New data model for graph-cut segmentation: application to automatic melanoma delineation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

New data model for graph-cut segmentation: application to automatic melanoma delineation

Résumé

We propose a new data model for graph-cut image segmentation, defined according to probabilities learned by a classification process. Unlike traditional graph-cut methods, the data model takes into account not only color but also texture and shape information. For melanoma images, we also introduce skin chromophore features and automatically derive "seed" pixels used to train the classifier from a coarse initial segmentation. On natural images, our method successfully segments objects having similar color but different texture. Its application to melanoma delineation compares favorably to manual delineation and related graph-cut segmentation methods.
Fichier principal
Vignette du fichier
Kechichian_ICIP14.pdf (8.46 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01080049 , version 1 (04-11-2014)

Identifiants

  • HAL Id : hal-01080049 , version 1

Citer

Razmig Kéchichian, Hao Gong, Marinette Revenu, Olivier Lézoray, Michel Desvignes. New data model for graph-cut segmentation: application to automatic melanoma delineation. ICIP 2014 - 21st IEEE International Conference on Image Processing, Oct 2014, Paris, France. ⟨hal-01080049⟩
481 Consultations
373 Téléchargements

Partager

Gmail Facebook X LinkedIn More