Robust Principal Component Analysis for computer vision

被引:0
|
作者
De la Torre, F [1 ]
Black, MJ [1 ]
机构
[1] Univ Ramon Llull, Dept Comunicac & Teor Senyal, Escola Engn Salle, Barcelona 08022, Spain
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Principal Component Analysis (PCA) has been widely used for the representation of shape, appearance, and motion. One drawback of typical PCA methods is that they are least squares estimation techniques and hence fail to account for "outliers" which are common in realistic training sets. In computer vision applications, outliers typically occur within a sample (image) due to pixels that are corrupted by noise, alignment errors, or occlusion. We review previous approaches for making PCA robust to outliers and present a new method that uses an intra-sample outlier process to account for pixel outliers. We develop the theory of Robust Principal Component Analysis (RPCA) and describe a robust M-estimation algorithm for learning linear multivariate representations of high dimensional data such as images. Quantitative comparisons with traditional PCA and previous robust algorithms illustrate the benefits of RPCA when outliers are present. Details of the algorithm are described and a software implementation, is being made publically available.
引用
收藏
页码:362 / 369
页数:8
相关论文
共 50 条
  • [41] Robust Principal Component Analysis with Side Information
    Chiang, Kai-Yang
    Hsieh, Cho-Jui
    Dhillon, Inderjit S.
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 48, 2016, 48
  • [42] Adaptive Weighted Robust Principal Component Analysis
    Xu, Zhengqin
    Lu, Yang
    Wu, Jiaxing
    He, Rui
    Wu, Shiqian
    Xie, Shoulie
    [J]. PROCEEDINGS OF THE 15TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2020), 2020, : 19 - 24
  • [43] Optimal Mean Robust Principal Component Analysis
    Nie, Feiping
    Yuan, Jianjun
    Huang, Heng
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), 2014, 32 : 1062 - 1070
  • [44] Robust Principal Component Analysis with Complex Noise
    Zhao, Qian
    Meng, Deyu
    Xu, Zongben
    Zuo, Wangmeng
    Zhang, Lei
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), 2014, 32 : 55 - 63
  • [45] Robust block tensor principal component analysis
    Feng, Lanlan
    Liu, Yipeng
    Chen, Longxi
    Zhang, Xiang
    Zhu, Ce
    [J]. SIGNAL PROCESSING, 2020, 166
  • [46] ROBUST PRINCIPAL COMPONENT ANALYSIS BY PROJECTION PURSUIT
    XIE, YL
    WANG, JH
    LIANG, YZ
    SUN, LX
    SONG, XH
    YU, RQ
    [J]. JOURNAL OF CHEMOMETRICS, 1993, 7 (06) : 527 - 541
  • [47] Robust principal component analysis for functional data
    N. Locantore
    J. S. Marron
    D. G. Simpson
    N. Tripoli
    J. T. Zhang
    K. L. Cohen
    Graciela Boente
    Ricardo Fraiman
    Babette Brumback
    Christophe Croux
    Jianqing Fan
    Alois Kneip
    John I. Marden
    Daniel Peña
    Javier Prieto
    Jim O. Ramsay
    Mariano J. Valderrama
    Ana M. Aguilera
    N. Locantore
    J. S. Marron
    D. G. Simpson
    N. Tripoli
    J. T. Zhang
    K. L. Cohen
    [J]. Test, 1999, 8 (1) : 1 - 73
  • [48] BAYESIAN LEARNING FOR ROBUST PRINCIPAL COMPONENT ANALYSIS
    Sundin, Martin
    Chatterjee, Saikat
    Jansson, Magnus
    [J]. 2015 23RD EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2015, : 2361 - 2365
  • [49] Robust Principal Component Analysis with Adaptive Neighbors
    Zhang, Rui
    Tong, Hanghang
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [50] Exactly Robust Kernel Principal Component Analysis
    Fan, Jicong
    Chow, Tommy W. S.
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (03) : 749 - 761