Abstraction of Exudates in Color Fundus Images

  • Richu Paul
  • S. Vasanthi
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 192)


Diabetic retinopathy is a major cause of blindness. Earliest signs of diabetic retinopathy are damage to blood vessels in the eye and then the formation of lesions in the retina. This project presents a method for the detection of abnormalities in the retina such as the exudates in retinopathy images using computational intelligence techniques. The color retinal images are segmented using fuzzy c-means clustering following color normalization and contrast enhancement. For classification of these segmented regions into exudates and nonexudates, a set of initial features such as color, size, edge strength, and texture are extracted. A genetic based algorithm is used to rank the features and identify the subset that gives the best classification results. Using a multilayer neural network classifier, the selected feature vectors are then classified.


Fuzzy c-means (FCMs) Kmeans algorithm Gabor filters Neural Networks (NNs) 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Phillips, R., Spencer, T., Ross, P., Sharp, P., Forrester, J.: Quantification of diabetic maculopathy by digital imaging of the fundus: Eye, vol. 5, pp. 130–137 (1991)Google Scholar
  2. 2.
    Gardner, G., Keating, D., Williamson, T., Elliott, A.: Automatic detection of diabetic retinopathy using an artificial neural network: A screening tool. Brit. J. Ophthalmol. 80, 940–944 (1996)CrossRefGoogle Scholar
  3. 3.
    Wang, H., Hsu, H., Goh, K., Lee, M.: An effective approach to detect lesions in retinal images. In: Proc. IEEE Conf. Comput. Vis. Pattern Recogn., Hilton Head Island, SC, vol. 2, pp. 181–187 (2000)Google Scholar
  4. 4.
    Hunter, A., Lowell, J., Owens, J., Kennedy, L.: Quantification of diabetic retinopathy using neural networks and sensitivity analysis. Proc. Artif. Neural Netw. Med. Biol., 81–86 (2000)Google Scholar
  5. 5.
    Sinthanayothin, C.: Image analysis for automatic diagnosis of diabetic retinopathy: Ph.D. dissertation, King’s College of London, London, U.K (1999)Google Scholar
  6. 6.
    Walter, T., Klein, J., Massin, P., Erginary, A.: A contribution of image processing to the diagnosis of diabetic retinopathy, detection of exudates in colour fundus images of the human retina. IEEE Trans. Med. Imag. 21(10), 1236–1243 (2002)CrossRefGoogle Scholar
  7. 7.
    Niemeijer, M., Ginneken, B.V., Russell, S.R., Suttorp, M., Abramoff, M.D.: Automated detection and differentiation of drusen, exudates and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis. Invest. Ophthalmol. Vis. Sci. 48, 2260–2267 (2007)CrossRefGoogle Scholar
  8. 8.
    Osareh, A., Mirmehdi, M., Thomas, B., Marham, R.: Automatic recognition of exudative maculopathy using fuzzy c-means clustering and neural networks. In: Proc. Medical Image Understanding Analysis Conf., pp. 49–52 (2001)Google Scholar
  9. 9.
    Rafael, C.G., Richard, E.W.: Digital Image Processing, 3rd edn., pp. 443–445, 598–605. University of Tennessee (1992)Google Scholar
  10. 10.
    Dougman, J.: High confidence visual recognition of persons by a test of statistical independence. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1148–1161 (1993)CrossRefGoogle Scholar
  11. 11.
    Osareh, A., Shadgar, B., Markham, R.: A Computational-Intelligence-Based Approach for Detection of Exudates in Diabetic Retinopathy Images. IEEE Trans. Inform Tech. in Biomedicine 13(4), 535–545 (2009)CrossRefGoogle Scholar
  12. 12.
    Stelios, K., Vassilios, C.: A robust fuzzy local information c-means clustering algorithm. IEEE Trans. Image Processing 19(5), 1328–1338 (2010)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Richu Paul
    • 1
  • S. Vasanthi
    • 1
  1. 1.Department of Electronics and communicationK.S.R College of TechnologyTiruchengodeIndia

Personalised recommendations