We present a component-based, trainable system for detecting frontal and near-frontal views of faces in still gray images. The system consists of a two-level hierarchy of Support Vector Machine (SVM) classifiers. On the first level, component classifiers independently detect components Of a face. On the second level, a single classifier checks if the geometrical configuration of the detected components in the image matches a geometrical model of a face. We propose a method for automatically learning components by using 3-D head models, This approach has the advantage that no manual interaction is required for choosing and extracting components. Experiments show that the component-based system is significantly more robust against rotations in depth than a comparable system trained on whole face patterns.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Component-based face detection


    Contributors:
    Heiselet, B. (author) / Serre, T. (author) / Pontil, M. (author) / Poggio, T. (author)


    Publication date :

    2001-01-01


    Size :

    882378 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Component-Based Face Detection

    Heisele, B. / Serre, T. / Pontil, M. et al. | British Library Conference Proceedings | 2001


    Advances in component based face detection

    Bileschi, S.M. / Heisele, B. | IEEE | 2003


    Advances in Component Based Face Detection

    Bileschi, S. / Heisele, B. / IEEE | British Library Conference Proceedings | 2003


    A Component-based Framework for Face Detection and Identification

    Heisele, B. / Serre, T. / Poggio, T. | British Library Online Contents | 2007


    Face recognition: component-based versus global approaches

    Heisele, B. / Ho, P. / Wu, J. et al. | British Library Online Contents | 2003