A new method for non-rigid registration of MRI images
Nima Torbati, Ahmad Ayatollahi · 2017
In this paper, the parametric registration methods based on function expansion theory are revised and by using the wavelet transform a general and simple framework for non-rigid image registration is introduced. Simplicity and generality are two main features of this method. The model parameters are updated by using forward and inverse wavelet transforms, in each iteration. In the results section, we evaluate the performance of the proposed method on two datasets of simulated and real magnetic resonance images (MRI) and show that the proposed method has a better performance compared to well-known registration methods in the literature.