Image registration is an important problem in image processing, especially in medical imaging. It is a hard optimization problem with objective function that is not appropriate for deterministic mathematical optimization. In this paper we propose a bi-resolution algorithm for rigid image registration based on recent fireworks algorithm. We tested our approach on retinal images from standard benchmark datasets and compared the results with other approaches from literature. Our proposed algorithm succeeded in registering images in all cases, and was more accurate than other compared methods.
No takes yet. Share an insight, caveat, or question.
Tuba et al. (2017) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: