Approximate reflectional symmetries of fuzzy objects with an application in model-based object recognition - Département Image, Données, Signal Accéder directement au contenu
Article Dans Une Revue Fuzzy Sets and Systems Année : 2004

Approximate reflectional symmetries of fuzzy objects with an application in model-based object recognition

Résumé

This paper is devoted to the study of reflectional symmetries of fuzzy objects. We introduce a symmetry measure which defines the degree of symmetry of an object with respect to a given plane. It is computed by measuring the similarity between the original object and its reflection. The choice of an appropriate measure of comparison is based on the desired properties of the symmetry measure. Then, an algorithm for computing the symmetry plane of fuzzy objects is proposed. This is done using an optimization technique in the space of plane parameters. Finally, we illustrate our approach with an application where the symmetry measure is used as an attribute in graph matching for model-based object recognition.
Fichier principal
Vignette du fichier
colliot_fss2004_postprint.pdf (1.05 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01251244 , version 1 (05-01-2016)

Identifiants

Citer

Olivier Colliot, Alexander V. Tuzikov, Roberto M. Cesar, Isabelle Bloch. Approximate reflectional symmetries of fuzzy objects with an application in model-based object recognition. Fuzzy Sets and Systems, 2004, 147 (1), pp.141-163. ⟨10.1016/j.fss.2003.07.003⟩. ⟨hal-01251244⟩
76 Consultations
112 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More