Random walks in directed hypergraphs and application to semi-supervised image segmentation - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Computer Vision and Image Understanding Année : 2014

Random walks in directed hypergraphs and application to semi-supervised image segmentation

Résumé

In this paper, we introduce for the first time the notion of directed hypergraphs in image processing and particularly image segmentation. We give a formulation of a random walk in a directed hypergraph that serves as a basis to a semi-supervised image segmentation procedure that is configured as a machine learning problem, where a few sample pixels are used to estimate the labels of the unlabeled ones. A directed hypergraph model is proposed to represent the image content, and the directed random walk formulation allows to compute a transition matrix that can be exploited in a simple iterative semi-supervised segmentation process. Experiments over the Microsoft GrabCut dataset have achieved results that demonstrated the relevance of introducing directionality in hypergraphs for computer vision problems.
Fichier principal
Vignette du fichier
RIACL-DUCOURNAU-2014-1.pdf (14.13 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01025272 , version 1 (17-07-2014)

Identifiants

Citer

Aurélien Ducournau, Alain Bretto. Random walks in directed hypergraphs and application to semi-supervised image segmentation. Computer Vision and Image Understanding, 2014, 120, pp.91-102. ⟨10.1016/j.patcog.2012.01.005⟩. ⟨hal-01025272⟩
399 Consultations
362 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More