BMVC91 pp 275-283 | Cite as

Automated Analysis of Retinal Images

  • Piotr Jasiobedzki
  • Chris J. Taylor
Conference paper


We describe a method for segmenting retinal images using positions of blood vessels supplying the retina. The image is tessellated into irregularly shaped primary regions which are bounded by vessels, chains of microaneurysms, edges, etc. Boundaries are classified into groups using a trained set of grey level models. We define a process of merging primary regions into large patches using image properties such as texture and intensity, and semantic interpretations of boundaries and their measured properties. The method which makes extensive use of morphological processing depends on a limited number of parameters which have natural physical interpretations.


Grey Level Retinal Image Image Property Primary Region Adjacency Graph 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Tanaka M., Tanaka K.: An Automatic Technique for Fundus Photograph Mosaic and Vascular Net Reconstruction. Proc. of MEDINFO 80, Tokyo, pp.116-120.Google Scholar
  2. [2]
    Jagoe R., Wootton R.: Quantification of Retinal Damage During Cardiopulmonary Bypass: Comparison of Computer and Human Assessment. IEE Proc., vol. 137, pt. I, no. 3, June, 1990, pp. 170–175.Google Scholar
  3. [3]
    Katz N., Goldbaum M., Nelson M., Chaudri S.: An Image Processing System for Automatic Retina Diagnosis. Proc. of SPTE vol. 902, 1988, pp.131–137.Google Scholar
  4. [4]
    Chaudri S., Chatterjee S., Katz N., Nelson M., Goldbaum M.: Detection of Blood Vessels in Retinal Images Using Two-Dimensional Matched Filters. IEEE Trans on Medical Imaging, vol. 8, no. 3, 1989, pp. 263–269.CrossRefGoogle Scholar
  5. [5]
    Akita K., Kuga H.: Pattern Recognition of Blood Vessel Networks in Ocular Fundus Images. Proc. SPIE vol. 375, 1982 pp. 436–441.Google Scholar
  6. [6]
    Lay J., Badouin B.: Computer Analysis of Angioflourograms. Proc. of VII Int. Conf. on Pattern Recognition, 1984, pp.927-929.Google Scholar
  7. [7]
    Goldberg E.G., Varma S., Spaeth S.: Quantification of Progressive Diabetic Macular Non-perfusion. Ophthalmic Surgery, vol. 20, no. 1, 1989, pp. 42–45.Google Scholar
  8. [8]
    Jasiobedzki P., Macleod D., Taylor C.J.: Detection of Non-perfused Zones in Retinal Images. IV IEEE Symposium on Computer Based Medical Systems, Baltimore, May, 1991, pp. 162-169.Google Scholar
  9. [9]
    Pavlidis T: Structural Pattern Recognition. Springer Verlag, 1979.Google Scholar
  10. [10]
    Meyer E, Beuchers S.: Morphological Segmentation. J. of Visual Communication and Image Interpretation, vol. 1, no. 1, Sept., 1990, pp. 21–26.CrossRefGoogle Scholar
  11. [11]
    Montanvert A., Meer P., Rosenfeld A.: Hierarchical Image Analysis Using Irregular Tesselations. IEEE Trans. on PAMI, vol. 13, no. 4, April, 1991, pp. 307–316.CrossRefGoogle Scholar
  12. [12]
    Goetcherian V: From Binary to Grey Tone Image Processing Using Fuzzy Logic Concepts. Pattern Recognition, vol. 12, 1980, pp. 7–15.CrossRefGoogle Scholar
  13. [13]
    Serra J.: Image Analysis and Mathematical Morphology. Academic Press, 1982.Google Scholar
  14. [14]
    Werman M., Peleg S.: Min-Max Operations in Texture Analysis. IEEE Trans. on PAMI, vol. 7, no. 6, 1985, pp. 730–733.CrossRefGoogle Scholar
  15. [15]
    Maragos P.: Pattern Spectrum and Multiscale Shape Representation. IEEE Trans. on PAMI, vol. 11, no. 7, July, 1989, pp. 701–715.CrossRefMATHGoogle Scholar
  16. [16]
    Mandelbrot B.: The Fractal Geometry of Nature. Freeman, 1982.Google Scholar
  17. [17]
    Peleg et al.: Multiple Resolution Texture Analysis and Classification. IEEE Trans. on PAMI, vol. 6, no. 4, 1984, pp.518–523.CrossRefMathSciNetGoogle Scholar
  18. [18]
    Rigaut J.P.: Automated Image Segmentation by Mathematical Morphology and Fractal Geometry. J. of Microscopy, vol. 150, 1988, pp. 21–30.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1991

Authors and Affiliations

  • Piotr Jasiobedzki
    • 1
  • Chris J. Taylor
    • 1
  1. 1.Wolfson Image Analysis Unit, Dept. of Medical BiophysicsUniversity of ManchesterManchesterUK

Personalised recommendations