Watershed Cuts: Thinnings, Shortest Path Forests, and Topological Watersheds

Jean Cousty 1 Gilles Bertrand 1 Laurent Najman 1 Michel Couprie 1
1 LIGM - Laboratoire d'Informatique Gaspard-Monge
Abstract : We recently introduced the watershed cuts, a notion of watershed in edge-weighted graphs. In this paper, our main contribution is a thinning paradigm from which we derive three algorithmic watershed cut strategies: the first one is well suited to parallel implementations, the second one leads to a flexible linear-time sequential implementation whereas the third one links the watershed cuts and the popular flooding algorithms. We state that watershed cuts preserve a notion of contrast, called connection value, on which are (implicitly) ased several morphological region merging methods. We also establish the links and differences between watershed cuts, minimum spanning forests, shortest-path forests and topological watersheds. Finally, we present illsutrations of the proposed framework to the segmentation of artwork surfaces and diffusion tensor images.
Document type :
Journal articles
Complete list of metadatas
https://hal-upec-upem.archives-ouvertes.fr/hal-00729346
Contributor : Jean Cousty <>
Submitted on : Monday, January 14, 2013 - 11:12:55 AM
Last modification on : Wednesday, July 4, 2018 - 4:33:25 PM
Long-term archiving on : Monday, April 15, 2013 - 3:52:28 AM

File

WatershedCutsPAMI-part2-full.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00729346, version 1

Collections

LIGM_A3SI | LIGM | ENPC | PARISTECH | UNIV-MLV | UPEC-UPEM | ESIEE-PARIS

Citation

Jean Cousty, Gilles Bertrand, Laurent Najman, Michel Couprie. Watershed Cuts: Thinnings, Shortest Path Forests, and Topological Watersheds. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2010, 32 (5), pp.925-939. ⟨hal-00729346⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

327

Files downloads

485

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD