SIFT特征提取方法在医学图像配准中的应用

Now many kinds of image registration methods have been developed. Image registration method based on feature points becomes a hot research in computer vision. In allusion to non-rigid registration of medical images, the paper gives a practical matching algorithm——the image registration algorithm based on the scale-invariant features transform (Scale Invariant Feature Transform, SIFT). The paper highlights the SIFT feature extraction and matching method. On the basis of the application of SIFT feature extraction to extract images feature points, the paper chooses affine transformation model, normalized mutual information measure to accomplish the image non-rigid registration process. The experimental results show that the method can achieve better registration results than the method based on mutual information.