ML Anthology

Extraction of Tubular Structures over an Orientation Domain

Mickaël Péchaud, Renaud Keriven, Gabriel Peyré
CVPR 2009 pp. 336-342
doi:10.1109/CVPR.2009.5206782 /cvpr/2009/pechaud2009cvpr-extraction/

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.

PDF CVPR Semantic Scholar

Cite

Text

Péchaud et al. "Extraction of Tubular Structures over an Orientation Domain." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206782

Markdown

[Péchaud et al. "Extraction of Tubular Structures over an Orientation Domain." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/pechaud2009cvpr-extraction/) doi:10.1109/CVPR.2009.5206782

BibTeX

@inproceedings{pechaud2009cvpr-extraction,
  title     = {{Extraction of Tubular Structures over an Orientation Domain}},
  author    = {Péchaud, Mickaël and Keriven, Renaud and Peyré, Gabriel},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2009},
  pages     = {336-342},
  doi       = {10.1109/CVPR.2009.5206782},
  url       = {https://mlanthology.org/cvpr/2009/pechaud2009cvpr-extraction/}
}