DMCA
Stable bounded canonical sets and image matching (2005)
| Venue: | IN ENERGY MINIMIZATION METHODS IN COMPUTER VISION AND PATTERN RECOGNITION, EMMCVPR 2005 |
| Citations: | 6 - 5 self |
BibTeX
@INPROCEEDINGS{Novatnack05stablebounded,
author = {John Novatnack and Trip Denton and Ali Shokoufandeh and Lars Bretzner},
title = {Stable bounded canonical sets and image matching},
booktitle = {IN ENERGY MINIMIZATION METHODS IN COMPUTER VISION AND PATTERN RECOGNITION, EMMCVPR 2005},
year = {2005},
pages = {316--331},
publisher = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A common approach to the image matching problem is representing images as sets of features in some feature space followed by establishing correspondences among the features. Previous work by Huttenlocher and Ullman [1] shows how a similarity transformation- rotation, translation, and scaling- between two images may be determined assuming that three corresponding image points are known. While robust, such methods suffer from computational inefficiencies for general feature sets. We describe a method whereby the feature sets may be summarized using the Stable Bounded Canonical Set (SBCS), thus allowing the efficient computation of point correspondences between large feature sets. We use a notion of stability to influence the set summarization such that stable image features are preferred.
Keyphrases
canonical set image matching stable bounded canonical set computational inefficiency large feature set previous work set summarization similarity transformation rotation common approach general feature set feature space point correspondence image point efficient computation feature extraction determine transformation stable image feature image matching problem
