Image registration is to find a transformation to map the corresponding image data. But in large deformation registration problems, it is very difficult to obtain a solution that has no folding. Lam and Lui (2014) has used Beltrami coefficient to control the transformation and avoid the twist. In this talk, I will propose novel diffeomorphic models based quasi-conformal theory for image registration. Numerical experiments demonstrate that the proposed models can get accurate and diffeomorphic transformations.
This presentation is part of Minisymposium “MS22 - Mapping problems in imaging, graphics and vision (3 parts)”
organized by: Ronald Lui (Chinese University of Hong Kong) , Ke Chen (University of Liverpool) .