Hi,<div><br></div><div>Thanks for the answers. Then is there any reason to use <span class="Apple-style-span" style="font-family: arial, sans-serif; font-size: 13px; border-collapse: collapse; ">SymmetricForcesDemonsRegistrationFilter if </span><span class="Apple-style-span" style="font-family: arial, sans-serif; font-size: 13px; border-collapse: collapse; ">FastSymmetricForcesDemonsRegistrationFilter is at hand? Could be any difference between the registration results of them?</span><br>
<br><div class="gmail_quote">On Thu, Feb 18, 2010 at 8:37 AM, Tom Vercauteren <span dir="ltr"><<a href="mailto:tom.vercauteren@gmail.com">tom.vercauteren@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Hi Zoltan,<br>
<br>
FastSymmetricForcesDemonsRegistrationFilter and<br>
SymmetricForcesDemonsRegistrationFilter use the same algorithm from<br>
Thirion. The only difference lies in the implementation. As<br>
illustrated by the name of the class,<br>
FastSymmetricForcesDemonsRegistrationFilter should just be faster...<br>
<font color="#888888"><br>
Tom<br>
</font><div><div></div><div class="h5"><br>
On Thu, Feb 18, 2010 at 00:59, Luis Ibanez <<a href="mailto:luis.ibanez@kitware.com">luis.ibanez@kitware.com</a>> wrote:<br>
> Hi Zoltan,<br>
><br>
><br>
> It seems that you missed the text from the header file:<br>
><br>
> itkSymmetricForcesDemonsRegistrationFilter.h<br>
><br>
><br>
> <quote><br>
> * This class was contributed by Corinne Mattmann, ETH Zurich, Switzerland.<br>
> * based on a variation of the DemonsRegistrationFilter. The basic modification<br>
> * is to use equation (5) from Thirion's paper along with the modification for<br>
> * avoiding large deformations when gradients have small values.<br>
> *<br>
> * SymmetricForcesDemonsRegistrationFilter implements the demons<br>
> deformable algorithm that<br>
> * register two images by computing the deformation field which will map a<br>
> * moving image onto a fixed image.<br>
> </quote><br>
><br>
><br>
> Is this the information that you are looking for ?<br>
><br>
><br>
> The difference in computation time is due to the fact that this<br>
> class computes gradients of both the Fixed image and the<br>
> Moving image.<br>
><br>
><br>
><br>
> Regards,<br>
><br>
><br>
> Luis<br>
><br>
><br>
><br>
> --------------------------------------------------------------------------------------<br>
> On Wed, Feb 17, 2010 at 2:15 PM, Zoltan Seress <<a href="mailto:seress.zoltan@gmail.com">seress.zoltan@gmail.com</a>> wrote:<br>
>><br>
>> Hi all,<br>
>> I have browsed the classes of itk 3.16 to get some information about the<br>
>> variants of the demons registration. I have found these:<br>
>> 1, itkDemonsRegistrationFilter: this is the one algorithm by Thirion: "Image<br>
>> matching as a Diffusion Process: and Analogy with Maxwell's Demons"<br>
>> 2, itkPointSetToSpatialObjectDemonsRegistration: this is another algorithm<br>
>> by Thirion<br>
>> 3, itkDiffeomorphicDemonsRegistrationFilter: it is presented by Vercauteren<br>
>> (<a href="http://hdl.handle.net/1926/510" target="_blank">http://hdl.handle.net/1926/510</a>) Algorithm 3 should be this one.<br>
>> 4, itkFastSymmetricForcesDemonsRegistrationFilter: it is also presented by<br>
>> Vercauteren (<a href="http://hdl.handle.net/1926/510" target="_blank">http://hdl.handle.net/1926/510</a>) Algorithm 2 should be this one.<br>
>> 5, itkSymmetricForcesDemonsRegistrationFilter: There is no additional info<br>
>> in the description. Has not been this implementation published somewhere?<br>
>> All I know that it uses both the moving image gradient and the fixed image<br>
>> gradient, and it is approximately 3 times slower<br>
>> than itkDemonsRegistrationFilter. Can you tell me more about this filter?<br>
>> PS: I know about other variants such as log-domain diffeomorphic demons and<br>
>> symmetric log-domain diffeomorphic demons, but these are too much for once.<br>
>> --<br>
>> Zoli<br>
>><br>
>> _____________________________________<br>
>> Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
>><br>
>> Visit other Kitware open-source projects at<br>
>> <a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
>><br>
>> Kitware offers ITK Training Courses, for more information visit:<br>
>> <a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
>><br>
>> Please keep messages on-topic and check the ITK FAQ at:<br>
>> <a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
>><br>
>> Follow this link to subscribe/unsubscribe:<br>
>> <a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
>><br>
>><br>
> _____________________________________<br>
> Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
><br>
> Visit other Kitware open-source projects at<br>
> <a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
><br>
> Kitware offers ITK Training Courses, for more information visit:<br>
> <a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
><br>
> Please keep messages on-topic and check the ITK FAQ at:<br>
> <a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
><br>
> Follow this link to subscribe/unsubscribe:<br>
> <a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
><br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br>Zoli<br>
</div>