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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Sanjiv Kumar, (author) / Hebert, (author)


    Publication date :

    2003-01-01


    Size :

    465396 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



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


    Located Hidden Random Fields: Learning Discriminative Parts for Object Detection

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

    Free access