Just one more comment in addition to what has been discussed here. I
also used the pyramid filter earlier for registration of 3D images. but
there was a problem that the Z-dimension was only 7 pixels. so
even for second step, it was divided by 2, giving <4 pixels.
but since the image pyramid filter internally uses gaussian filter
(correct me if i am wrong) it needs more than 4 pixels for
approximation, and hence it didnt worked out for me. However in the
pyramid we can set different scales for different dimensions, by which
I was able to achieve the desired results.<br>
<br>
regards,<br>
Ashish.<br><br><div><span class="gmail_quote">On 11/27/05, <b class="gmail_sendername">Luis Ibanez</b> <<a href="mailto:luis.ibanez@kitware.com">luis.ibanez@kitware.com</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>Hi Grace,<br><br>You can use the pyramids for 3D registration.<br><br>There is nothing wrong about it.<br><br>The reason why the example in 3D is not using<br>the pyramid is that the example is intended to<br>be very simple.
<br><br><br>The fact that you attempted to use the pyramid<br>and didn't performed better, just doesn't mean<br>anything.<br><br>This anecdotic information is useless. Saying<br>that you try something once, and it didn't work
<br>is not a technical way of reporting a problem.<br><br><br><br>In order to be useful, Your report should mention<br>details such as:<br><br><br>1) Image modality<br><br>2) Image size<br><br>3) Components in your registration framework
<br> 3.1) Optimizer<br> 3.2) do you use a Transform initializer ?<br> 3.3) What Transform are you using<br><br>4) How many levels did you set in your pyramid<br><br>5) What parameters did you set up on ever level.
<br><br>6) When you say that it "performed worsely"<br><br> what do you mean ?<br><br> 6.1) it did not converged ?<br> 6.2) it did converged but took longer ?<br> 6.3) it converged but the images are still
<br> misaligned ?<br><br><br>Please be more specific when you report problems.<br><br><br><br>It is very dangerous to generalize ad-hoc rules<br>out of anecdotic information. Doing so is more<br>along the lines of developing superstitions rather
<br>than working in scientific research.<br><br>Such practices are fine for publishing papers on<br>Decadent Journals where author only need to be able<br>to say that "my method is better than any other one".<br>
This is not acceptable when you really want to solve<br>problems in image processing.<br><br><br>Please report your experience, with enough amount of<br>detail for allowing somebody else to reproduce what<br>you attempted. Only in this way we can provide you
<br>with useful advice.<br><br><br><br><br>Regards,<br><br><br><br> Luis<br><br><br><br>---------------<br>Grace Chen wrote:<br>> Hi all, good day!<br>><br>> I use the transform and the optimizer (VersorRigid3DTransform,
<br>> VersorRigid3DTransformOptimizer, and CenteredTransformInitializer) to<br>> perforom 3D rigid registration on my data, and I notice that in itk<br>> example, the image pyramid isn't used for the 3D registration. I tried
<br>> adding that to my registration program, but it produced worsely<br>> registered output. Does anyone one know why? Does that mean I<br>> shouldn't use image pyramid technique for registering 3D data?<br>>
<br>> Thanx!!<br>><br>> Grace<br>><br>><br>> ------------------------------------------------------------------------<br>><br>> _______________________________________________<br>> Insight-users mailing list
<br>> <a href="mailto:Insight-users@itk.org">Insight-users@itk.org</a><br>> <a href="http://www.itk.org/mailman/listinfo/insight-users">http://www.itk.org/mailman/listinfo/insight-users</a><br><br>_______________________________________________
<br>Insight-users mailing list<br><a href="mailto:Insight-users@itk.org">Insight-users@itk.org</a><br><a href="http://www.itk.org/mailman/listinfo/insight-users">http://www.itk.org/mailman/listinfo/insight-users</a><br></blockquote>
</div><br><br clear="all"><br>-- <br>Ashish Poddar<br><<a href="http://ahpoddar.bizhat.com">http://ahpoddar.bizhat.com</a>><br>Its high time we standardize everything!