Extraction of Tubular Structures over an Orientation Domain - Archive ouverte HAL Access content directly
Conference Papers Year : 2009

Extraction of Tubular Structures over an Orientation Domain

Abstract

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.
Fichier principal
Vignette du fichier
CVPR.pdf (988.87 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00365599 , version 1 (03-03-2009)

Identifiers

  • HAL Id : hal-00365599 , version 1

Cite

Mickaël Péchaud, Gabriel Peyré, Renaud Keriven. Extraction of Tubular Structures over an Orientation Domain. IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09), Jun 2009, Florida, United States. ⟨hal-00365599⟩
172 View
500 Download

Share

Gmail Facebook X LinkedIn More