Learning Shape Segmentation Using Constrained Spectral Clustering and Probabilistic Label Transfer

Avinash Sharma 1 Etienne Von Lavante 1 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We propose a spectral learning approach to shape segmentation. The method is composed of a constrained spectral clustering algorithm that is used to supervise the segmentation of a shape from a training data set, followed by a probabilistic label transfer algorithm that is used to match two shapes and to transfer cluster labels from a training-shape to a test-shape. The novelty resides both in the use of the Laplacian embedding to propagate must-link and cannot-link constraints, and in the segmentation algorithm which is based on a learn, align, transfer, and classify paradigm. We compare the results obtained with our method with other constrained spectral clustering methods and we assess its performance based on ground-truth data.
Type de document :
Communication dans un congrès
Kostas Daniilidis and Petros Maragos and Nikos Paragios. ECCV 2010 - European Conference on Computer Vision, Sep 2010, Heraklion, Greece. Springer, 6315, pp.743-756, 2010, Lecture Notes in Computer Science. 〈10.1007/978-3-642-15555-0_54〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00549401
Contributeur : Radu Horaud <>
Soumis le : mardi 21 décembre 2010 - 21:23:42
Dernière modification le : jeudi 11 janvier 2018 - 06:22:00
Document(s) archivé(s) le : mardi 22 mars 2011 - 03:14:21

Fichier

SharmaLavanteHoraudECCV2010.pd...
Accord explicite pour ce dépôt

Identifiants

Collections

Citation

Avinash Sharma, Etienne Von Lavante, Radu Horaud. Learning Shape Segmentation Using Constrained Spectral Clustering and Probabilistic Label Transfer. Kostas Daniilidis and Petros Maragos and Nikos Paragios. ECCV 2010 - European Conference on Computer Vision, Sep 2010, Heraklion, Greece. Springer, 6315, pp.743-756, 2010, Lecture Notes in Computer Science. 〈10.1007/978-3-642-15555-0_54〉. 〈inria-00549401〉

Partager

Métriques

Consultations de la notice

269

Téléchargements de fichiers

228