<table cellspacing="0" cellpadding="0" border="0" ><tr><td valign="top" style="font: inherit;">Hi Yi,<div><br></div><div>Each vector in the deformation filed image has the same dimension as the input image,</div><div><br></div><div>meaning that it has equal number of dimensions for each pixel corresponding to movement</div><div><br></div><div>of the input pixel. Naturally the deformation field image would have the same size as</div><div><br></div><div>the input image so it wold cover all the pixels in the input image.</div><div><br></div><div>As for your third question, note that the input and output image would also have the same</div><div><br></div><div>size, so using the deformation field it is clear that which pixels correspond to each other.</div><div><br></div><div>Hope this answers your
questions,</div><div><br></div><div>Dawood</div><div><br></div><div><br></div><div>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<</div><div><br></div><div>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<</div><div><br></div><div><br></div><div><span class="Apple-style-span" style="font-family: 'Times New Roman'; font-size: medium; "><pre>Dear group,
I'm a little confused about the itkWarpImageFilter....
1. I understand that in computing the deformed (output) image, we
should go through the domain of the *output* image, and inversely
trace back (according to the deformation vector field) to find the
intensity in the input image.
2. However, on page 242 of the software guide, above equation 6.21, we
see that the deformation vector field (as a vector image) should have
the same size as the *input* image. So the deformation field is
defined on the domain of the *input* image.
3. Then, go back to item 1, how do we achieve the inversion of the
vector field so as it defines on the domain of the *output* image?
Is there anything I misunderstand? Thanks for any hint!
Best,
yi</pre></span></div></td></tr></table>