Improving the matching precision of SIFT

Zhongwei Tang 1 Pascal Monasse 2, 3, 4 Jean-Michel Morel 1
2 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : Matching precision of scale-invariant feature transform (SIFT) is evaluated and improved in this paper. The aim of the paper is not to invent a new feature detector more invariant than the others. Instead, we focus on SIFT method and evaluate and improve the matching precision, defined as the root mean square error (RMSE) under ground truth geometric trans-form. Matching precision reflects to some extent the average relative localization precision between two images. For scale invariant feature detectors like SIFT, the matching precision decreases with the scale of features due to the sub-sampling in the scale space. We propose to cancel the sub-sampling to improve the matching precision. But in case of scale change, the improvement is marginal due to the coarse scale quanti-zation in the scale space. One more sophisticated method is also proposed to improve the matching precision in case of scale change. These modifications can be easily extended to other scale invariant feature detectors.
Type de document :
Communication dans un congrès
International Conference on Image Processing, Oct 2014, Paris, France. 2015, Image Processing (ICIP), 2014 IEEE International Conference on. 〈10.1109/ICIP.2014.7026164〉
Liste complète des métadonnées

Littérature citée [2 références]  Voir  Masquer  Télécharger

https://hal-enpc.archives-ouvertes.fr/hal-01075813
Contributeur : Pascal Monasse <>
Soumis le : lundi 20 octobre 2014 - 12:47:07
Dernière modification le : jeudi 5 juillet 2018 - 14:25:52
Document(s) archivé(s) le : mercredi 21 janvier 2015 - 10:46:21

Fichier

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

Licence


Distributed under a Creative Commons Paternité - Pas d'utilisation commerciale - Pas de modification 4.0 International License

Identifiants

Citation

Zhongwei Tang, Pascal Monasse, Jean-Michel Morel. Improving the matching precision of SIFT. International Conference on Image Processing, Oct 2014, Paris, France. 2015, Image Processing (ICIP), 2014 IEEE International Conference on. 〈10.1109/ICIP.2014.7026164〉. 〈hal-01075813〉

Partager

Métriques

Consultations de la notice

864

Téléchargements de fichiers

705