A Robust Solution to Multi-modal Image Registration by Combining Mutual Information with Multi-scale Derivatives

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5761)


In this paper we present a novel method for performing image registration of different modalities. Mutual Information (MI) is an established method for performing such registration. However, it is recognised that standard MI is not without some problems, in particular it does not utilise spatial information within the images. Various modifications have been proposed to resolve this, however these only offer slight improvement to the accuracy of registration. We present Feature Neighbourhood Mutual Information (FNMI) that combines both image structure and spatial neighbourhood information which is efficiently incorporated into Mutual Information by approximating the joint distribution with a covariance matrix (c.f. Russakoff’s Regional Mutual Information). Results show that our approach offers a very high level of accuracy that improves greatly on previous methods. In comparison to Regional MI, our method also improves runtime for more demanding registration problems where a higher neighbourhood radius is required. We demonstrate our method using retinal fundus photographs and scanning laser ophthalmoscopy images, two modalities that have received little attention in registration literature. Registration of these images would improve accuracy when performing demarcation of the optic nerve head for detecting such diseases as glaucoma.


Mutual Information Image Registration Optic Nerve Head Search Optimisation Robust Solution 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Viola, P.A., Wells, W.M.: Alignment by maximization of mutual information. In: ICCV, pp. 16–23 (1995)Google Scholar
  2. 2.
    Collignon, A., Maes, F., Delaere, D., Vandermeulen, D., Suetens, P., Marchal, G.: Automated multimodality image registration based on information theory. In: Proc. Int. Conf. Information Processing in Medical Imaging, pp. 263–274 (1995)Google Scholar
  3. 3.
    Mellor, M., Brady, M.: Phase mutual information as a similarity measure for registration. Medical Image Analysis 9(4), 330–343 (2005)CrossRefGoogle Scholar
  4. 4.
    Pluim, J.P.W., Maintz, J.B.A., Viergever, M.A.: Image registration by maximization of combined mutual information and gradient information. IEEE Trans. Med. Imaging 19(8), 809–814 (2000)CrossRefGoogle Scholar
  5. 5.
    Dowson, N.D.H., Bowden, R., Kadir, T.: Image template matching using mutual information and NP-windows. In: ICPR, vol. (2), pp. 1186–1191 (2006)Google Scholar
  6. 6.
    Rueckert, D., Clarkson, M., Hill, D., Hawkes, D.: Non-rigid registration using higher-order mutual information. In: Medical Imaging: Image Processing, pp. 438–447 (2000)Google Scholar
  7. 7.
    Beijing, C., JunLi, L., Gang, C.: Study of medical image registration based on second-order mutual information. In: IEEE International Conference on Multimedia & Expo, pp. 956–959 (2007)Google Scholar
  8. 8.
    Kubecka, L., Jan, J.: Registration of bimodal retinal images - improving modifications. In: IEEE Int. Conf. on Engineering in Medicine and Biology, pp. 1695–1698 (2004)Google Scholar
  9. 9.
    Russakoff, D.B., Tomasi, C., Rohlfing, T., Maurer, C.R.: Image similarity using mutual information of regions. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 596–607. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    Yang, C., Jiang, T.-Z., Wang, J., Zheng, L.: A neighborhood incorporated method in image registration. In: Yang, G.-Z., Jiang, T.-Z., Shen, D., Gu, L., Yang, J. (eds.) MIAR 2006. LNCS, vol. 4091, pp. 244–251. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    ter Haar Romeny, B.M., Florack, L.M.J., Koenderink, J.J., Viergever, M.A.: Scale space: Its natural operators and differential invariants. In: Colchester, A.C.F., Hawkes, D.J. (eds.) IPMI 1991. LNCS, vol. 511, pp. 239–255. Springer, Heidelberg (1991)CrossRefGoogle Scholar
  12. 12.
    Shannon, C.: A mathematical theory of communication. Bell System Technical Journal 27, 379–423, 623–656 (1948)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Lagarias, J.C., Reeds, J.A., Wright, M.H., Wright, P.: Convergence properties of the Nelder-Mead simplex method in low dimensions. SIAM Journal of Optimization 9(1), 112–147 (1998)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  1. 1.School of Computer ScienceCardiff UniversityUK
  2. 2.School of Optometry and Vision SciencesCardiff UniversityUK

Personalised recommendations