Abstract
We introduce a new non-linear registration model based on a curvature type regularizer. We show that affine linear transformations belong to the kernel of this regularizer. Consequently, an additional global registration is superfluous. Furthermore, we present an implementation of the new scheme based on the numerical solution of the underlying Euler-Lagrange equations. The real discrete cosine transform is the backbone of our implementation and leads to a stable and fast backslashmathcalO(n backslashlog n)algorithm, where n denotes the number of voxels. We demonstrate the advantages of the new technique for synthetic data sets. Moreover, first convincing results for the registration of MR-mammography images are presented.
Original language | English |
---|---|
Title of host publication | Computational Science --- ICCS 2002 |
Editors | Peter M. A. Sloot, Alfons G. Hoekstra, C. J. Kenneth Tan, Jack J. Dongarra |
Number of pages | 5 |
Volume | 2331 |
Place of Publication | Berlin, Heidelberg |
Publisher | Springer Berlin Heidelberg |
Publication date | 10.04.2002 |
Pages | 202-206 |
ISBN (Print) | 978-3-540-43594-5 |
ISBN (Electronic) | 978-3-540-47789-1 |
DOIs | |
Publication status | Published - 10.04.2002 |
Event | International Conference on Computational Science 2002 - Amsterdam, Netherlands Duration: 21.04.2002 → 24.04.2002 Conference number: 96801 |