[Insight-users] Determining itk::RegularStepGradientDescentOptimizer->SetScales()

Luis Ibanez luis.ibanez at kitware.com
Wed Apr 27 11:39:17 EDT 2005


Hi Jan,

The rule of thumb is to figure out how much each one of those
parameters will change for your registration, and then rescale
that range to [-1:1].

For example,

if you are doing 2D rigid you will have a 2D transform with
three parameters:

      Tx  translation in millimeters along X
      Ty  translation in millimeters along Y
      R   rotation in radians

and you anticipate that your images need a correction of the
order of 10 to 50 millimeters in translation and 0.01 to 0.1
radians in rotation, then you should put scales:

      scale[0] = 1/50;     scale for Tx
      scale[1] = 1/50;     scale for Ty
      scale[2] = 1/0.1;    scale for Rotation

Of course, those will be just "good values to start with".
You will still need to refine them according to the behavior
of the optimizer.


Regards,


    Luis



---------------------
Jan Schreiber wrote:

> Hello ITK-Users, 
> 
> I am performing registration on 2D x-ray images, using
> MattesMutualInformation, Similarity2DTransform, AffineTransform and
> RegularStepGradientDescentOptimizer. 
> 
> Does anyone know a good way to determine the values for the SetScales()
> function?
> Is there a methodical way to compute these values or to estimate them
> from samples?
> 
> I played around with some values I took from the examples with the
> result that it works for some images but not for others (e.g. different
> image size)
> 
> Thanks in advance, 
> Jan
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
> 
> 





More information about the Insight-users mailing list