We propose an approach to include contextual features for labeling images, in which each pixel is assigned to one of a finite set of labels. The features are incorporated into a probabilistic framework, which combines the outputs of several components. Components differ in the information they encode. Some focus on the image-label mapping, while others focus solely on patterns within the label field. Components also differ in their scale, as some focus on fine-resolution patterns while others on coarser, more global structure. A supervised version of the contrastive divergence algorithm is applied to learn these features from labeled image data. We demonstrate performance on two real-world image databases and compare it to a classifier and a Markov random field.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multiscale conditional random fields for image labeling


    Contributors:


    Publication date :

    2004-01-01


    Size :

    455689 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multiscale Conditional Random Fields for Image Labeling

    He, X. / Zemel, R. / Carreira-Perpinan, M. et al. | British Library Conference Proceedings | 2004


    On Learning Conditional Random Fields for Stereo

    Pal, C. J. / Weinman, J. J. / Tran, L. C. et al. | British Library Online Contents | 2012


    Scale-invariant contour completion using conditional random fields

    Xiaofeng Ren, / Fowlkes, C.C. / Malik, J. | IEEE | 2005


    Diagram structure recognition by Bayesian conditional random fields

    Qi, Y. / Szummer, M. / Minka, T.P. | IEEE | 2005


    Scale-Invariant Contour Completion Using Conditional Random Fields

    Ren, X. / Fowlkes, C. / Malik, J. et al. | British Library Conference Proceedings | 2005