Abstract | ||
---|---|---|
A multi-label point-set registration method is presented in this paper. It focuses on carefully computing an initial transform to help the registration process converge towards the optimal deformation. The proposed method is particularly efficient in cases where the deformation is discontinuous or nearly discontinuous. A simple synthetic example is presented to illustrate the advantage of the method. A real-data example is also presented in the context of multi-modality registration (blockface to Magnetic Resonance Imaging, MRI) for brain atlas construction. In both examples, visual and numeric results illustrate the superiority of the presented method compared to two recent multi-label registration contributions. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ISBI.2015.7163947 | 2015 IEEE 12TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI) |
Keywords | Field | DocType |
Point-set registration, Deformable registration, Rigidity constraints, Atlas construction, Tupinambis | Computer vision,Point set registration,Brain atlas,Pattern recognition,Medical imaging,Computer science,Image segmentation,Artificial intelligence,Image registration | Conference |
ISSN | Citations | PageRank |
1945-7928 | 0 | 0.34 |
References | Authors | |
9 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
E Van Reeth | 1 | 4 | 2.50 |
Michaël Sdika | 2 | 81 | 9.17 |
Pierre-Herve Luppi | 3 | 0 | 0.34 |
Paul-Antoine Libourel | 4 | 0 | 0.34 |
Olivier Beuf | 5 | 1 | 2.07 |