Convex Color Image Segmentation with Optimal Transport Distances
Language
en
Communication dans un congrès
This item was published in
Proceedings of the fifth International Conference on Scale Space and Variational Methods in Computer Vision, Proceedings of the fifth International Conference on Scale Space and Variational Methods in Computer Vision, International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'15), 2015-05-31, Lège Cap Ferret. 2015-05-31p. 256-269
English Abstract
This work is about the use of regularized optimal-transport distances for convex, histogram-based image segmentation. In the considered framework, fixed exemplar histograms define a prior on the statistical features of the ...Read more >
This work is about the use of regularized optimal-transport distances for convex, histogram-based image segmentation. In the considered framework, fixed exemplar histograms define a prior on the statistical features of the two regions in competition. In this paper, we investigate the use of various transport-based cost functions as discrepancy measures and rely on a primal-dual algorithm to solve the obtained convex optimization problem.Read less <
English Keywords
Optimal transport
Wasserstein distance
Sinkhorn distance
convex optimization
image segmentation
Origin
Hal imported