[Insight-users] itkSYN itkBsplineSYN Image Registration- Optimizer Documentation??

brian avants stnava at gmail.com
Wed Jan 22 11:23:09 EST 2014


hi emma

many answers can be found by reading through relevant tests.  for example:

https://github.com/InsightSoftwareConsortium/ITK/blob/master/Modules/Registration/RegistrationMethodsv4/test/itkBSplineSyNImageRegistrationTest.cxx

these tests represent raw material for a v4 software guide which hans
johnson is leading.

the fast variant of syn is similar to "the demons algorithm"

in that it is a specific algorithm, not a generic one.

so, to answer your questions:

Is there a simple way to set the learning rate given a scaleEstimator for
> these methods (without using the ans registration helper ) or must one
> simply choose one at the beginning and hope for the best??
>

yes - just set the learning rate at the beginning ( e.g 0.1 ).

syn takes care of rescaling over iterations internally.   no scaleEstimator

is needed for displacement fields/diffeomorphisms because the parameters

all scale in the same way.

changes in x are equivalent to changes in y.

changes in x are different than changes in theta.


>
> I am also finding it difficult to determine which optimizer these methods
> use as in the ANTS headers there are two options a GradientDescent and a
> conjugate gradient descent, any ideas??
>

greedy syn uses its own optimization fast optimization of the diff
objective.  time varying syn uses gradient descent.  memory concerns abound
when you move beyond these first order approaches.


>
> I initially used the ITK libraries as they provided a method that I could
> begin using state of the art image processing algorithms without the steep
> learning curve, is there any pending documentation or software guide for
> the new ITKV4 framework.
>

Great to hear!  Keep at it.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20140122/a625678f/attachment.html>


More information about the Insight-users mailing list