A level-set based approach to image registration

Abstract

Image registration is an often encountered problem in various fields including medical imaging, computer vision and image processing. Here, the authors present a novel curve evolution approach expressed in a level-set framework to achieve image registration. The key features of the authors' algorithm are, (a) it can account for small and large deformations, (b) it is very fast (unlike most large deformation schemes) and (c) existence and uniqueness of the solution for the evolution model has been established in a Sobolev space. The authors demonstrate the implementation results on a variety of images including synthetic and real data.

Ähnliche Arbeiten