Constructing models for content-based image retrieval - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2001

Constructing models for content-based image retrieval


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.
Fichier principal
Vignette du fichier (291.31 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00548274 , version 1 (21-12-2010)



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. pp.11--39, ⟨10.1109/CVPR.2001.990922⟩. ⟨inria-00548274⟩
198 View
1344 Download



Gmail Facebook X LinkedIn More