Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

D. Zikic, A. Kamen, N. Navab
Unifying Characterization of Deformable Registration Methods Based on the Inherent Parameterization
International Workshop on Biomedical Image Registration (WBIR), in Lübeck, Germany, July 11-13 2010. (bib)

In this paper, we propose to characterize some of the most common deformable registration methods in a unified way, based on their parameterization. In contrast to traditional classifications, we do not apply this characterization only to standard 'parametric' methods such as B-Spline Free-form deformations, but extend it to 'non-parametric' methods, that is, the variational approach with explicitly defined regularization energy, and the Demons method. To this end, we consider parameterizations by linear combinations of arbitrary basis functions. For the variational approach we utilize the tensor product piecewise linear bases, as used for linear interpolation. For the fluid demons method, we demonstrate that this approach can be seen an inherently parameterized by densely located Gaussian basis functions. Stating the inherent parameterization of these approaches allows a clear distinction between these methods. This point of view opens new possible ways of relating the different methods to each other.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Edit | Attach | Refresh | Diffs | More | Revision r1.13 - 30 Jan 2019 - 15:16 - LeslieCasas

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif