[Insight-users] rgb images

[Maureen Haining]

Good Morning ITK Users,

I have two black and white RGB images (.tif file format) and would like to
register one to the other. The registration will require a translation,
rotation and scale.

1. I am looking at the ImageRegistration7 example that demonstrates the use
of the CenteredSimilarity2DTransform. Would this be the most appropriate
approach to use?

2. Would the ImageRegistration9 example (the AffineTransform) also be a
possible approach? Could you give a simple explanation of the difference
between the two?

3. This example uses PixelType float when defining the images.  Would I need
to cast my images to pixel type float first? Or perhaps use the
ImageAdaptor? Alternatively I could obtain my images in 8-bit or 16-bit grey
scale .tif format and imput those images into the optimizer. Would this be a
better approach?

Thank you for any help you can provide. I am new to medical imaging and can
use as much specific information as you can give.

Maureen
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20080722/5f02b0fa/attachment.htm>