Segmentation by Tangent Filter

Abstract : Image contour detection is fundamental to many image analysis applications, including image segmentation, object recognition and classification.In this paper, the main idea is to treat the pixel with a special mask for each pixel based on a criterion the orientation of the gradient. The masks used are inspired by the operators of Laplacian. The pixel processed is not in the center of the mask but on its tangent. The results obtained are very positive on certain types of images.
Type de document :
Communication dans un congrès
MedPRAI-2016 (Mediterranean Conference on Pattern Recognition and Artificial Intelligence), Nov 2016, Tebessa, Algeria. ACM Press, New York, NY, USA MedPRAI-2016 Proceedings of the Mediterranean Conference on Pattern Recognition and Artificial Intelligence pp.25-30, 2016, MedPRAI-2016 Proceedings of the Mediterranean Conference on Pattern Recognition and Artificial Intelligence 〈http://dl.acm.org/citation.cfm?doid=3038884.3038889〉. 〈10.1145/3038884.3038889〉
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01588373
Contributeur : Le2i - Université de Bourgogne <>
Soumis le : vendredi 15 septembre 2017 - 15:33:52
Dernière modification le : vendredi 13 juillet 2018 - 11:56:01

Identifiants

Collections

Citation

M. Boulakradeche, Samy Ait-Aoudia, Dominique Michelucci, A. Farouzi, K. Taibouni. Segmentation by Tangent Filter. MedPRAI-2016 (Mediterranean Conference on Pattern Recognition and Artificial Intelligence), Nov 2016, Tebessa, Algeria. ACM Press, New York, NY, USA MedPRAI-2016 Proceedings of the Mediterranean Conference on Pattern Recognition and Artificial Intelligence pp.25-30, 2016, MedPRAI-2016 Proceedings of the Mediterranean Conference on Pattern Recognition and Artificial Intelligence 〈http://dl.acm.org/citation.cfm?doid=3038884.3038889〉. 〈10.1145/3038884.3038889〉. 〈hal-01588373〉

Partager

Métriques

Consultations de la notice

54