Thumbnail - No thumbnail

Extraction of Tubular Structures over an Orientation Domain

Keriven, Renaud; Peyré, Gabriel; Péchaud, Mickaël (2009-06-26T09:04:47Z), Extraction of Tubular Structures over an Orientation Domain, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20-25 June 2009, Miami, Florida, USA. Proceedings, IEEE, p. 336-342

Type
Communication / Conférence
Lien vers un document non conservé dans cette base
http://hal.archives-ouvertes.fr/hal-00365599/en/
Date
2009-06-26
Titre du colloque
IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09)
Date du colloque
2009-06
Ville du colloque
Miami (Floride)
Pays du colloque
États-Unis
Titre de l'ouvrage
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20-25 June 2009, Miami, Florida, USA. Proceedings
Éditeur
IEEE
Isbn
978-1-4244-3992-8
Pages
336-342
Métadonnées
Afficher la notice complète
Auteur(s)
Keriven, Renaud
Peyré, Gabriel
Péchaud, Mickaël
Résumé (EN)
This paper presents a new method to extract tubular structures from bi-dimensional images. The core of the proposed algorithm is the computation of geodesic curves over a four-dimensional space that includes local orientation and scale. These shortest paths follow closely the centerline of tubular structures, provide an estimation of the radius and can deal robustly with crossings over the image plane. Numerical experiments on a database of synthetic and natural images show the superiority of the proposed approach with respect to several method based on shortest paths extractions.
Mots-clés
geodesics; networks; fast marching; medical imaging; vessels; Centerlines