We propose a robust model selection criterion for mixtures of subspaces called minimum effective dimension (MED). Previous information-theoretic model selection criteria typically assume that data can be modelled with a parametric model of certain (possibly differing) dimension and a known error distribution. However, for mixtures of subspaces with different dimensions, a generalized notion of dimensionality is needed and hence introduced in this paper. The proposed MED criterion minimizes this geometric dimension subject to a given error tolerance (regardless of the noise distribution). Furthermore, combined with a purely algebraic approach to clustering mixtures of subspaces, namely the generalized PCA (GPCA), the MED is designed to also respect the global algebraic and geometric structure of the data. The result is a non-iterative algorithm called robust GPCA that estimates from noisy data an unknown number of subspaces with unknown and possibly different dimensions subject to a maximum error bound. We test the algorithm on synthetic noisy data and in applications such as motion/image/video segmentation.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Minimum effective dimension for mixtures of subspaces: a robust GPCA algorithm and its applications


    Beteiligte:
    Kun Huang, (Autor:in) / Yi Ma, (Autor:in) / Vidal, R. (Autor:in)


    Erscheinungsdatum :

    01.01.2004


    Format / Umfang :

    644690 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Minimum Effective Dimension for Mixtures of Subspaces: A Robust GPCA Algorithm and Its Applications

    Huang, K. / Ma, Y. / Vidal, R. et al. | British Library Conference Proceedings | 2004


    A New GPCA Algorithm for Clustering Subspaces by Fitting, Differentiating and Dividing Polynomials

    Vidal, R. / Ma, Y. / Piazzi, J. et al. | British Library Conference Proceedings | 2004



    GPCA adds audit scheme

    Online Contents | 2014


    Generalized Principal Component Analysis (GPCA)

    Vidal, R. / Ma, Y. / Sastry, S. et al. | British Library Conference Proceedings | 2003