Effects of Preprocessing Eye Fundus Images on Appearance Based Glaucoma Classification

  • Jörg Meier
  • Rüdiger Bock
  • Georg Michelson
  • László G. Nyúl
  • Joachim Hornegger
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4673)


Early detection of glaucoma is essential for preventing one of the most common causes of blindness. Our research is focused on a novel automated classification system based on image features from fundus photographs which does not depend on structure segmentation or prior expert knowledge. Our new data driven approach that needs no manual assistance achieves an accuracy of detecting glaucomatous retina fundus images compareable to human experts. In this paper, we study image preprocessing methods to provide better input for more reliable automated glaucoma detection. We reduce disease independent variations without removing information that discriminates between images of healthy and glaucomatous eyes. In particular, nonuniform illumination is corrected, blood vessels are inpainted and the region of interest is normalized before feature extraction and subsequent classification. The effect of these steps was evaluated using principal component analysis for dimension reduction and support vector machine as classifier.


Glaucoma Retina imaging Digital color fundus photograph Classification Image enhancement 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Sivalingam, E.: Glaucoma: An overview. J. Ophthalmic Nurs. Tech. 15(1), 15–18 (1996)Google Scholar
  2. 2.
    Lester, M., Garway-Heath, D., Lemij, H.: Optic Nerve Head and Retinal Nerve Fibre Analysis. European Glaucoma Society (2005)Google Scholar
  3. 3.
    Malinovsky, V.E.: An overview of the Heidelberg Retina Tomograph. J. Am. Optom. Assoc. 67(8), 457–467 (1996)Google Scholar
  4. 4.
    Chrástek, R., Wolf, M., Donath, K., Niemann, H., Paulus, D., Hothorn, T., Lausen, B., Lämmer, R., Mardin, C., Michelson, G.: Automated segmentation of the optic nerve head for diagnosis of glaucoma. Med. Image. Anal. 9(4), 297–314 (2005)CrossRefGoogle Scholar
  5. 5.
    Swindale, N.V., Stjepanovic, G., Chin, A., Mikelberg, F.S.: Automated analysis of normal and glaucomatous optic nerve head topography images. Investig Ophthalmol Vis. Sci. 41(7), 1730–1742 (2000)Google Scholar
  6. 6.
    Greaney, M.J, Hoffman, D.C, Garway-Heath, D.F, Nakla, M., Coleman, A.L, Caprioli, J.: Comparison of optic nerve imaging methods to distinguish normal eyes from those with glaucoma. Invest Ophthalmol. Vis. Sci. 43(1), 140–145 (2002)Google Scholar
  7. 7.
    Hornegger, J., Niemann, H., Risack, R.: Appearance-based object recognition using optimal feature transforms. Pattern Recogn. 2(33), 209–224 (2000)CrossRefGoogle Scholar
  8. 8.
    Zhao, W., Chellappa, R., Phillips, P.J., Rosenfeld, A.: Face recognition: A literature survey. ACM Comput. Surv. 35(4), 399–458 (2003)CrossRefGoogle Scholar
  9. 9.
    Narasimha-Iyer, H., Can, A., Roysam, B., Stewart, C.V., Tanenbaum, H.L., Majerovics, A., Singh, H.: Robust detection and classification of longitudinal changes in color retinal fundus images for monitoring diabetic retinopathy. IEEE Trans. Biomed. Eng. 53(6), 1084–1098 (2006)CrossRefGoogle Scholar
  10. 10.
    Hoover, A., Kouznetsova, V., Goldbaum, M.: Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imag. 19(3), 203–210 (2000)CrossRefGoogle Scholar
  11. 11.
    Walter, T., Klein, J.-C.: Automatic detection of microaneurysms in color fundus images of the human retina by means of the bounding box closing. In: Colosimo, A., Giuliani, A., Sirabella, P. (eds.) ISMDA 2002. LNCS, vol. 2526, pp. 210–220. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  12. 12.
    Canny, J.F.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986)CrossRefGoogle Scholar
  13. 13.
    Can, A., Shen, H., Turner, J.N., Tanenbaum, H.L., Roysam, B.: Rapid automated tracing and feature extraction from retinal fundus images using direct exploratory algorithms. IEEE Trans. Inform. Tech. Biomed. 3(2), 125–138 (1999)CrossRefGoogle Scholar
  14. 14.
    Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of the 27th annual conference on Computer graphics and interactive techniques, SIGGRAPH 2000, New Orleans, USA, pp. 417–424 (2000)Google Scholar
  15. 15.
    Shen, J., Chan, T.F.: Mathematical models for local nontexture inpaintings. SIAM J. Appl. Math. 62(3), 1019–1043 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Karali, E., Asvestas, P., Nikita, K.S., Matsopoulos, G.K.: Comparison of different global and local automatic registration schemes: An application to retinal images. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3216, pp. 813–820. Springer, Heidelberg (2004)Google Scholar
  17. 17.
    EL-Manzalawy, Y., Honavar, V.: WLSVM: Integrating LibSVM into Weka Environment (2005), software available at

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Jörg Meier
    • 1
  • Rüdiger Bock
    • 1
  • Georg Michelson
    • 2
  • László G. Nyúl
    • 1
  • Joachim Hornegger
    • 1
  1. 1.Institute of Pattern Recognition, University of Erlangen-Nuremberg, Martensstraße 3, 91058 Erlangen 
  2. 2.Department of Ophthalmology, University of Erlangen-Nuremberg, Schwabachanlage 6, 91054 Erlangen 

Personalised recommendations