Convex Color Image Segmentation with Optimal Transport Distances
| hal.structure.identifier | Equipe Image - Laboratoire GREYC - UMR6072 | |
| dc.contributor.author | RABIN, Julien | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | PAPADAKIS, Nicolas | |
| dc.date.accessioned | 2024-04-04T03:18:45Z | |
| dc.date.available | 2024-04-04T03:18:45Z | |
| dc.date.created | 2014-12-18 | |
| dc.date.issued | 2015-05-31 | |
| dc.date.conference | 2015-05-31 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/194442 | |
| dc.description.abstractEn | 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. | |
| dc.language.iso | en | |
| dc.source.title | Proceedings of the fifth International Conference on Scale Space and Variational Methods in Computer Vision | |
| dc.subject.en | Optimal transport | |
| dc.subject.en | Wasserstein distance | |
| dc.subject.en | Sinkhorn distance | |
| dc.subject.en | convex optimization | |
| dc.subject.en | image segmentation | |
| dc.title.en | Convex Color Image Segmentation with Optimal Transport Distances | |
| dc.type | Communication dans un congrès | |
| dc.subject.hal | Informatique [cs]/Traitement du signal et de l'image | |
| dc.subject.hal | Sciences de l'ingénieur [physics]/Traitement du signal et de l'image | |
| bordeaux.page | 256-269 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.conference.title | International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'15) | |
| bordeaux.country | FR | |
| bordeaux.title.proceeding | Proceedings of the fifth International Conference on Scale Space and Variational Methods in Computer Vision | |
| bordeaux.conference.city | Lège Cap Ferret | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-01133447 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | oui | |
| hal.conference.end | 2015-06-04 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-01133447v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.btitle=Proceedings%20of%20the%20fifth%20International%20Conference%20on%20Scale%20Space%20and%20Variational%20Methods%20in%20Computer%20Vision&rft.date=2015-05-31&rft.spage=256-269&rft.epage=256-269&rft.au=RABIN,%20Julien&PAPADAKIS,%20Nicolas&rft.genre=unknown |
Files in this item
| Files | Size | Format | View |
|---|---|---|---|
|
There are no files associated with this item. |
|||