We propose a unified framework based on a general definition of geometric transform (GeT) for modeling appearance. GeT represents the appearance by applying designed functionals over certain geometric sets. We show that image warping, Radon transform, trace transform, etc. are special cases of our definition. Moreover, three different types of GeTs are designed to handle deformation, articulation and occlusion and applied to fingerprinting the appearance inside a contour. They include the contour-driven GeT, the feature curve based GeT and selecting functionals to model the appearance inside the convex hull of the contour. A multi-resolution representation that combines both shape and appearance information is also proposed. We apply our approach to image synthesis and object recognition. The proposed approach produces promising results when applied to fingerprinting the appearance of human and body parts despite the challenges due to articulated motion and deformations.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Appearance modeling under geometric context


    Beteiligte:
    Jian Li, (Autor:in) / Zhou, S.K. (Autor:in) / Chellappa, R. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    434001 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Appearance Modeling Under Geometric Context

    Li, J. / Zhou, S. / Chellappa, R. et al. | British Library Conference Proceedings | 2005



    Combining Priors, Appearance, and Context for Road Detection

    Alvarez, Jose M. / Lopez, Antonio M. / Gevers, Theo et al. | IEEE | 2014



    TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation

    Shotton, Jamie / Winn, John / Rother, Carsten et al. | Springer Verlag | 2006

    Freier Zugriff