[Insight-users] affine transform

annelaure al_didier at yahoo.fr
Thu Apr 19 04:23:53 EDT 2007


Hi,
I apply the equation 8.11 p440 in the ITK Software Guide in order to obtain
the final coordinates of my points. I considered that the firt matrix of
this equation is constituted by the 9 first result parameters and that
Cx=0,Cy=0 and Cz=0.
I try to register a theorical rib (95 points)
www710.univ-lyon1.fr/~adidier/cote8_thpts.txt on a segmentation rib (4280
points)   www710.univ-lyon1.fr/~adidier/cote8_segpts.txt in using the code
previously described. I don't obtain good results. I try to proceed to a
classical icp registration (iterativeclosestpoint2.cxx) first but the
results are not better. 
Should I change some optimizer parameters? Should I proceed to a rigid
registration before in order to bring closer the two ribs?
Thank you so much for your answer,
Best regards,
Anne-Laure




Luis Ibanez wrote:
> 
> 
> 
> Hi Annelaure,
> 
> 
>                No need ot make assumptions
> 
> 
> Please read the documentation of the AffineTransform class:
> 
> http://www.itk.org/Insight/Doxygen/html/classitk_1_1AffineTransform.html
> 
> In particular the GetParameters and SetParameters() methods.
> 
> 
> You should also read the description of this Transform in the
> ITK Software Guide:
> 
>          http://www.itk.org/ItkSoftwareGuide.pdf
> 
> 
> In section 8.8.16 "Affine Transform" in pdf-pages 439-440.
> 
> Pay particular attention to Table 8.15 in pdf-page 439.
> 
> 
> 
> Please note that all the examples are described in detail
> in the ITK Software Guide.
> 
> 
> 
>    Regards,
> 
> 
> 
>        Luis
> 
> 
> -------------------
> annelaure wrote:
>> Hi,
>> I use Iterative closest point 1 with the affine transform. I obtain 12
>> numbers : Solution = [0.563524, -0.0204711, -0.0675956, 0.308023,
>> 0.539417,
>> -0.0100321, -0.0645276, -0.0436415, 0.554475, 83.8441, 81.0703, 139.525].
>> I
>> suppose that the 3 last numbers are the translation parameters; but I
>> don't
>> know where are the rotation parameters, and the scaling parameters. Thank
>> you so much for your help,
>> best regards,
>> Anne-Laure
>> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
> 
> 

-- 
View this message in context: http://www.nabble.com/affine-transform-tf3566227.html#a10073847
Sent from the ITK - Users mailing list archive at Nabble.com.



More information about the Insight-users mailing list