We propose a novel representation for characterizing image differences using a deformable technique for obtaining pixel-wise correspondences. This representation, which is based on a deformable 3D mesh in XYI-space, is then experimentally compared with two related correspondence methods: optical flow and intensity differences. Furthermore, we make use of a probabilistic similarity measure for direct image matching based on a Bayesian analysis of image variations. We model two classes of variation in facial appearance: intra-personal and extra-personal. The probability density function for each class is estimated from training data and used to compute a similarity measure based on the a posteriori probabilities. The performance advantage of our deformable probabilistic matching technique is demonstrated using 1700 faces from the USA Army's "FERET" face database.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Bayesian face recognition with deformable image models


    Contributors:
    Moghaddam, B. (author) / Nastar, C. (author) / Pentland, A. (author)


    Publication date :

    2001-01-01


    Size :

    1145881 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Bayesian Face Recognition with Deformable Image Models

    Moghaddam, B. / Nastar, C. / Pentland, A. et al. | British Library Conference Proceedings | 2001


    A Bayesian similarity measure for deformable image matching

    Moghaddam, B. / Nastar, C. / Pentland, A. | British Library Online Contents | 2001


    Optical Flow Constraints on Deformable Models with Applications to Face Tracking

    DeCarlo, D. / Metaxas, D. | British Library Online Contents | 2000


    Bayesian Face Recognition Using Support Vector Machine and Face Clustering

    Li, Z. / Tang, X. / IEEE Computer Society | British Library Conference Proceedings | 2004