DMCA
Correspondence Propagation with Weak Priors
| Citations: | 2 - 0 self |
BibTeX
@MISC{Wang_correspondencepropagation,
author = {Huan Wang and Shuicheng Yan and Jianzhuang Liu and Xiaoou Tang and Thomas S. Huang},
title = {Correspondence Propagation with Weak Priors},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
For the problem of image registration, the top few reliable correspondences are often relatively easy to obtain, while the overall matching accuracy may fall drastically as the desired correspondence number increases. In this paper, we present an efficient feature matching algorithm to employ sparse reliable correspondence priors for piloting the feature matching process. First, the feature geometric relationship within individual image is encoded as a spatial graph, and the pairwise feature similarity is expressed as a bipartite similarity graph between two feature sets; then the geometric neighborhood of the pairwise assignment is represented by a categorical product graph, along which the reliable correspondences are propagated; and finally a closed-form solution for feature matching is deduced by ensuring the feature geometric coherency as well as pairwise feature agreements. Furthermore, our algorithm is naturally applicable for incorporating manual correspondence priors for semi-supervised feature matching. Extensive experiments on both toy examples and real-world applications demonstrate the superiority of our algorithm over the state-of-the-art feature matching techniques.
Keyphrases
weak prior individual image feature geometric relationship efficient feature sparse reliable correspondence prior pairwise feature agreement state-of-the-art feature feature set toy example overall matching accuracy spatial graph closed-form solution geometric neighborhood pairwise feature similarity extensive experiment semi-supervised feature bipartite similarity graph manual correspondence prior feature geometric coherency desired correspondence number increase categorical product graph feature matching image registration top reliable correspondence reliable correspondence real-world application pairwise assignment
