An automatic image registration scheme based on the nonsubsampled contourlet transform

In this paper, a new feature points extraction method based on the nonsubsampled contourlet transform (NSCT) is proposed for image registration. The primary motivation of this work is to determine the effectiveness of the NSCT transform for feature points extraction for the use of image registration. The performance of the proposed NSCT-based registration algorithm is demonstrated and validated in a series of carefully designed synthetic experiments. The preliminary experimental results show the robustness and efficiency of the algorithm in the presence of noise and common image processing operations as well as rigid geometric transformations, and confirm the success of the proposed NSCT-based feature points extraction approach.