Abstract | ||
---|---|---|
Inthispaper,wedevelopdatadrivenregistrationalgorithms, relying on robust pixel similarity metrics, that enable an accurate (sub- pixel) rigid registration of dissimilar single and multimodal 2D/3D im- ages.A\softredescending"estimatorisassociatedtoatopdownstochatic multigrid relaxation algorithm in order to obtain robust, data driven multimodal image registrations. With the stochastic multigrid strategy, the registration is not aected by local minima in the objective function and a manual initialization near the optimal solution is not necessary. Theproposedrobustsimilaritymetricsarecomparedtothemostpopular standard similarity metrics, on synthetic as well as on real world image pairs showing gross dissimilarities. Two case-studies are considered: the registrationof single and multimodal 3D medical imagesand thematch- ingofmultispectralremotelysensedimagesshowinglargeovercastareas. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1007/BFb0054733 | ECCV (2) |
Keywords | Field | DocType |
dissimilar single,multimodal images,robust registration,image registration,objective function,local minima | Computer vision,Computer science,Multispectral image,Image processing,Mutual information,Artificial intelligence,Pixel,Initialization,Multigrid method,Machine learning,Image registration,Estimator | Conference |
ISBN | Citations | PageRank |
3-540-64613-2 | 2 | 0.42 |
References | Authors | |
14 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
C. Nikou | 1 | 679 | 46.56 |
Fabrice Heitz | 2 | 401 | 59.55 |
Jean-Paul Armspach | 3 | 221 | 26.60 |