inria-00548649, version 1
Latent mixture vocabularies for object categorization and segmentation
Diane Larlus 1Frédéric Jurie
a, 1, 2
Image and Vision Computing 27, 5 (2009) 523--534
Résumé : The visual vocabulary is an intermediate level representation which has been proved to be very powerful for addressing object categorization problems. It is generally built by vector quantizing a set of local image descriptors, independently of the object model used for categorizing images. We propose here to embed the visual vocabulary creation within the object model construction, allowing to make it more suited for object class discrimination and therefore for object categorization. We also show that the model can be adapted to perform object level segmentation task, without needing any shape model, making the approach very adapted to high intra-class varying objects.
- a – Université de Caen
- 1 : LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
- CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
- 2 : Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen (GREYC)
- CNRS : UMR6072 – Université de Caen – Ecole Nationale Supérieure d'Ingénieurs de Caen
- Domaine : Informatique/Vision par ordinateur et reconnaissance de formes
- Mots-clés : Object categorization – Object segmentation – Visual vocabulary creation
- inria-00548649, version 1
- http://hal.inria.fr/inria-00548649
- oai:hal.inria.fr:inria-00548649
- Contributeur : Team Lear
- Déposé pour le compte de :
- Soumis le : Mercredi 27 Avril 2011, 13:26:45
- Dernière modification le : Mardi 10 Mai 2011, 15:54:00
Documents associés
Exporter