High-accuracy image registration algorithm using B-splines

Image registration is an important enabling technology in dynamic image analysis. In this paper, we present a novel and efficient approach to dense image registration, which is based on a three-dimensional free-form B-splines deformation model. The registration process can be described as a two step process. The first step involves the identification of a set of salient features and the second involves the computation of the alignment of these features. Results using atmospheric turbulence image data are presented that demonstrate high-accuracy of matching while unnecessary distortions are avoided. Our results indicate that increasing the complexity of the deformation model improves registration accuracy significantly, especially at medical image analysis.