[Insight-users] Using MultiResolutionImageRegistrationMethod

[Karthik Krishnan]

Ranjan, Sohan (GE, Research) wrote:

>I would appreciate if I could get clarification on the following vis-a-vis 
>MultiResolutionImageRegistrationMethod:
>
>1. Does the code uses copies of downsampled images for computation, or 
>    image iterators are used smartly for computation?
>
>  
>
Yes, its copies of downsampled images.

>2. Is it possible to skip levels in registration? 
>
>  
>
Yes. You have the liberty of specifying your own shrink levels for 
registration.

http://www.itk.org/Insight/Doxygen/html/classitk_1_1MultiResolutionPyramidImageFilter.html

>For example, suppose I have a huge image which is read, but I want to do registration
>at the four-times resolution. Can I use an instance of MultiResolutionImageRegistrationMethod 
>with, say, 4 levels, and then I do registration only at the extreme coarse level and exit. By doing 
>this, I would not need to make an extra copy of the downsampled image.
>
>
>Sohan Ranjan
>
>_______________________________________________
>Insight-users mailing list
>Insight-users at itk.org
>http://www.itk.org/mailman/listinfo/insight-users
>
>  
>