Spatially-Variant Directional Mathematical Morphology Operators Based on a Diffused Average Squared Gradient Field

Abstract : This paper proposes an approach for mathematical morphology operators whose structuring element can locally adapt its orientation across the pixels of the image. The orientation at each pixel is extracted by means of a diffusion process of the average squared gradient field. The resulting vector field, the average squared gradient vector flow, extends the orientation information from the edges of the objects to the homogeneous areas of the image. The provided orientation field is then used to perform a spatially variant filtering with a linear structuring element. Results of erosion, dilation, opening and closing spatially-variant on binary images prove the validity of this theoretical sound and novel approach.
Type de document :
Communication dans un congrès
Jacques Blanc-Talon, Salah Bourennane, Wilfried Philips, Dan Popescu, and Paul Scheunders. 10th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2008, Oct 2008, Juan les Pins, France. Springer, 5259, pp.542-553, 2008, Lecture Notes in Computer Science. <10.1007/978-3-540-88458-3_49>
Liste complète des métadonnées


https://hal-mines-paristech.archives-ouvertes.fr/hal-00834032
Contributeur : Doriane Ibarra <>
Soumis le : jeudi 13 juin 2013 - 22:41:30
Dernière modification le : mardi 12 septembre 2017 - 11:41:16
Document(s) archivé(s) le : samedi 14 septembre 2013 - 04:17:13

Fichier

VerduAngulo_ACVIS08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Rafael Verdu-Monedero, Jesus Angulo. Spatially-Variant Directional Mathematical Morphology Operators Based on a Diffused Average Squared Gradient Field. Jacques Blanc-Talon, Salah Bourennane, Wilfried Philips, Dan Popescu, and Paul Scheunders. 10th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2008, Oct 2008, Juan les Pins, France. Springer, 5259, pp.542-553, 2008, Lecture Notes in Computer Science. <10.1007/978-3-540-88458-3_49>. <hal-00834032>

Partager

Métriques

Consultations de
la notice

220

Téléchargements du document

100