A comparison of affine region detectors

Abstract : The paper gives a snapshot of the state of the art in affine covariant region detectors, and compares their performance on a set of test images under varying imaging conditions. Six types of detectors are included: detectors based on affine normalization around Harris (Mikolajczyk and Schmid, 2002; Schaffalitzky and Zisserman, 2002) and Hessian points (Mikolajczyk and Schmid, 2002), a detector of ‘maximally stable extremal regions', proposed by Matas et al. (2002); an edge-based region detector (Tuytelaars and Van Gool, 1999) and a detector based on intensity extrema (Tuytelaars and Van Gool, 2000), and a detector of ‘salient regions', proposed by Kadir, Zisserman and Brady (2004). The performance is measured against changes in viewpoint, scale, illumination, defocus and image compression. The objective of this paper is also to establish a reference test set of images and performance software, so that future detectors can be evaluated in the same framework.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2005, 65 (1/2), pp.43--72. 〈http://www.springerlink.com/content/744376233t370532/〉. 〈10.1007/s11263-005-3848-x〉
Liste complète des métadonnées

Littérature citée [46 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548528
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:09:11
Dernière modification le : mercredi 11 avril 2018 - 01:57:01
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:10:05

Fichier

affine_ijcv05.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Krystian Mikolajczyk, Tinne Tuytelaars, Cordelia Schmid, Andrew Zisserman, Jiri Matas, et al.. A comparison of affine region detectors. International Journal of Computer Vision, Springer Verlag, 2005, 65 (1/2), pp.43--72. 〈http://www.springerlink.com/content/744376233t370532/〉. 〈10.1007/s11263-005-3848-x〉. 〈inria-00548528〉

Partager

Métriques

Consultations de la notice

1116

Téléchargements de fichiers

4094