A Neighborhood Incorporated Method in Image Registration
Mutual information has been widely used in image registration as an effective similarity measure. It has attracted a lot of attention to the effective use of the spatial information. Here we propose a new measure that includes the mean of the neighborhood region of each pixel as one variable of the two-dimension normal distribution assumed in our method. The experimental results show that our method can not only improve the robustness of mutual information, but also reduce the affect of noise in image registration.
KeywordsMutual Information Spatial Information Image Registration Pixel Pair Marginal Probability Distribution
Unable to display preview. Download preview PDF.
- 1.Hill, D.L.G., Batchelor, P.G., Holden, M., Hawkes, D.J.: Medical image registration. Phys. Med. Biol., R1–R45 (2001)Google Scholar
- 3.Collignon, A., Maes, F., Delaere, D., Vandermeulen, D., Suetens, P., Marchal, G.: Automated multi-modality image registration based on information theory. In: Proc. of Information Processing in Medical Imaging, pp. 263–274. Kluwer, Norwell (1995)Google Scholar
- 4.Viola, P., Wells, W.M.: Alignment by maximization of mutual information. In: Proc. of 5th Int. Conf. Computer Vision, Boston, MA, pp. 16–23 (1995)Google Scholar
- 8.Rueckert, D., Clarkson, M.J., Hill, D.L.G., Hawkes, D.J.: Non-rigid registration using higher-order mutual information. In: Proc. SPIE Medical Imaging 2000: Image Processing, San Diego, CA, pp. 438–447 (2000)Google Scholar
- 11.Tomazevie, D., Likar, B., Pernus, F.: Multi-Feature Mutual Information. In: Proc. of SPIE, vol. 5370, pp. 143–154 (2004)Google Scholar