This paper shows a self-organized system designed to obtain compressed representations of instances of a population of visual forms. It is shown how, when applied to face shape information, the system evolves into a prototype of the population and induces automatic warping, or caricaturing, transformations where geometrical differences between forms are increased, improving, as a consequence, recognition performance. In this way, the proposed system provides a unified account for the whole chain of face processing tasks including data compression, detection, and recognition. Experimental data is presented to show the feasibility of our approach in terms of performance and robustness to changes in illumination and face expressions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning and caricaturing the face space using self-organization and Hebbian learning for face processing


    Contributors:
    Pujol, A. (author) / Wechsler, H. (author) / Villanueva, J.J. (author)


    Publication date :

    2001-01-01


    Size :

    684647 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning and Caricaturing the Face Space Using Self-Organization and Hebbian Learning for Face Processing

    Pujol, A. / Wechsler, H. / Villanueva, J. et al. | British Library Conference Proceedings | 2001


    3D modeling system of human face and full 3D facial caricaturing

    Fujiwara, T. / Koshimizu, H. / Fujimura, K. et al. | IEEE | 2001


    3D Modeling System of Human Face and Full 3D Facial Caricaturing

    Fujiwara, T. / Koshimizu, H. / Fujimura, K. et al. | British Library Conference Proceedings | 2001


    An Expression Synthesis in Caricaturing

    Miyazaki, K. / Nakayama, H. | British Library Online Contents | 2000


    Automatic Face Classifications by Self-Organization for Face Recognition

    Sato, Y. / Yoda, I. / Sakaue, K. et al. | British Library Conference Proceedings | 2003