In this paper, we present a novel algorithm for incremental principal component analysis. Based on the largest-eigenvalue-theory, i.e. the eigenvector associated with the largest eigenvalue of a symmetry matrix can be iteratively estimated with any initial value, we propose an iterative algorithm, referred as LET-IPCA, to incrementally update the eigenvectors corresponding to the leading eigenvalues. LET-IPCA is covariance matrix free and seamlessly connects the estimations of the leading eigenvectors by cooperatively preserving the most dominating information, as opposed to the state-of-the-art algorithm CCIPCA, in which the estimation of each eigenvector is independent. The experiments on both the MNIST digits database and the CMU PIE face database show that our proposed algorithm is much superior to CCIPCA in both convergency speed and accuracy.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Largest-eigenvalue-theory for incremental principal component analysis


    Beteiligte:
    Shuicheng Yan, (Autor:in) / Xiaoou Tang, (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    399747 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Largest-Eigenvalue-Theory for Incremental Principal Component Analysis

    Yan, S. / Tang, X. | British Library Conference Proceedings | 2005


    Incremental Principal Component Pursuit for Video Background Modeling

    Rodriguez, P. | British Library Online Contents | 2016


    Inertial principal axes as an eigenvalue problem

    Carpenter, John E. | TIBKAT | 1955


    Euler Principal Component Analysis

    Liwicki, S. / Tzimiropoulos, G. / Zafeiriou, S. et al. | British Library Online Contents | 2013


    Backwards Principal Component Analysis and Principal Nested Relations

    Damon, J. | British Library Online Contents | 2014