Convex Color Image Segmentation with Optimal Transport Distances
Computer Vision and Pattern Recognition
2015-03-17 v2
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 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.
Cite
@article{arxiv.1503.01986,
title = {Convex Color Image Segmentation with Optimal Transport Distances},
author = {Julien Rabin and Nicolas Papadakis},
journal= {arXiv preprint arXiv:1503.01986},
year = {2015}
}
Comments
A short version of this report has been submitted to the Fifth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) 2015