Overlap invariant image registration #1022
Unanswered
tjalfelaedtke
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Greetings,
I have been trying to register 3D-images which have been acquired using optical coherence tomography (OCT). I have been successful with the default parameters when the images to be registered had a lot of overlap. Unfortunately, in cases, where a good registration would produce <70% overlap of the images, things do not work anymore.
The optimization always converges to a solution which provides maximum overlap and tries to map the maximum number of points, which I do not want when performing an EulerTransform.
I already tried using the NormalizedMutualInformation metric instead of AdvancedMattesMutualInformation as it claims to be less sensitive for situations like that but this failed in the same way.
Are there any suggestions on how to fix this problem?
Thank you!
Tjalfe
Beta Was this translation helpful? Give feedback.
All reactions