2D filtering of curvilinear structures by ranking the orientation responses of path operators (RORPO)

Abstract : We present a filtering method for 2D curvilinear structures, called RORPO (Ranking the Orientation Responses of Path Operators). RORPO is based on path operators, a recently developed family of mathematical morphology filters. Compared with state of the art methods, RORPO is non-local and well adapted to the intrinsic anisotropy of curvilinear structures. Since RORPO does not depend on a linear scale-space framework, it tends to preserve object contours without a blurring effect. Due to these properties, RORPO is a useful low-level filter and can also serve as a curvilinear prior in segmentation frameworks. In this article, after introducing RORPO, we develop the 2D version of the algorithm and present a few applications.
Type de document :
Article dans une revue
Image Processing On Line, IPOL - Image Processing on Line, 2017, 7, pp.246-261. 〈http://www.ipol.im/pub/art/2017/207/article.pdf〉. 〈10.5201/ipol.2017.207〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01599528
Contributeur : Odyssée Merveille <>
Soumis le : lundi 2 octobre 2017 - 12:02:28
Dernière modification le : vendredi 9 février 2018 - 21:15:28

Lien texte intégral

Identifiants

Collections

Citation

Odyssée Merveille, Benoît Naegel, Hugues Talbot, Laurent Najman, Nicolas Passat. 2D filtering of curvilinear structures by ranking the orientation responses of path operators (RORPO). Image Processing On Line, IPOL - Image Processing on Line, 2017, 7, pp.246-261. 〈http://www.ipol.im/pub/art/2017/207/article.pdf〉. 〈10.5201/ipol.2017.207〉. 〈hal-01599528〉

Partager

Métriques

Consultations de la notice

144