<div>hi,Luis,</div>
<div>Thanks very much for your reply!</div>
<div>I have noticed the <a onclick="return top.js.OpenExtLink(window,event,this)" href="http://www.itk.org/Insight/Doxygen/html/classitk_1_1ThinPlateR2LogRSplineKernelTransform.html" target="_blank">ThinPlateR2LogRSplineKernelTransform</a> just this morning,and I have done the experiments with it as well as with ThinPlateSplineTransform using the same image.But the results are almost the same.I don't know why there are the same results with the different GMatrix. </div>
<div>In addition, I still have the question:</div>
<div>According to the ThinPlateSpline theory, the farther the pixel distant from the original Landmark,the smaller the deformation will be (This is because the sum of the wi*r will be smaller).So that the deformation at infinity will be zero.</div>
<div>But when I can use the ThinPlateSplineWarp.cxx to get the deformation field, the deformation field is bigger in the edge than in the centre. Can you help me?</div>
<div> </div>
<div>feng</div>
<div><br><br> </div>
<div><span class="gmail_quote">2008/4/21, Luis Ibanez <<a href="mailto:luis.ibanez@kitware.com">luis.ibanez@kitware.com</a>>:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid"><br>Hi Feng,<br><br>Thanks for your comments regarding this example.<br><br><br>Please note that ITK provides multiple implementations<br>
of KernelTransforms, all of them deriving from the class:<br><a href="http://www.itk.org/Insight/Doxygen/html/classitk_1_1KernelTransform.html">http://www.itk.org/Insight/Doxygen/html/classitk_1_1KernelTransform.html</a><br>
<br>It seems that you are interested in using the class:<br><a href="http://www.itk.org/Insight/Doxygen/html/classitk_1_1ThinPlateR2LogRSplineKernelTransform.html">http://www.itk.org/Insight/Doxygen/html/classitk_1_1ThinPlateR2LogRSplineKernelTransform.html</a><br>
<br>instead of the transform class:<br><a href="http://www.itk.org/Insight/Doxygen/html/classitk_1_1ThinPlateSplineKernelTransform.html">http://www.itk.org/Insight/Doxygen/html/classitk_1_1ThinPlateSplineKernelTransform.html</a><br>
<br>that is featured in that example.<br><br><br><br>You can therefore, simply change the #include of the header file,<br>and the class name in the typedef statement that instantiates the<br>type of the transform.<br><br>
<br>Please let us know if you have any further questions.<br><br><br> Thanks<br><br><br> Luis<br><br><br><br>---------------------<br>feng yang wrote:<br>> hi,Luis,<br>><br>> I am trying to get the deformation field from a Landmark file using the<br>
> ThinPlateSpline transform.But I discover a problem,: in the<br>> itkThinPlateSplineKernelTransform.txx, the G Matrix is gotten as<br>> :"GMatrix[i][i] = r". This is true for the 3D image,but for the 2D image<br>
> ,the G matrix should be:GMatrix[i][i]=r^2*log(r^2),which I got from the<br>> paper:"Thin-Plate Spline Approximation for image registration".However,<br>> G matrix is gotten as :"GMatrix[i][i] = r" for all the dimenson image.<br>
> So the itkThinPlateSplineKernelTransform is just useful for 3D image? Am<br>> I right £ï£ò¡¡£É¡¡£è£á£ö£å¡¡£í£á£ä£å¡¡£ó£ï£í£å¡¡£í£é£ó£õ£î£ä£å£ò£ó£ô£á£î£ä£¿<br>><br>> £Ô£è£á£î£ë¡¡£ù£ï£õ¡¡£ö£å£ò£ù¡¡£í£õ£ã£è£¡<br>><br>> £æ£å£î£ç<br></blockquote></div><br>