Geometric Image Registration under Locally Variant Illuminations Using Huber M-estimator

  • M. M. Fouad
  • R. M. Dansereau
  • A. D. Whitehead
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6134)

Abstract

In this paper, we extend our previous work on presenting a registration model for images having arbitrarily-shaped locally variant illuminations from shadows to multiple shading levels. These variations tend to degrade the performance of geometric registration and impact subsequent processing. Often, traditional registration models use a least-squares estimator that is sensitive to outliers. Instead, we propose using a robust Huber M-estimator to increase the geometric registration accuracy (GRA). We demonstrate the proposed model and compare it to other models on simulated and real data. This modification shows clear improvements in terms of GRA and illumination correction.

Keywords

Image Registration Variant Illumination Global Illumination Registration Model Illumination Correction 
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.

References

  1. 1.
    Zitová, B., Flusser, J.: Image registration methods: A Survey. Image & Vis. Comp. 21, 977–1000 (2003)CrossRefGoogle Scholar
  2. 2.
    Gevrekci, M., Gunturk, B.: Superresolution under photometric diversity of images. Advances in Signal Proc. (2007)Google Scholar
  3. 3.
    Szeliski, R.: Image alignment and stitching: A tutorial. Found. and Trends in Comp. Graphics and Vision 2 (2006)Google Scholar
  4. 4.
    Lou, L., Zhang, F., Xu, C., Li, F., Xue, M.: Automatic registration of aerial image series using geometric invariance. In: IEEE ICAL, pp. 1198–1203 (2005)Google Scholar
  5. 5.
    Aylward, S., Jomier, J., Weeks, S., Bullitt, E.: Registration of vascular images. Comp. Vis. 55, 123–138 (2003)CrossRefGoogle Scholar
  6. 6.
    Xu, D., Kasparis, T.: Robust image registration under spatially non-uniform brightness changes. In: IEEE ICASSP, vol. 2, pp. 945–948 (2005)Google Scholar
  7. 7.
    Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. Comp. Vis. and Patt. Recog. 2, 506–513 (2004)Google Scholar
  8. 8.
    Battiato, S., Gallo, G., Puglisi, G., Scellato, S.: SIFT features tracking for video stabilization. In: Proc. 14th ICIAP, pp. 825–830 (2007)Google Scholar
  9. 9.
    Fischler, M., Bolles, R.: Random Sample Consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Comm. Of the ACM 24, 381–395 (1981)Google Scholar
  10. 10.
    Hartley, R., Zisserman, A.: Multiple view geometry in computer vision, 2nd edn. Cambridge University Press, Cambridge (2003)Google Scholar
  11. 11.
    Periaswamy, S., Farid, H.: Elastic registration in the presence of intensity variations. IEEE Trans. Med. Imag. 22, 865–874 (2003)CrossRefGoogle Scholar
  12. 12.
    Aguiar, P.: Unsupervised simultaneous registration and exposure correction. In: IEEE ICIP, pp. 361–364 (2006)Google Scholar
  13. 13.
    Altunbasak, Y., Mersereau, R., Patti, A.: A fast parametric motion estimation algorithm with illumination and lens distortion correction. IEEE Trans. Image Proc. 12, 395–408 (2003)CrossRefGoogle Scholar
  14. 14.
    Bartoli, A.: Groupwise geometric and photometric direct image registration. IEEE Trans. Patt. Ana. & Mach. Intel. 30, 2098–2108 (2008)CrossRefGoogle Scholar
  15. 15.
    Fouad, M., Dansereau, R., Whitehead, A.: Geometric registration of images with arbitrarily-shaped local intensity variations from shadows. In: IEEE ICIP, pp. 201–204 (2009)Google Scholar
  16. 16.
    Huber, P.: Robust Statistics, 1st edn. Wiley, New York (1981)MATHGoogle Scholar
  17. 17.
    Kanungo, T., Mount, D., Netanyahu, N., Piatko, C., Silverman, R.: An efficient K-means clustering algorithm: Analysis and implementation. IEEE Trans. Patt. Ana. & Mach. Intel. 24, 881–892 (2002)CrossRefGoogle Scholar
  18. 18.
    Mangasarian, O., Musicant, D.: Robust linear and support vector regression. IEEE Trans. Patt. Ana. & Mach. Intel. 22, 950–955 (2000)CrossRefGoogle Scholar
  19. 19.
    Jiang, J., Zheng, S., Toga, A., Tu, Z.: Learning based coarse-to-fine image registration. In: IEEE ICCVPR, pp. 1–7 (2008)Google Scholar
  20. 20.
    Nocedal, J., Wright, S.: Numerical optimization. Springer, New York (1999)MATHCrossRefGoogle Scholar
  21. 21.
  22. 22.
  23. 23.
    Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Proc. 13, 600–612 (2004)CrossRefGoogle Scholar
  24. 24.
    Barnea, D., Silverman, H.: A class of algorithms of fast digital image registration. IEEE Trans. Comp. 21, 179–186 (1972)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • M. M. Fouad
    • 1
  • R. M. Dansereau
    • 1
  • A. D. Whitehead
    • 1
  1. 1.Dept. of Systems and Computer EngineeringCarleton UniversityOttawaCanada

Personalised recommendations