Convex Color Image Segmentation with Optimal Transport Distances

Julien Rabin (1) , Nicolas Papadakis (2)

1 Equipe Image - Laboratoire GREYC - UMR6072
2 IMB - Institut de Mathématiques de Bordeaux

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.

Mots clés: Optimal transport; Wasserstein distance; Sinkhorn distance; convex optimization; image segmentation

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Julien Rabin, Nicolas Papadakis. Convex Color Image Segmentation with Optimal Transport Distances. International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'15), May 2015, Lège Cap Ferret, France. pp.256-269. ⟨hal-01133447⟩