TY - GEN
T1 - Multiclass pixel labeling with non-local matching constraints
AU - Gould, Stephen
PY - 2012
Y1 - 2012
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84866689521&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2012.6248002
DO - 10.1109/CVPR.2012.6248002
M3 - Conference contribution
SN - 9781467312264
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2783
EP - 2790
BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Y2 - 16 June 2012 through 21 June 2012
ER -