Bootstrap Resampling for Image Registration Uncertainty Estimation Without Ground Truth.

We address the problem of estimating the uncertainty of pixel based image registration algorithms, given just the two images to be registered, for cases when no ground truth data available. Our novel method uses bootstrap resampling. It is very general, applicable to almost any registration method based minimizing a pixel-based similarity criterion; we demonstrate using the SSD, SAD, correlation, and mutual information criteria. We show experimentally that the bootstrap method provides better estimates of the registration accuracy than the state-of-the-art Cramér-Rao bound method. Additionally, we evaluate also fast registration accuracy estimation (FRAE) method which based on quadratic sensitivity analysis ideas and has a negligible computational overhead. FRAE mostly works better than Cramér-Rao bound method but is outperformed by the bootstrap method. [ABSTRACT FROM AUTHOR]