Please use this identifier to cite or link to this item: https://doi.org/10.1109/TIP.2008.2006602
Title: Correspondence propagation with weak priors
Authors: Wang, H.
Yan, S. 
Liu, J.
Tang, X.
Huang, T.S.
Keywords: Feature matching
Image registration
Object correspondence
Propagation
Weak prior
Issue Date: 2009
Source: Wang, H., Yan, S., Liu, J., Tang, X., Huang, T.S. (2009). Correspondence propagation with weak priors. IEEE Transactions on Image Processing 18 (1) : 140-150. ScholarBank@NUS Repository. https://doi.org/10.1109/TIP.2008.2006602
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. © 2008 IEEE.
Source Title: IEEE Transactions on Image Processing
URI: http://scholarbank.nus.edu.sg/handle/10635/55459
ISSN: 10577149
DOI: 10.1109/TIP.2008.2006602
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

11
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

11
checked on Nov 16, 2017

Page view(s)

23
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.