DocumentCode :
3559746
Title :
Correspondence Propagation with Weak Priors
Author :
Wang, Huan ; Yan, Shuicheng ; Liu, Jianzhuang ; Tang, Xiaoou ; Huang, Thomas S.
Author_Institution :
Dept. of Comput. Sci., Yale Univ., New Haven, CT
Volume :
18
Issue :
1
fYear :
2009
Firstpage :
140
Lastpage :
150
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.
Keywords :
graph theory; image matching; image registration; bipartite similarity graph; correspondence propagation; feature geometric coherency; feature geometric relationship; feature matching algorithm; geometric neighborhood; image registration; pairwise assignment; pairwise feature agreements; pairwise feature similarity; product graph; semisupervised feature matching; sparse reliable correspondence priors; spatial graph; weak priors; Application software; Closed-form solution; Computer vision; Councils; Detectors; Feature extraction; Image recognition; Image registration; Quadratic programming; Three dimensional displays; Feature matching, weak prior; image registration; object correspondence; propagation; Algorithms; Artificial Intelligence; Image Enhancement; Image Interpretation, Computer-Assisted; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique;
fLanguage :
English
Journal_Title :
Image Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1057-7149
Type :
jour
DOI :
10.1109/TIP.2008.2006602
Filename :
4711355
Link To Document :
بازگشت