[Insight-users] rgb images

Luis Ibanez luis.ibanez at kitware.com
Wed Jul 23 08:28:21 EDT 2008


Hi Maureen,

1) CenteredSimilarityTransform2D is an appropriate Transform to use.


2) The Affine transform is also an option, but keep in mind that
    with this transform you may get shearing deformations as well.

    Please read the description of these two transforms in the
    ITK Software Guide

            http://www.itk.org/ItkSoftwareGuide.pdf

    Search in the "Image Registration" chapter.


3) ITK will convert your RGB images to luminance, and then will cast
    the luminance pixel type to the pixel type that you used for
    instantiating the itk::Image inside your code.


Please let us know if you run into any problem.


    Thanks


       Luis


----------------------
Maureen Haining wrote:
> 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
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> 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