Recently, it was proven empirically that facial expressions can be modelled as isometries, that is, geodesic distances on the facial surface were shown to be significantly less sensitive to facial expressions compared to Euclidean ones. Based on this assumption, the 3DFACE face recognition system was built. The system efficiently computes expression invariant signatures based on isometry-invariant representation of the facial surface. One of the crucial steps in the recognition system was embedding of the face geometric structure into a Euclidean (flat) space. Here, we propose to replace the flat embedding by a spherical one to construct isometric invariant representations of the facial image. We refer to these new invariants as spherical canonical images. Compared to its Euclidean counterpart, spherical embedding leads to notably smaller metric distortion. We demonstrate experimentally that representations with lower embedding error lead to better recognition. In order to efficiently compute the invariants we introduce a dissimilarity measure between the spherical canonical images based on the spherical harmonic transform.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Expression-invariant face recognition via spherical embedding


    Contributors:


    Publication date :

    2005-01-01


    Size :

    259363 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Expression-Invariant Face Recognition via Spherical Embedding

    Bronstein, A. M. / Bronstein, M. M. / Kimmel, R. | British Library Conference Proceedings | 2005


    Ultrafast invariant face recognition

    Alam, M.S. / Al-Samman, A.R. | IEEE | 2000


    Robust Expression-Invariant Face Recognition from Partially Missing Data

    Bronstein, A. M. / Bronstein, M. M. / Kimmel, R. | British Library Conference Proceedings | 2006


    Ultrafast Invariant Face Recognition

    Alam, M. S. / IEEE | British Library Conference Proceedings | 2000