Name
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. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/TIP.2008.2006602 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
semisupervised feature matching,feature geometric coherency,image matching,propagation,semi-supervised feature matching,spatial graph,sparse reliable correspondence priors,propagation.,weak prior,pairwise feature similarity,correspondence propagation,pairwise feature agreement,product graph,feature set,reliable correspondence,feature geometric relationship,weak priors,bipartite similarity graph,graph theory,image registration,feature matching algorithm,index terms image registration,feature matching,efficient feature,pairwise assignment,pairwise feature agreements,geometric neighborhood,object correspondence,state-of-the-art feature,labeling,indexing terms,algorithm design and analysis,accuracy,feature extraction | Graph theory,Pairwise comparison,Computer vision,Algorithm design,Pattern recognition,Feature (computer vision),Bipartite graph,Feature extraction,Artificial intelligence,3-dimensional matching,Mathematics,Image registration | Journal |
Volume | Issue | ISSN |
18 | 1 | 1057-7149 |
Citations | PageRank | References |
5 | 0.55 | 18 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Huan Wang | 1 | 457 | 19.67 |
| Shuicheng Yan | 2 | 767 | 25.71 |
| Jianzhuang Liu | 3 | 1614 | 98.72 |
| Xiaoou Tang | 4 | 15728 | 670.19 |
| Thomas S. Huang | 5 | 27815 | 2618.42 |