The Gui is very helpful and works really well as a tool for evaluating intensity based image registration. However the core function is a convergence algorithm and possibly because of this, never seems to produce pixel perfect or near perfect registration. It's main advantage is obviously to automate the process without requiring control point user intervention.
Conversely from my experience, imtransform seems to produce better registration results and I can get pixel perfect registration in most cases for my application, but this requires user intervention for control point generation.
What would be really good, from my viewpoint is an algorithm which takes the initial control points from the base image and then automatically searches for equivalent matches in the unregistered image. Any help you can provide in this direction would be a definite five star!
Thanks for the rating. I guess I would still call this an intensity-based segmentation, unless you are extracting properties of the regions (centers, radii) and using some algorithm to match. In this case your intensities are binary-valued, but they're still intensities.
I have 2 images which they contain a circle.
First, I segmented the circle in both images, then apply your registration app to register them.
My question is, what will be the name of my registration?
Since, my images are "black & white", I think I cannot name it "intensity-based", right?
Thank you very much Brett to provide me a comprehensive information. Appreciate your help and looking forward to see more great jobs from you. If I face any issue, i will back to ask you.