[ITK-users] [ITK] CorrelationImageToImageMetricv4 returns with very low correlation values

Lowekamp, Bradley (NIH/NLM/LHC) [C] blowekamp at mail.nih.gov
Wed Aug 17 15:08:52 EDT 2016


Hello,

You seem to need a way to interactively explore your program, images and registration setup.

All ITK registration metrics are designed to be minimized. So the correlations are negative if I recall correctly.

You may want to look into Slicer3D (https://www.slicer.org) for a image visualizer which is aware of ITK’s image geometry.

You also may want to look into using an interactive programing environment such as Python to better understand the image geometry and the properties of what you are trying to setup.

You may find the SimpleITK Notebooks on Image Registration useful:

http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/

HTH,
Brad

On Aug 17, 2016, at 2:52 PM, Andrew Harris <aharr8 at uwo.ca<mailto:aharr8 at uwo.ca>> wrote:

Hello,
I am attempting to register two 3D images using the CorrelationImageToImageMetricv4, the LBFGSBOptimizer, and a 3DVersorRigidRegistration. Even if I put the same volumes in to the registration for both the fixed and moving image, I get a very low value for correlation.  One thought I had was I might be setting the origins incorrectly, as previously in the project the origin was defined as the centre of the image cubes and I have attempted to stay with that convention, and I haven’t found an example in the ITK examples where the origin is set to something other than 0.  The other issue might be that the original data is a char array so I had to create a cast filter to change the image to floats, and the origins might be getting confused between the two. If anyone has any thoughts they would be welcome, I can provide source code if that would be helpful.

--

AH


-----------------------------------------------------------------------------------------------

This email and any attachments thereto may contain private, confidential, and privileged materials for the sole use of the intended recipient. Any reviewing, copying, or distribution of this email (or any attachments thereto) by other than the intended recipient is strictly prohibited. If you are not the intended recipient, please contact the sender immediately and permanently destroy this email and any attachments thereto.

_____________________________________
Powered by www.kitware.com<http://www.kitware.com>

Visit other Kitware open-source projects at
http://www.kitware.com/opensource/opensource.html

Kitware offers ITK Training Courses, for more information visit:
http://www.kitware.com/products/protraining.php

Please keep messages on-topic and check the ITK FAQ at:
http://www.itk.org/Wiki/ITK_FAQ

Follow this link to subscribe/unsubscribe:
http://public.kitware.com/mailman/listinfo/insight-users

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20160817/532b3f26/attachment.html>


More information about the Insight-users mailing list