Multiclass pixel labeling with non-local matching constraints

Stephen Gould*

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    22 Citations (Scopus)

    Abstract

    A popular approach to pixel labeling problems, such as multiclass image segmentation, is to construct a pairwise conditional Markov random field (CRF) over image pixels where the pairwise term encodes a preference for smoothness within local 4-connected or 8-connected pixel neighborhoods. Recently, researchers have considered higherorder models that encode soft non-local constraints (e.g., label consistency, connectedness, or co-occurrence statistics). These new models and the associated energy minimization algorithms have significantly pushed the state-of-the-art for pixel labeling problems. In this paper, we consider a new non-local constraint that penalizes inconsistent pixel labels between disjoint image regions having similar appearance. We encode this constraint as a truncated higher-order matching potential function between pairs of image regions in a conditional Markov random field model and show how to perform efficient approximate MAP inference in the model. We experimentally demonstrate quantitative and qualitative improvements over a strong baseline pairwise conditional Markov random field model on two challenging multiclass pixel labeling datasets.

    Original languageEnglish
    Title of host publication2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
    Pages2783-2790
    Number of pages8
    DOIs
    Publication statusPublished - 2012
    Event2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 - Providence, RI, United States
    Duration: 16 Jun 201221 Jun 2012

    Publication series

    NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    ISSN (Print)1063-6919

    Conference

    Conference2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
    Country/TerritoryUnited States
    CityProvidence, RI
    Period16/06/1221/06/12

    Fingerprint

    Dive into the research topics of 'Multiclass pixel labeling with non-local matching constraints'. Together they form a unique fingerprint.

    Cite this