Shape Palindromes: Analysis of Intrinsic Symmetries in 2D Articulated Shapes

Abstract : Analysis of intrinsic symmetries of non-rigid and articulated shapes is an important problem in pattern recognition with numerous applications ranging from medicine to computational aesthetics. Considering articulated planar shapes as closed curves, we show how to represent their extrinsic and intrinsic symmetries as self-similarities of local descriptor sequences, which in turn have simple interpretation in the frequency domain. The problem of symmetry detection and analysis thus boils down to analysis of descriptor sequence patterns. For that purpose, we show two efficient computational methods: one based on Fourier analysis, and another on dynamic programming. Metaphorically, the later can be compared to finding palindromes in text sequences.
Type de document :
Communication dans un congrès
Alfred M. Bruckstein and Bart M. ter Haar Romeny and Alexander M. Bronstein and Michael M. Bronstein. SSVM 2011 - 3rd International Conference on Scale Space and Variational Methods in Computer Vision, May 2011, Ein-Gedi, Israel. Springer-Verlag, 6667, pp.665-676, 2012, Lecture Notes in Computer Science. 〈10.1007/978-3-642-24785-9_56〉
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00590276
Contributeur : Team Perception <>
Soumis le : mardi 3 mai 2011 - 09:54:34
Dernière modification le : mercredi 11 avril 2018 - 01:58:55
Document(s) archivé(s) le : vendredi 9 novembre 2012 - 10:25:12

Fichier

paper-79.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Amit Hooda, Michael Bronstein, Alexander Bronstein, Radu Horaud. Shape Palindromes: Analysis of Intrinsic Symmetries in 2D Articulated Shapes. Alfred M. Bruckstein and Bart M. ter Haar Romeny and Alexander M. Bronstein and Michael M. Bronstein. SSVM 2011 - 3rd International Conference on Scale Space and Variational Methods in Computer Vision, May 2011, Ein-Gedi, Israel. Springer-Verlag, 6667, pp.665-676, 2012, Lecture Notes in Computer Science. 〈10.1007/978-3-642-24785-9_56〉. 〈inria-00590276〉

Partager

Métriques

Consultations de la notice

250

Téléchargements de fichiers

221