Abstract：Image registration based on mutual information is of high accuracy and robustness. Hence, it has received much attention these years. Unfortunately, the mutual information function is generally not a smooth function but one containing many local maxima, which has a large influence on optimization. This paper proposes a registration method based on wavelet representation. In this method the mutual information is used as the similarity measure and a hybrid algorithm combined by ant colony algorithm and Powell’s method as the search technique. This method is applied to the 3D registration of CT and MR. Experiments shows that this registration method could efficiently restrain local maxima of mutual information function and the subvoxel accuracy can be achieved.
2007, Vol. 29 
