Abstract | ||
---|---|---|
Image registration is a crucial and necessary step before image fusion. It aims to achieve the optimal match between two or more images of the same scene taken at different times, from different viewpoints, and/or by different sensors. In the procedure of image registration, several types of uncertainty will be encountered, e.g., the selection of control points and the distance or the dissimilarity measures used for image matching. In this paper, we model these uncertainty in image registration using the theory of belief functions. By jointly using the pixel level and feature level information, more effective image registrations are accomplished. Experimental results, comparisons and related analyses illustrate the effectiveness of our evidential reasoning based image registration approach. |
Year | DOI | Venue |
---|---|---|
2013 | null | Fusion |
Keywords | DocType | Volume |
image matching,image fusion,case-based reasoning,belief functions,uncertainty,dissimilarity,optimal match,image registration,evidential reasoning,measurement uncertainty,cognition,psnr,case based reasoning | Conference | null |
Issue | ISBN | Citations |
null | 978-605-86311-1-3 | 0 |
PageRank | References | Authors |
0.34 | 10 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Deqiang Han | 1 | 218 | 22.90 |
Jean Dezert | 2 | 777 | 61.59 |
Shicheng Li | 3 | 0 | 0.34 |
Chongzhao Han | 4 | 446 | 71.68 |
Yi Yang | 5 | 1 | 1.36 |