We present spectral histogram representations for visual modeling. Based on a generative process, the representation is derived by partitioning the frequency domain into small disjoint regions and assuming independence among the regions. This gives rise to a set of filters and a representation consisting of marginal distributions of those filter responses. A distinct advantage of our representation is that it can be effectively used for different classification and recognition tasks, which is demonstrated by experiments and comparisons in texture classification, face recognition, and appearance-based 3D object recognition. The marked improvement over existing methods justifies our principle that effective priori knowledge should be derived from physical generative processes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Spectral histogram representations for visual modeling


    Contributors:
    Xiuwen Liu, (author) / Qiang Zhang, (author)


    Publication date :

    2003-01-01


    Size :

    470876 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Spectral Histogram Representations for Visual Modeling

    Liu, X. / Zhang, Q. | British Library Conference Proceedings | 2004


    Real-time nonparametric background modeling using moving histogram method for visual surveillance [5298-60]

    Lee, G.-D. / Lee, W.-H. / Jeong, D.-S. et al. | British Library Conference Proceedings | 2004


    Parametric Representations for Nonlinear Modeling of Visual Data

    Zhu, Y. / Comaniciu, D. / Ramesh, V. et al. | British Library Conference Proceedings | 2001


    Parametric representations for nonlinear modeling of visual data

    Ying Zhu, / Comaniciu, D. / Ramesh, V. et al. | IEEE | 2001