05-23 修回日期:2014-12-11 出版日期:2015-02-20 发布日期:2015-05-23
  • 通讯作者: 吴小俊(1967-),男,江苏丹阳人,教授,博士,主要研究方向为模式识别.E-mail:xiaojun_wu_jnu@163.com E-mail:xiaojun_wu_jnu@163.com
  • 作者简介:任捷怡(1988-),男,江苏无锡人,博士研究生,主要研究方向为模式识别.E-mail:alvisland@gmail.com
  • 基金资助:
    国家自然科学基金资助项目(61373055)

An improved method of covariance discriminative learning

REN Jieyi, WU Xiaojun   

  1. School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, Jiangsu, China
  • Received:2015-05-23 Revised:2014-12-11 Online:2015-02-20 Published:2015-05-23

摘要: 以协方差鉴别学习(covariance discriminative learning, CDL)为基础,对图像集的隶属于黎曼流形之上的协方差矩阵进行双向降维。将降维后的协方差矩阵与有效的黎曼度量,如对数欧氏距离(log euclidean distance, LED)结合得到一个核函数来将这些协方差矩阵映射到欧式空间中进行分类。改进的CDL方法由于减少了协方差矩阵的维数,从而降低了计算复杂度并提高了分类精度。通过在标准数据集上的实验,验证了该改进方法的有效性。

关键词: 人脸识别, 黎曼度量, 协方差矩阵, 鉴别分析, 物体分类

Abstract: Based on the original Covariance Discriminative Learning method, a bidirectional dimension reduction was applied on those covariance matrices, which lied on a Riemannian manifold. Combining these covariance matrices with an efficient Riemannian metric, i.e., log euclidean distance (LED), a kernel function that mapped the covariance matrix from Riemannian manifold to Euclidean space for classification was derived. As a result of dimension reduction of covariance matrices, this method improved accuracy of classification and reduced the complexity of computation. The results were observed through experiments on standard datasets.

Key words: discriminant analysis, riemannian metric, face recognition, covariance matrix, object classification

中图分类号: 

  • TP391.4
[1] ARANDJELOVIC O, SHAKHNAROVICH G, FISHER J, et al. Face recognition with image sets using manifold density divergence[C]//Computer Vision and Pattern Recognition, 2005. San Diego: IEEE, 2005:581-588.
[2] CEVIKALP H, TRIGGS B. Face recognition based on image sets[C]//Computer Vision and Pattern Recognition, 2010. San Francisco: IEEE, 2010:2567-2573.
[3] HU Y, MIAN A S, OWENS R. Face recognition using sparse approximated nearest points between image sets[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2012, 34(10):1992-2004.
[4] WANG R, SHAN S, CHEN X, et al. Manifold-manifold distance with application to face recognition based on image set[C]//Computer Vision and Pattern Recognition, 2008. Anchorage: IEEE, 2008:1-8.
[5] WANG R, CHEN X. Manifold discriminant analysis[C]//Computer Vision and Pattern Recognition, 2009. Miami: IEEE, 2009:429-436.
[6] KIM M, KUMAR S, PAVLOVIC V, et al. Face tracking and recognition with visual constraints in real-world videos[C]//Computer Vision and Pattern Recognition, 2008. Anchorage:IEEE, 2008:1-8.
[7] KIM T K, ARANDJELOVIC O, CIPOLLA R. Boosted manifold principal angles for image set-based recognition[J]. Pattern Recognition, 2007, 40(9):2475-2484.
[8] KIM T K, KITTLER J, CIPOLLA R. Discriminative learning and recognition of image set classes using canonical correlations[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2007, 29(6):1005-1018.
[9] TURK M, Pentland A. Eigenfaces for recognition[J]. Journal of cognitive neuroscience, 1991, 3(1):71-86.
[10] BELHUMUR P N, HESPANHA J P, KRIEGMAN D. Eigenfaces vs. fisherfaces:Recognition using class specific linear projection[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1997, 19(7):711-720.
[11] WANG R, GUO H, DAVIS L S, et al. Covariance discriminative learning: A natural and efficient approach to image set classification[C]//Computer Vision and Pattern Recognition, 2012. Rhode Island: IEEE, 2012:2496-2503.
[12] ARSIGNY V, FILLARD P, PENNEC X, et al. Geometric means in a novel vector space structure on symmetric positive-definite matrices[J]. SIAM journal on matrix analysis and applications, 2007, 29(1):328-347.
[13] JAYASUMANA S, HARTLEY R, SALZMAN M, et al. Kernel methods on the riemannian manifold of symmetric positive definite matrices[C]//Computer Vision and Pattern Recognition, 2013. Portland: IEEE, 2013:73-80.
[14] FISHER R A. The use of multiple measurements in taxonomic problems[J]. Annals of Eugenics, 1936, 7(2):179-188.
[15] BAUDAT G, ANOUAR F. Generalized discriminant analysis using a kernel approach[J]. Neural Computation, 2000, 12(10):2385-2404.
[16] 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 and Machine Intelligence, IEEE Transactions on, 2004, 26(1):131-137.
[17] ZHANG D, ZHOU Z H. (2D) 2PCA: two-directional two-dimensional PCA for efficient face representation and recognition[J]. Neurocomputing, 2005, 69(1):224-231.
[18] LEE K C, HO J, YANG M H, et al. Video-based face recognition using probabilistic appearance manifolds[C]//Computer Vision and Pattern Recognition, 2003. Madison: IEEE, 2003:313-320.
[19] LEIBE B, SCHIELE B. Analyzing appearance and contour based methods for object categorization[C]//Computer Vision and Pattern Recognition, 2003. Madison: IEEE, 2003:1-7.
[20] VIOLA P, JONES M J. Robust real-time face detection[J]. International journal of computer vision, 2004, 57(2):137-154.
[1] 张振月,李斐,江铭炎. 基于低秩表示投影的无监督人脸特征提取[J]. 山东大学学报(工学版), 2018, 48(1): 15-20.
[2] 周凯,元昌安,覃晓,郑彦,冯文铎. 基于核贝叶斯压缩感知的人脸识别[J]. 山东大学学报(工学版), 2016, 46(3): 74-78.
[3] 谢志华. 一种新的血流建模方法及其在红外人脸识别中的应用[J]. 山东大学学报(工学版), 2013, 43(5): 1-5.
[4] 郭慧玲,王士同*,闫晓波. 基于广义旋转不变性核函数的人脸识别[J]. 山东大学学报(工学版), 2012, 42(5): 71-79.
[5] 曹红根1,袁宝华1,朱辉生2. 结合对比度信息与LBP的分块人脸识别[J]. 山东大学学报(工学版), 2012, 42(4): 29-34.
[6] 翟俊海1,翟梦尧1,张素芳2,王熙照1. 基于小波子空间集成的人脸识别[J]. 山东大学学报(工学版), 2012, 42(2): 1-6.
[7] 王熙照,白丽杰*,花强,刘玉超. null[J]. 山东大学学报(工学版), 2011, 41(4): 1-6.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!