<div dir="ltr">Hello Richard,<div><br></div><div>I am using "HelloWorld" registration example with RegularStepGradienDescent optimizer and MeanSquareImageToImage metric. At the end of registration algorithm I want to compute metric value again using transform calculated by the algorithm but I get different value as compared to the metric value evaluated in last iteration.</div><div><br></div><div>Best Regards,<br></div><div>Suneeza</div><div><br></div><div> </div></div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Jan 2, 2016 at 6:48 PM, Richard Frank <span dir="ltr"><<a href="mailto:rfrank@dominionsw.com" target="_blank">rfrank@dominionsw.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">What optimizer/ algorithm are you using? Some use random selections of data as a speed optimization which on average give good results for better performance. But possibly slightly different results. If the differences are great then you might have to look at how you pick the first "guess"...how the images are pre-positioned prior to registration.<br>
<br>
Rick Frank<br>
<br>
Sent from my iPad<br>
<br>
> On Jan 2, 2016, at 12:00 PM, "<a href="mailto:insight-users-request@itk.org">insight-users-request@itk.org</a>" <<a href="mailto:insight-users-request@itk.org">insight-users-request@itk.org</a>> wrote:<br>
><br>
> Send Insight-users mailing list submissions to<br>
> <a href="mailto:insight-users@itk.org">insight-users@itk.org</a><br>
><br>
> To subscribe or unsubscribe via the World Wide Web, visit<br>
> <a href="http://public.kitware.com/mailman/listinfo/insight-users" rel="noreferrer" target="_blank">http://public.kitware.com/mailman/listinfo/insight-users</a><br>
> or, via email, send a message with subject or body 'help' to<br>
> <a href="mailto:insight-users-request@itk.org">insight-users-request@itk.org</a><br>
><br>
> You can reach the person managing the list at<br>
> <a href="mailto:insight-users-owner@itk.org">insight-users-owner@itk.org</a><br>
><br>
> When replying, please edit your Subject line so it is more specific<br>
> than "Re: Contents of Insight-users digest..."<br>
><br>
><br>
> Today's Topics:<br>
><br>
> 1. Metric Evaluation (suneeza hanif)<br>
><br>
><br>
> ----------------------------------------------------------------------<br>
><br>
> Message: 1<br>
> Date: Fri, 1 Jan 2016 23:17:36 +0100<br>
> From: suneeza hanif <<a href="mailto:suneezahanif02@gmail.com">suneezahanif02@gmail.com</a>><br>
> To: <a href="mailto:insight-users@itk.org">insight-users@itk.org</a><br>
> Subject: [ITK-users] Metric Evaluation<br>
> Message-ID:<br>
> <CA+-JtYVXHj_n4=0NDkv6Urmgqqh=<a href="mailto:8OUXiqDkw3DwNQq_Nni6Sw@mail.gmail.com">8OUXiqDkw3DwNQq_Nni6Sw@mail.gmail.com</a>><br>
> Content-Type: text/plain; charset="utf-8"<br>
><br>
> Hello Everyone,<br>
><br>
> I need help regarding metric calculation. When I run registration algorithm<br>
> and use final results(e.g. rotation angle and translation) to calculate<br>
> metric once again at the end of process I get different value as compared<br>
> to the value of metric evaluated in last iteration. I am using same metric<br>
> for registration and later.<br>
><br>
> I also did this after one iteration but i still i get different values.<br>
><br>
> Does anyone know how to solve this problem?<br>
><br>
> Thanks in advance.<br>
><br>
> Best Regards,<br>
> Suneeza<br>
> -------------- next part --------------<br>
><br>
</blockquote></div><br></div>