Speeding up image registration

edit

Hi guys.

I am using findTransformECC to perform image registration and it has been working great so far. However, I need to speed up the process by a factor of 5x. I was thinking of using Cuda and delegate the registration to the GPU. What do you guys think? I have no experience with Cuda though. Would I have to rewrite the function findTransformECC from scratch? Many thanks.