Generalized regularization term for non-parametric multimodal image registration

In the field of non-rigid medical image registration, many regularizers based on first- or second-order derivatives have been studied. In this paper, a new regularization term based on fractional order derivatives is proposed for the registration of multimodal (e.g., medical) images. It can be seen as a generalization of the diffusion and curvature smoothing terms, but with this approach it is possible to obtain better registration results in terms of both similarity of the images and smoothness of the transformation. This registration scheme is tested on two realistic medical imaging scenarios, comparing the obtained results with the optimally registered diffusion and curvature cases.