Persistence-based Structural Recognition

Chunyuan Li 1 Maks Ovsjanikov 2 Frederic Chazal 1
1 GEOMETRICA - Geometric computing
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Saclay - Ile de France
2 LIX, Ecole Polytechnique
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
Abstract : This paper presents a framework for object recognition using topological persistence. In particular, we show that the so-called persistence diagrams built from functions defined on the objects can serve as compact and informative descriptors for images and shapes. Complementary to the bag-of-features representation, which captures the distribution of values of a given function, persistence diagrams can be used to characterize its structural properties, reflecting spatial information in an invariant way. In practice, the choice of function is simple: each dimension of the feature vector can be viewed as a function. The proposed method is general: it can work on various multimedia data, including 2D shapes, textures and triangle meshes. Extensive experiments on 3D shape retrieval, hand gesture recognition and texture classification demonstrate the performance of the proposed method in comparison with state-of-the-art methods. Additionally, our approach yields higher recognition accuracy when used in conjunction with the bag-offeatures.
Type de document :
Communication dans un congrès
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, Jun 2014, Colombus, Ohio, United States. pp.1995-2002, 2014
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01073075
Contributeur : Frédéric Chazal <>
Soumis le : mercredi 8 octobre 2014 - 19:29:20
Dernière modification le : jeudi 9 février 2017 - 15:16:23

Identifiants

  • HAL Id : hal-01073075, version 1

Collections

Citation

Chunyuan Li, Maks Ovsjanikov, Frederic Chazal. Persistence-based Structural Recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, Jun 2014, Colombus, Ohio, United States. pp.1995-2002, 2014. <hal-01073075>

Partager

Métriques

Consultations de la notice

275