Spectral Demons – Image Registration via Global Spectral Correspondence

  • Herve Lombaert
  • Leo Grady
  • Xavier Pennec
  • Nicholas Ayache
  • Farida Cheriet
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7573)


Image registration is a building block for many applications in computer vision and medical imaging. However the current methods are limited when large and highly non-local deformations are present. In this paper, we introduce a new direct feature matching technique for non-parametric image registration where efficient nearest-neighbor searches find global correspondences between intensity, spatial and geometric information. We exploit graph spectral representations that are invariant to isometry under complex deformations. Our direct feature matching technique is used within the established Demons framework for diffeomorphic image registration. Our method, called Spectral Demons, can capture very large, complex and highly non-local deformations between images. We evaluate the improvements of our method on 2D and 3D images and demonstrate substantial improvement over the conventional Demons algorithm for large deformations.


Large Deformation Image Registration Shape Retrieval Global Scope Transformation Error 
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.
    Crum, W.R., Hartkens, T., Hill, D.L.: Non-rigid image registration: theory and practice. Br. J. of Radiology 77, 140–153 (2004)CrossRefGoogle Scholar
  2. 2.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L., Leach, M.O., Hawkes, D.J.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE TMI 18, 712–721 (1999)Google Scholar
  3. 3.
    Chui, H., Rangarajan, A.: A new algorithm for non-rigid point matching. In: CVPR, pp. 44–51 (2000)Google Scholar
  4. 4.
    Miller, M.I., Trouvé, A., Younes, L.: On the metrics and Euler-Lagrange equations of computational anatomy. An. Review of Biomed. Eng. 4, 375–405 (2002)CrossRefGoogle Scholar
  5. 5.
    Beg, M.F., Miller, M.I., Trouvé, A., Younes, L.: Computing large deformation metric mappings via geodesic flows of diffeomorphisms. IJCV 61, 139–157 (2005)CrossRefGoogle Scholar
  6. 6.
    Bossa, M., Hernandez, M., Olmos, S.: Contributions to 3D Diffeomorphic Atlas Estimation: Application to Brain Images. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 667–674. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  7. 7.
    Allassonnière, S., Amit, Y., Trouvé, A.: Towards a coherent statistical framework for dense deformable template estimation. Royal Stat. Soc. 69, 3–29 (2007)Google Scholar
  8. 8.
    Durrleman, S., Fillard, P., Pennec, X., Trouvé, A., Ayache, N.: Registration, atlas estimation and variability analysis of white matter fiber bundles modeled as currents. NeuroImage 55, 1073–1090 (2011)CrossRefGoogle Scholar
  9. 9.
    Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Diffeomorphic demons: efficient non-parametric image registration. NeuroImage 45, 61–72 (2009)CrossRefGoogle Scholar
  10. 10.
    Chung, F.R.K.: Spectral Graph Theory. AMS (1997)Google Scholar
  11. 11.
    Grady, L.J., Polimeni, J.R.: Discrete Calculus: Applied Analysis on Graphs for Computational Science. Springer (2010)Google Scholar
  12. 12.
    Umeyama, S.: An eigendecomposition approach to weighted graph matching problems. IEEE TPAMI 10, 695–703 (1988)zbMATHCrossRefGoogle Scholar
  13. 13.
    Scott, G.L., Longuet-Higgins, H.C.: An algorithm for associating the features of two images. Royal Soc. Bio. Sciences 244, 21–26 (1991)CrossRefGoogle Scholar
  14. 14.
    Shapiro, L.S., Brady, J.M.: Feature-based correspondence: an eigenvector approach. Image and Vision Computing 10, 283–288 (1992)CrossRefGoogle Scholar
