Bijective image registration using thin-plate splines

Abstract

Image registration is the process of geometrically aligning two or more images. In this paper we describe a method for registering pairs of images based on thin-plate spline mappings. The proposed algorithm minimizes the difference in gray-level intensity over bijective deformations. By using quadratic sufficient constraints for bijectivity and a least squares formulation this optimization problem can be addressed using quadratic programming and a modified Gauss-Newton method. This approach also results in a very computationally efficient algorithm. Example results from the algorithm on three different types of images are also presented.