<div><br></div>Hi Yoann,<div><br></div><div>1) Are you using the CenteredTransformInitializer ?</div><div><br></div><div>2) What are the sizes (in pixels along each dimension) of </div><div> your Fixed and Moving images ?</div>
<div><br></div><div>3) What are the pixel spacings of your two images ?</div><div><br></div><div>4) What are the origins of your two images ?<br></div><div><br></div><div>5) What exact values are you using in the optimizer scales array ?</div>
<div><br></div><div><br></div><div>Please let us know,</div><div><br></div><div><br></div><div> Thanks</div><div><br></div><div><br></div><div> Luis<br><br></div><div><br></div><div>--------------------------<br>
<div class="gmail_quote">On Mon, Aug 17, 2009 at 10:26 AM, Yoann Moreau <span dir="ltr"><<a href="mailto:yoann.moreau@gmail.com">yoann.moreau@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Hey everyones !
<br> <p>I have a problem with ImageRegistration : <br></p><p> I'm trying to register images (a Fixed image and a Moving one (same image but which I applied to a scaling,
translation and rotation transform). <br></p><p>I 've obtain excellent results when I
applied only a rotation and a scalling transformation.I based my code on ImageRegistration9.cxx and use a an AffinTransform based on MatesMultualInformation for the
metric, RegularStepGradientDescentOptimizer for the optimizer. <br> </p><p>Therefore as soon as I applied a translation Translation in X, Y, translation factors are
still very low ( near to 0) and results for other factors determination tion are worse. <br></p><p></p><p> </p>I supposed the problem come from Optimizer Scales and more precisely from adjustment of TranslationFactors towards rotation and scaling factor.<br>
I try recommandation "to use a factor proportional to the diagonal length of the image", Therefore I'm working on Satellite images with a resolution of 10 m by pixel.<br>Resultts using that estimation are worse. Have you got an idea of how I can solve my problem with translation factors determination ?<br>
<br><br><br>reference :<br> <a href="http://public.kitware.com/pipermail/insight-users/2004-July/009558.html" target="_blank">http://public.kitware.com/pipermail/insight-users/2004-July/009558.html</a><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>
Please keep messages on-topic and check the ITK FAQ at: <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></blockquote></div><br></div>