<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=gb2312">
<META content="MSHTML 6.00.2900.2963" name=GENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=#ffffff>
<DIV><FONT face="Bookman Old Style">Hi,</FONT></DIV>
<DIV><FONT face="Bookman Old Style"></FONT> </DIV>
<DIV><FONT face="Bookman Old Style">I have two landmards. The source landmarks
pt1 is a set of points, which is selected from image1 and the target
landmarks pt2 is a set of points, which is selected from image2. Now I want to
use ThinPlateSplineKernelTransform to register them. I do as below,</FONT></DIV>
<DIV><FONT face="Bookman Old Style"></FONT> </DIV>
<DIV><FONT
face="Bookman Old Style">transform->SetSourceLandmarks(pt1);</FONT></DIV>
<DIV><FONT
face="Bookman Old Style">transform->SetTargetLandmarks(pt2);</FONT></DIV>
<DIV><FONT face="Bookman Old Style">transfomr->Update();</FONT></DIV>
<DIV><FONT face="Bookman Old Style"></FONT> </DIV>
<DIV><FONT face="Bookman Old Style"> resampler->SetTransform( transform
);<BR> resampler->SetInterpolator(interpolator);<BR> resampler->SetInput(image2);<BR> size
=
image1->GetLargestPossibleRegion().GetSize();<BR> resampler->SetSize(size);<BR> resampler->SetOutputOrigin(
image1->GetOrigin() );<BR> resampler->SetOutputSpacing(
image1->GetSpacing() );<BR><BR> resampler->SetDefaultPixelValue( 0
);<BR> resampler->Update(); </FONT></DIV>
<DIV><FONT face="Bookman Old Style"></FONT> </DIV>
<DIV><FONT face="Bookman Old Style">Is it correct?</FONT></DIV>
<DIV><FONT face="Bookman Old Style"></FONT> </DIV>
<DIV><FONT face="Bookman Old Style">Best,</FONT></DIV>
<DIV><FONT face="Bookman Old Style"></FONT> </DIV>
<DIV><FONT face="Bookman Old Style">Yixun Liu</FONT></DIV>
<DIV><FONT face="Bookman Old Style"></FONT> </DIV>
<DIV><FONT face="Bookman Old Style"></FONT> </DIV></BODY></HTML>