Automatic Detection of Glaucomatous Changes Using Adaptive Thresholding and Neural Networks

  • Katarzyna Sta̧por
  • Lesław Pawlaczyk
  • Radim Chrastek
  • Georg Michelson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3039)


In this paper the new method for automatic classification of fundus eye images into normal and glaucomatous ones is proposed. The new, morphological features for quantitative cup evaluation are proposed based on genetic algorithms. For computation of these features the original method for automatic segmentation of the cup contour is proposed. The computed features are then used in classification procedure which is based on multilayer perceptron. The mean sensitivity is 90%, while the mean specificity: 86%. The obtained results are encouraging.


Genetic Algorithm Automatic Detection Invariant Moment Glaucoma Progress Border Pixel 
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.
    Arabas, J.: Lectures on genetic algorithms. WNT, Warsaw (2001)Google Scholar
  2. 2.
    Bishop, C.M.: Neural networks for pattern recognition. Clarendon Press, Oxford (1995)Google Scholar
  3. 3.
    Chaudhuri, S., et al.: Detection of Blood Vessels in Retinal Images Using Two-Dimensional Matched Filter. IEEE Transactions on Medical Imaging 8(3) (September 1989)Google Scholar
  4. 4.
    Goh, K.G., et al.: ADRIS An Automatic Diabetic Retinal Image Screening system. In: Cios, K.J. (ed.) Medical Data Mining and Knowledge Discovery, November 2000, pp. 181–201. Springer, New York (2000)Google Scholar
  5. 5.
    Gonzalez, R.C., Woods, R.E.: Digital image processing. Prentice-Hall, Englewood Cliffs (2002)Google Scholar
  6. 6.
    Kanski, J., et al.: Glaucoma: a color manual of diagnosis and treatment. Butterworth-Heinemann, Butterworths (1996)Google Scholar
  7. 7.
    Morris, D.T., Donnison, C.: Identifying the Neuroretinal Rim Boundary Using Dynamic Contours. Image and Vision Computing 17, 169–174 (1999)CrossRefGoogle Scholar
  8. 8.
    Osareh, A., et al.: Classification and localisation of diabetic related eye disease. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 502–516. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  9. 9.
    Trier, O., Jain, A., Taxt, T.: Feature extraction methods for character recognition - a survey. Pattern Recognition, 641–662 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Katarzyna Sta̧por
    • 1
  • Lesław Pawlaczyk
    • 1
  • Radim Chrastek
    • 2
  • Georg Michelson
    • 3
  1. 1.Institute of Computer ScienceSilesian University of TechnologyGliwicePoland
  2. 2.Chair for Pattern RecognitionFriedrich-Alexander-University Erlangen-NurembergErlangenGermany
  3. 3.Department of OphthalmologyFriedrich-Alexander-University Erlangen-NurembergErlangenGermany

Personalised recommendations