2D filtering of curvilinear structures by ranking the orientation responses of path operators (RORPO)
Odyssée Merveille
(1)
,
Benoît Naegel
(1)
,
Hugues Talbot
(2)
,
Laurent Najman
(2)
,
Nicolas Passat
(3)
Odyssée Merveille
- Fonction : Auteur
- PersonId : 12603
- IdHAL : odyssee-merveille
- ORCID : 0000-0002-9918-3761
- IdRef : 201427788
Benoît Naegel
- Fonction : Auteur
- PersonId : 13207
- IdHAL : benoit-naegel
- ORCID : 0000-0002-7695-1473
- IdRef : 09031669X
Hugues Talbot
- Fonction : Auteur
- PersonId : 1939
- IdHAL : hugues-talbot
- ORCID : 0000-0002-2179-3498
- IdRef : 181843056
Laurent Najman
- Fonction : Auteur
- PersonId : 28
- IdHAL : laurent-najman
- ORCID : 0000-0002-6190-0235
- IdRef : 087172712
Nicolas Passat
- Fonction : Auteur
- PersonId : 17335
- IdHAL : nicolas-passat
- ORCID : 0000-0002-0320-4581
- IdRef : 101512821
Résumé
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.
Format du dépôt | Fichier |
---|---|
Type de dépôt | Article dans une revue |
Titre |
en
2D filtering of curvilinear structures by ranking the orientation responses of path operators (RORPO)
|
Résumé |
en
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.
|
Auteur(s) |
Odyssée Merveille
1
, Benoît Naegel
1
, Hugues Talbot
2
, Laurent Najman
2
, Nicolas Passat
3
1
ICube -
Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie
( 217648 )
- 300 bd Sébastien Brant - BP 10413 - F-67412 Illkirch Cedex
- France
2
LIGM -
Laboratoire d'Informatique Gaspard-Monge
( 3210 )
- Université de Paris-Est Marne-la-Vallée, Cité Descartes, Bâtiment Copernic, 5 bd Descartes, 77454 Marne-la-Vallée Cedex 2
- France
3
CRESTIC -
Centre de Recherche en Sciences et Technologies de l'Information et de la Communication - EA 3804
( 21189 )
- UFR Sciences Exactes et Naturelles, Moulin de la Housse, BP 1039, 51687 Reims CEDEX 2, FRANCE
- France
|
Langue du document |
Anglais
|
Nom de la revue |
|
Vulgarisation |
Non
|
Comité de lecture |
Oui
|
Audience |
Internationale
|
Date de publication |
2017
|
Volume |
7
|
Page/Identifiant |
246-261
|
Domaine(s) |
|
Voir aussi |
|
Projet(s) ANR |
|
Mots-clés |
en
mathematical morphology, path operators, filtering, curvilinear structure, path operator
|
DOI | 10.5201/ipol.2017.207 |
Origine :
Fichiers éditeurs autorisés sur une archive ouverte
Loading...