Minimum Description Length and the Inference of Scene Structure from Images

Abstract : Model selection is a central task in computer vision. The minimum description length (MDL) method links model selection to data compression: the best model is the one which yields the largest compression of the data. The general theoretical framework for compression is Kolmogorov complexity. MDL differs from Bayesian model selection (BMS) in that it is biased against complex probability density functions. MDL is applied to a model selection problem in computer vision. The following models are considered: background, collineation, affine fundamental and fundamental models. The experiments show that the collineation model is a good choice even for sets of image correspondences for which the 'true' model is a fundamental matrix.
keyword : computer vision
Type de document :
Communication dans un congrès
IEE Colloquium on Applications of Statistics to Pattern Recognition, Apr 1999, Birmingham, United Kingdom. 1999, 〈10.1049/ic:19990366〉
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00525678
Contributeur : Peter Sturm <>
Soumis le : lundi 30 mai 2011 - 12:11:47
Dernière modification le : lundi 30 mai 2011 - 13:16:17
Document(s) archivé(s) le : mercredi 31 août 2011 - 02:21:13

Fichiers

MaybankSturm-iee99.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Steve Maybank, Peter Sturm. Minimum Description Length and the Inference of Scene Structure from Images. IEE Colloquium on Applications of Statistics to Pattern Recognition, Apr 1999, Birmingham, United Kingdom. 1999, 〈10.1049/ic:19990366〉. 〈inria-00525678〉

Partager

Métriques

Consultations de la notice

67

Téléchargements de fichiers

70