For the purpose of object recognition, we learn one discriminative classifier based on one prototype, using shape context distances as the feature vector. From multiple prototypes, the outputs of the classifiers are combined using the method called "error correcting output codes". The overall classifier is tested on a benchmark dataset and is shown to outperform existing methods with far fewer prototypes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning a discriminative classifier using shape context distances


    Beteiligte:
    Hao Zhang, (Autor:in) / Malik, J. (Autor:in)


    Erscheinungsdatum :

    01.01.2003


    Format / Umfang :

    812556 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Learning a Discriminative Classifier Using Shape Context Distances

    Zhang, H. / Malik, J. / IEEE | British Library Conference Proceedings | 2003



    Discriminative Deep Face Shape Model for Facial Point Detection

    Wu, Y. / Ji, Q. | British Library Online Contents | 2015


    Magnetotail shape at lunar distances: ARTEMIS observations

    Akay, Iklim Gencturk / Kaymaz, Zerefsan / Sibeck, David G. | IEEE | 2013