In this work we present discriminative random fields (DRFs), a discriminative framework for the classification of image regions by incorporating neighborhood interactions in the labels as well as the observed data. The discriminative random fields offer several advantages over the conventional Markov random field (MRF) framework. First, the DRFs allow to relax the strong assumption of conditional independence of the observed data generally used in the MRF framework for tractability. This assumption is too restrictive for a large number of applications in vision. Second, the DRFs derive their classification power by exploiting the probabilistic discriminative models instead of the generative models used in the MRF framework. Finally, all the parameters in the DRF model are estimated simultaneously from the training data unlike the MRF framework where likelihood parameters are usually learned separately from the field parameters. We illustrate the advantages of the DRFs over the MRF framework in an application of man-made structure detection in natural images taken from the Corel database.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Discriminative random fields: a discriminative framework for contextual interaction in classification


    Beteiligte:
    Sanjiv Kumar, (Autor:in) / Hebert, (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    465396 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification

    Kumar, S. / Hebert, M. / IEEE | British Library Conference Proceedings | 2003


    Discriminative Random Fields

    Kumar, S. / Hebert, M. | British Library Online Contents | 2006


    Located Hidden Random Fields: Learning Discriminative Parts for Object Detection

    Kapoor, Ashish / Winn, John | Springer Verlag | 2006

    Freier Zugriff

    Located Hidden Random Fields: Learning Discriminative Parts for Object Detection

    Kapoor, A. / Winn, J. | British Library Conference Proceedings | 2006