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).


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Object class recognition by unsupervised scale-invariant learning


    Contributors:
    Fergus, R. (author) / Perona, P. (author) / Zisserman, A. (author)


    Publication date :

    2003-01-01


    Size :

    2392608 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    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