DREAM2S: Deformable Regions Driven by an Eulerian Accurate Minimization Method for Image and Video Segmentation

Stéphanie Jehan-Besson 1 Michel Barlaud 1 Gilles Aubert 2
1 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Equipe IMAGES-CREATIVE
SIS - Signal, Images et Systèmes
2 JAD - Laboratoire Jean Alexandre Dieudonné
Abstract : This paper deals with image and video segmentation using active contours.We propose a general form for the energy functional related to region-based active contours.We compute the associated evolution equation using shape derivation tools and accounting for the evolving region-based terms. Then we apply this general framework to compute the evolution equation from functionals that include various statistical measures of homogeneity for the region to be segmented. Experimental results show that the determinant of the covariance matrix appears to be a very relevant tool for segmentation of homogeneous color regions. As an example, it has been successfully applied to face segmentation in real video sequences.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2003, pp.45-70
Liste complète des métadonnées

Littérature citée [49 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-00664596
Contributeur : Michel Barlaud <>
Soumis le : mardi 31 janvier 2012 - 10:46:48
Dernière modification le : mercredi 31 janvier 2018 - 10:24:05
Document(s) archivé(s) le : mardi 1 mai 2012 - 02:21:51

Fichier

IJCV-03.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00664596, version 1

Collections

I3S | DIEUDONNE | UNICE | UNIV-COTEDAZUR

Citation

Stéphanie Jehan-Besson, Michel Barlaud, Gilles Aubert. DREAM2S: Deformable Regions Driven by an Eulerian Accurate Minimization Method for Image and Video Segmentation. International Journal of Computer Vision, Springer Verlag, 2003, pp.45-70. 〈hal-00664596〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

240

Téléchargements de fichiers

111

Contact


archive-ouverte@inria.fr