We propose a new technique for direct visual matching of images for the purposes of face recognition, database search and image retrieval. Specifically, we argue in favor of a probabilistic measure of similarity, in contrast to simpler methods which are based on standard L/sub 2/ norms (e.g., template matching) or subspace-restricted norms (e.g., eigenspace matching). The proposed similarity measure is based on a Bayesian analysis using two mutually-exclusive classes of image variation as encountered in a typical face recognition task. The high-dimensional probability density functions for each respective class are obtained from training data using an eigenspace density estimation technique and subsequently used to compute a similarity measure based on the relevant a posteriori probability, which is used to rank matches in the database. The performance advantage of this probabilistic matching technique over standard nearest-neighbor eigenspace matching is demonstrated using results from ARPA's 1996 "FERET" face recognition competition, in which this algorithm was found to be the top performer by a 10% (or better) margin to the other competitors.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Probabilistic matching for face recognition


    Contributors:


    Publication date :

    1998-01-01


    Size :

    758093 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Probabilistic Matching for Face Recognition

    Moghaddam, B. / Pentland, A. / University of Arizona et al. | British Library Conference Proceedings | 1998



    Probabilistic Identity Characterization for Face Recognition

    Zhou, S. / Chellappa, R. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Local manifold matching for face recognition

    Wei Liu, / Wei Fan, / Yunhong Wang, et al. | IEEE | 2005


    Local Manifold Matching for Face Recognition

    Liu, W. / Fan, W. / Wang, Y. et al. | British Library Conference Proceedings | 2005