Principal components analysis (PCA) has been proved to be a useful tool for many computer vision and signal processing problems. One drawback of traditional PCA is that they are based on least squares estimation techniques and hence fail to account for "outliers" which are commonly occurred in realistic training sets. To make PCA more robust to real-world problems such as image reconstruction addressed in this paper, we develop a two-step algorithm that can eliminate the outliers on both frame level and pixel level through the LASSO and RPCA separately. With LASSO optimization method, we may obtain sparse projected coefficients of the original image into the basis image space. According to the sparsity of these coefficients, sample outliers can be recognized automatically. Then, with the use of robust M-estimation, the influence of intra-sample outliers may be overwhelmed to great extent. Additionally, due to orthogonality of the principal components, the soft-threshold estimation can be applied to the LASSO to alleviate the computational costs, hence make our robust PCA method more applicable to large scale problems. An experiment on object image reconstruction is used to illustrate the advantage of our proposed technique over standard PCA.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Robust Framework For Eigenspace Image Reconstruction


    Beteiligte:
    XiaoTong, Yuan (Autor:in) / HongWen, Zhu (Autor:in) / ShuTang, Yang (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    215109 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Robust localization using eigenspace of spinning-images

    Jogan, M. / Leonardis, A. | IEEE | 2000



    Robust eigenspace assignment using singular value sensitivities

    GARG, SANJAY / Sverdrup Technology / Inc. et al. | AIAA | 1991


    Robust Localization using Eigenspace of Spinning-Images

    Jogan, M. / Leonardis, A. / IEEE | British Library Conference Proceedings | 2000


    An Eigenspace Approach to Multiple Image Registration

    Schweitzer, H. / United States; National Aeronautics and Space Administration | British Library Conference Proceedings | 1998