<div class="gmail_quote">This is not surprising. What optimizer are you using ? Does it require the computation of derivatives ? <br><br>With a binary volume, you would have large homogeneous regions and consequently several bspline nodes would end up getting derivative values of 0 during optimization. <br>
<br>You could try to transform the intensities of the images prior to registration, possibly register their danielsson distance maps, or smooth the images prior to registratation etc, so as to get nonzero derivatives to help the optimizer guide the registration<br>
<br>HTH<br>--<br>karthik<br><br><br>On Wed, Jan 14, 2009 at 11:15 AM, Carola Schmidt <span dir="ltr"><<a href="mailto:carola.schmidt@igd.fraunhofer.de">carola.schmidt@igd.fraunhofer.de</a>></span> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Hi,<br>
<br>
I just tried to register two binary images with the BSplineRegistration but it does not seem to work. The registration method I use works on general volumes but when I change the input to a binary volume it does not transform the image.<br>
Which registration method could I use to register two binary images which I have created with the the itk::thresholdfilter?<br>
Thanks.<br>
<br>
Greetings,<br>
Carola<br>
_______________________________________________<br>
Insight-users mailing list<br>
<a href="mailto:Insight-users@itk.org" target="_blank">Insight-users@itk.org</a><br>
<a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
</blockquote></div><br><br clear="all"><br>-- <br>Karthik Krishnan<br>R&D Engineer,<br>Kitware Inc.<br>Ph: 518 371 3971 x119<br>Fax: 518 371 3971<br>