We present a system that can recover and track the 3D speech movements of a speaker's face for each image of a monocular sequence. A speaker-specific face model is used for tracking: model parameters are extracted from each image by an analysis-by-synthesis loop. To handle both the individual specificities of the speaker's articulation and the complexity of the facial deformations during speech, speaker-specific models of the face 3D geometry and appearance are built from real data. The geometric model is linearly controlled by only six articulatory parameters. Appearance is seen either as a classical texture map or through local appearance of a relevant subset of 3D points. We compare several appearance models: they are either constant or depend linearly on the articulatory parameters. We evaluate these different appearance models with ground truth data.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Shape and appearance models of talking faces for model-based tracking


    Contributors:
    Odisio, M. (author) / Bailly, G. (author)


    Publication date :

    2003-01-01


    Size :

    538264 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Shape and Appearance Models of Talking Faces for Model-based Tracking

    Odisio, M. / Bailly, G. / IEEE | British Library Conference Proceedings | 2003


    Shape based appearance model for kernel tracking

    Wang, Z. / Salah, M. B. / Zhang, H. et al. | British Library Online Contents | 2012


    Computer Graphics Animations of Talking Faces Based on Stochastic Models

    Brooke, N. M. / Scott, S. D. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994



    Towards a low bandwidth talking face using appearance models

    Theobald, B. J. / Kruse, S. M. / Bangham, J. A. et al. | British Library Online Contents | 2003