Revisiting Component Tree Based Segmentation Using Meaningful Photometric Informations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Revisiting Component Tree Based Segmentation Using Meaningful Photometric Informations

Résumé

This paper proposes to revisit a recent interactive segmentation algorithm based on an original image representation called the component-tree [1]. This method relies on an optimisation process allowing to choose a segmentation result fitting at best some image markers defined by the user. We propose different solutions to improve the efficiency of the method, in particular by including meaningful photometric informations and by assessing automatically the user parameter α.
Fichier non déposé

Dates et versions

hal-00761303 , version 1 (05-12-2012)

Identifiants

Citer

Michal Kowalczyk, Bertrand Kerautret, Benoît Naegel, Jonathan Weber. Revisiting Component Tree Based Segmentation Using Meaningful Photometric Informations. International Conference on Computer Vision and Graphics (ICCVG, Sep 2012, Varsovie, Poland. pp.475-482, ⟨10.1007/978-3-642-33564-8_57⟩. ⟨hal-00761303⟩
111 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More