A New Normalized Supervised Edge Detection Evaluation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

A New Normalized Supervised Edge Detection Evaluation

Résumé

In digital images, edges characterize object boundaries, then their detection remains a crucial stage in numerous applications. To achieve this task, many edge detectors have been designed, producing different results, with different qualities. Evaluating the response obtained by these detectors has become a crucial task. In this paper, several referenced-based boundary detection evaluations are detailed, pointing their advantages and disadvantages through concrete examples of edge images. Then, a new supervised edge map quality measure is proposed, comparing a ground truth contour image, the candidate contour image and their associated spacial nearness. Compared to other boundary detection assessments, this new method has the advantage to be normalized and remains a more reliable edge map quality measure.
Fichier principal
Vignette du fichier
template_IbPRIA2017_finale.pdf (1021.34 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01940333 , version 1 (30-11-2018)

Identifiants

Citer

Hasan Abdulrahman, Baptiste Magnier, Philippe Montesinos. A New Normalized Supervised Edge Detection Evaluation. IbPRIA 2017 - Iberian Conference on Pattern Recognition and Image Analysis, Jun 2017, Faro, Portugal. pp.203-213, ⟨10.1007/978-3-319-58838-4_23⟩. ⟨hal-01940333⟩
21 Consultations
105 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More