[Insight-users] TPS Interpolation in 3D

[Kerstin Müller]

Hello everybody,

I'll have a question regarding the TPS interpolation in 3-D. I'm reading
the paper of Davis which is cited in the itk Documentation.

Is there a good explanation why the kernel matrix G considers only | r |
and not r^2 log(r) in 3-D ? I can't find a proper solution, why this holds.
And there are even both implementations in itk, but I'll get better results
with the first one.
Furthermore, how do i ensure that the points further away from the control
points are only affected by the affine transformation?

Thanks a lot for answering.

Best,

Kerstin
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20111215/1d8b792f/attachment.htm>