M. Rukoz,
M. Manouvrier, and
G. Jomier.
Quadtree-based Distances between Images.
Technical report 37 (Note de recherche en ligne ISSN : 1769-7417),
Paris-Dauphine University,
2003.
Submitted to publication - Revision in progress.
Abstract: This article presents the Delta-distance, a generalization of image similarity distances defined on images represented with a quadtree. A quadtree is a recursive partitioning structure which can be used to handle posi tional information of image features in content-based image retrieval. Using different weights on quadtree nod es and different distances between nodes, distances between quadtrees or perceptual similarity between images can be computed based on the general definition of Delta. We show how existing quadtree-based image distanc es appear to be particular cases of the Delta-distance. Moreover, new distances between images can be defin ed based on the Delta-distance definition.
@TechReport{RMJ03,
author = {Rukoz, M. and Manouvrier, M. and Jomier, G.},
title = {{Quadtree-based Distances between Images}},
institution = {Paris-Dauphine University},
year = {2003},
number = {37 (Note de recherche en ligne ISSN : 1769-7417)},
note = {Submitted to publication - Revision in progress},
abstract = {This article presents the Delta-distance, a generalization of image similarity distances defined on images represented with a quadtree. A quadtree is a recursive partitioning structure which can be used to handle posi tional information of image features in content-based image retrieval. Using different weights on quadtree nod es and different distances between nodes, distances between quadtrees or perceptual similarity between images can be computed based on the general definition of Delta. We show how existing quadtree-based image distanc es appear to be particular cases of the Delta-distance. Moreover, new distances between images can be defin ed based on the Delta-distance definition.}
}