New data model for graph-cut segmentation: application to automatic melanoma delineation - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1) , (1) , (2) , (2) , (1)
1
2

Abstract

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
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-01080049 , version 1

Cite

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⟩
472 View
351 Download

Share

Gmail Facebook Twitter LinkedIn More