  15. 15.
    Jain, V., Zhang, H.: Robust 3D shape correspondence in the spectral domain. In: Int. Conf. on Shape Modeling and App. (2006)Google Scholar
  16. 16.
    Mateus, D., Horaud, R., Knossow, D., Cuzzolin, F., Boyer, E.: Articulated shape matching using Laplacian eigenfunctions and unsupervised point registration. In: CVPR, pp. 1–8 (2008)Google Scholar
  17. 17.
    Reuter, M.: Hierarchical shape segmentation and registration via topological features of Laplace-Beltrami eigenfunctions. IJCV 89, 287–308 (2009)CrossRefGoogle Scholar
  18. 18.
    Lombaert, H., Grady, L., Polimeni, J.R., Cheriet, F.: Spectral correspondence for brain matching. In: IPMI, pp. 660–670 (2011)Google Scholar
  19. 19.
    Egozi, A., Keller, Y., Guterman, H.: Improving shape retrieval by spectral matching and meta similarity. IEEE Trans. Image Processing 19, 1319–1327 (2010)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Zhang, H., Van Kaick, O., Dyer, R.: Spectral mesh processing. Eurographics 29 (2010)Google Scholar
  21. 21.
    van Kaick, O., Zhang, H., Hamarneh, G., Cohen-Or, D.: A survey on shape correspondence. Eurographics 30, 1681–1707 (2011)Google Scholar
  22. 22.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE TPAMI 22, 888–905 (2000)CrossRefGoogle Scholar
  23. 23.
    Meila, M., Shi, J.: Learning segmentation by random walks. In: NIPS (2000)Google Scholar
  24. 24.
    Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Non-parametric Diffeomorphic Image Registration with the Demons Algorithm. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part II. LNCS, vol. 4792, pp. 319–326. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  25. 25.
    Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Symmetric Log-Domain Diffeomorphic Registration: A Demons-Based Approach. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008, Part I. LNCS, vol. 5241, pp. 754–761. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  26. 26.
    Tlusty, T.: A relation between the multiplicity of the second eigenvalue of a graph Laplacian, Courant’s nodal line theorem and the substantial dimension of tight polyhedral surfaces. Electronic Journal of Linear Algebra 16, 315–324 (2010)MathSciNetGoogle Scholar
  27. 27.
    Cachier, P., Bardinet, E., Dormont, D., Pennec, X., Ayache, N.: Iconic feature based nonrigid registration: the PASHA algorithm. CVIU 89, 272–298 (2003)zbMATHGoogle Scholar
  28. 28.
    Fischl, B., Sereno, M., Tootell, R., Dale, A.: High-resolution intersubject averaging and a coordinate system for the cortical surface. H. Brain Map. 8, 272–284 (1999)CrossRefGoogle Scholar
  29. 29.
    Yeo, B.T., Sabuncu, M.R., Vercauteren, T., Ayache, N., Fischl, B., Golland, P.: Spherical demons: Fast diffeomorphic Landmark-Free surface registration. IEEE TMI 29 (2010)Google Scholar
  30. 30.
    Luxburg, U.: A tutorial on spectral clustering. Stat. and Comp. 17, 395–416 (2007)CrossRefGoogle Scholar
  31. 31.
    Robles-Kelly, A.: Segmentation via Graph-Spectral Methods and Riemannian Geometry. In: Gagalowicz, A., Philips, W. (eds.) CAIP 2005. LNCS, vol. 3691, pp. 661–668. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  32. 32.
    Drineas, P., Mahoney, M.W.: On the Nyström method for approximating a Gram matrix for improved Kernel-Based learning. J. Mach. Learn. Res. 6, 2153–2175 (2005)zbMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Herve Lombaert
    • 1
    • 2
  • Leo Grady
    • 3
  • Xavier Pennec
    • 2
  • Nicholas Ayache
    • 2
  • Farida Cheriet
    • 1
  1. 1.Ecole Polytechnique de MontrealCanada
  2. 2.INRIA Sophia AntipolisFrance
  3. 3.Siemens Corporate ResearchPrincetonUSA

Personalised recommendations