Constructing models for content-based image retrieval

Cordelia Schmid 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper presents a new method for constructing models from a set of positive and negative sample images ; the method requires no manual extraction of significant objects or features. Our model representation is based on two layers. The first one consists of “generic” descriptors which represent sets of similar rotational invariant feature vectors. Rotation invariance allows to group similar, but rotated patterns and makes the method robust to model deformations. The second layer is the joint probability on the frequencies of the “generic” descriptors over neighborhoods. This probability is multi-modal and is represented by a set of “spatial-frequency” clusters. It adds a statistical spatial constraint which is rotationally invariant. Our twolayer representation is novel ; it allows to efficiently capture “texture-like” visual structure. The selection of distinctive structure determines characteristic model features (common to the positive and rare in the negative examples) and increases the performance of the model. Models are retrieved and localized using a probabilistic score. Experimental results for “textured” animals and faces show a very good performance for retrieval as well as localization.
Type de document :
Communication dans un congrès
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR '01), Dec 2001, Kauai, United States. IEEE Computer society, 2, pp.11--39, 2001, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=990922〉. 〈10.1109/CVPR.2001.990922〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548274
Contributeur : Thoth Team <>
Soumis le : mardi 21 décembre 2010 - 11:39:54
Dernière modification le : mercredi 11 avril 2018 - 01:56:19
Document(s) archivé(s) le : mardi 22 mars 2011 - 02:32:11

Fichier

Schmid_CVPPR01.ps-1.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Cordelia Schmid. Constructing models for content-based image retrieval. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR '01), Dec 2001, Kauai, United States. IEEE Computer society, 2, pp.11--39, 2001, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=990922〉. 〈10.1109/CVPR.2001.990922〉. 〈inria-00548274〉

Partager

Métriques

Consultations de la notice

368

Téléchargements de fichiers

1156