Multi-view face detection and recognition has been a challenging problem. The challenge is due to the fact that the distribution of multi-view faces in a feature space is more dispersed and more complicated than that of frontal faces. This paper presents an investigation into several view-subspace representations of multi-view faces: learning by using independent component analysis (ICA), independent subspace analysis (ISA) and topographic independent component analysis (TICA). It is shown that view-specific basis components can be learned from multi-view face examples in an unsupervised way by using ICA, ISA and TICA; whereas the components learned by using principal component analysis reveal little view-related information. The learned results provide sensible basis for constructing view-subspaces for multi-view faces. Comparative experiments demonstrate distinctive properties of ICA, ISA and TICA results, and the suitability of the results as representations of multi-view faces.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    View-subspace analysis of multi-view face patterns


    Contributors:


    Publication date :

    2001-01-01


    Size :

    1281027 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    View-Subspace Analysis of Multi-View Face Patterns

    Li, S. / Lv, X. / Zhang, H. et al. | British Library Conference Proceedings | 2001


    Robust Multi-Camera View Face Recognition

    Kisku, D.R. / Mehrotra, H. / Gupta, P. et al. | British Library Online Contents | 2011


    Robust Multi-Camera View Face Recognition

    Kisku, Dakshina R. / Mehrotra, Hunny / Gupta, Phalguni et al. | British Library Online Contents | 2011


    Multi-view face detection with FloatBoost

    ZhenQiu Zhang, / MingJing Li, / Li, S.Z. et al. | IEEE | 2002


    Multi-View Face Detection with FloatBoost

    Zhang, Z.-Q. / Li, M.-J. / Li, S. Z. et al. | British Library Conference Proceedings | 2002