Fusion for CT image and MR image based on nonsubsampled transformation

The paper propose a new algorithm based on NSCT in fusion for CT image and MR image. The low-frequents subbands and high-frequents subbands are get after NSCT. Gray value weighting is adopted in low-frequency image, and maximum module rule are adopted in high-frequents subbands. Experimental results compare with other method, and a set of quantitative evaluation criteria is given. Experimental results show that anatomical information can be obtained effectively , and both the edge and texture features can be reserved successfully.