[Insight-users] Deformation vectors in the BSplineDeformationTransform?

[Charl Botha]

2009/8/18 motes motes <mort.motes at gmail.com>:
> "Mapping the moving image onto the fixed image is much easier when you
> simply have to iterate over the pixels / voxels of the fixed image,
> and for each pixel / voxel you have a vector pointing to the position
> in the moving domain that you have to interpolate.  For example, for a
> 2D case, you'd have a stock-standard double nested loop (rows /
> columns) for the fixed image, at each position you'd look up the
> corresponding vector, use that to determine the position in the moving
> space, interpolate the moving image pixel, then put that at your
> current position in the fixed image."
>
> But on page 227 in the itkSoftwareGuide it says:
>
> "Probably the most important thing to keep in mind when resampling
> images is that the transform
> is used to map points from the output image space into the input image
> space. In this case,
> Figure 6.42 shows that the translation is applied to every point of
> the output image and the
> resulting position is used to read the intensity from the input image."
>
>
> But maybe you assume that the moving image is the input image and the
> fixed inmage is the output image in the transform?

I'm not assuming anything.  In this context I always refer to fixed
and moving images, as most of the deformable registration filters do.