Skip to Main content Skip to Navigation
Journal articles

Segmentation de catégories d'objets par combinaison d'un modèle d'apparence et d'un champ de Markov

Diane Larlus 1 Frédéric Jurie 2
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
2 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : In this article, we consider the task of category level object segmentation. Object models based on bag-of-words representations achieve state-of-the-art performance for object recognition. However, they fail to accurately locate object boundaries and thus produce inaccurate object segmentation. On the other hand, Markov Random Field based models used for image segmentation focus on object boundaries but can hardly use global object constraints, which is required when dealing with object categories whose appearance may vary significantly. The key contribution of this paper is to combine the advantages of these two approaches. First, a blob-based mechanism allows to detect objects using visual word occurrences, and produces rough image segmentation. Second, a MRF component produces clean cuts, guided by local image cues (color, texture and edge cues) and by long-distance dependency given by the blob model, which enforces label consistency. Our approach is validated on standard public datasets, containing different object classes, in presence of cluttered backgrounds and large view point changes.
Document type :
Journal articles
Complete list of metadatas
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 10:25:16 AM
Last modification on : Thursday, November 19, 2020 - 1:00:24 PM


  • HAL Id : inria-00548667, version 1


Diane Larlus, Frédéric Jurie. Segmentation de catégories d'objets par combinaison d'un modèle d'apparence et d'un champ de Markov. Revue I3 - Information Interaction Intelligence, Cépaduès, 2008, 8 (2). ⟨inria-00548667⟩



Record views