We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Object class recognition by unsupervised scale-invariant learning


    Beteiligte:
    Fergus, R. (Autor:in) / Perona, P. (Autor:in) / Zisserman, A. (Autor:in)


    Erscheinungsdatum :

    01.01.2003


    Format / Umfang :

    2392608 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Object Class Recognition by Unsupervised Scale-Invariant Learning

    Fergus, R. / Perona, P. / Zisserman, A. et al. | British Library Conference Proceedings | 2003


    Selection of Scale-Invariant Parts for Object Class Recognition

    Dorko, G. / Schmid, C. / IEEE | British Library Conference Proceedings | 2003



    Scale-Invariant Shape Features for Recognition of Object Categories

    Jurie, F. / Schmid, C. / IEEE Computer Society | British Library Conference Proceedings | 2004