Automated Detection of Optic Disc in Fundus Images

  • R. Burman
  • A. Almazroa
  • K. Raahemifar
  • V. Lakshminarayanan
Conference paper
Part of the Springer Proceedings in Physics book series (SPPHY, volume 166)


Optic disc (OD) localization is an important preprocessing step in the automated image detection of fundus image infected with glaucoma. An Interval Type-II fuzzy entropy based thresholding scheme along with Differential Evolution (DE) is applied to determine the location of the OD in the right of left eye retinal fundus image. The algorithm, when applied to 460 fundus images from the MESSIDOR dataset, shows a success rate of 99.07 % for 217 normal images and 95.47 % for 243 pathological images. The mean computational time is 1.709 s for normal images and 1.753 s for pathological images. These results are important for automated detection of glaucoma and for telemedicine purposes.


Differential EvolutionDifferential Evolution Optic Disc Normal Image Parent Vector Fundus Image 


  1. 1.
    Rotaru F, Bejinariu SI, Nit CD, Ramona R, Lazăr C (2014) Optic disc identification methods for retinal images. Comput Sci J Moldova, 22, 2(65) (invited article)Google Scholar
  2. 2.
    Kauppi T, Kälviäinen H (2008) Simple and robust optic disc localisation using colour decorrelated templates. In: Proceedings of 10th international conference on advanced concepts for intelligent vision system. Springer, Berlin, pp 719–729Google Scholar
  3. 3.
    Benzid R, Arar D, Bentoumi M (2008) A fast technique for gray level image thresholding and quantization based on the entropy maximization. In: 5th international multi-conference on systems, signals and devices, pp 1–4Google Scholar
  4. 4.
    Sarkar S, Das S, Chaudhuri SS (2012) Multilevel image thresholding based on Tsallis entropy and differential evolution. SEMCCO LNCS 7677:17–24Google Scholar
  5. 5.
    Sahoo PK, Arora G (2004) A thresholding method based on two dimensional Renyi’s entropy. Pattern Recogn 37:1149–1161CrossRefMATHGoogle Scholar
  6. 6.
    Zhao MS, Fu AMN, Yan H (2001) A technique of three level thresholding based on probability partition and fuzzy 3-partition. IEEE Trans Fuzzy Syst 9(3):469–479CrossRefGoogle Scholar
  7. 7.
    Tao WB, Tian JW, Liu J (2003) Image segmentation by three-level thresholding based on maximum fuzzy entropy and genetic algorithm. Pattern Recogn Lett 24:3069–3078CrossRefGoogle Scholar
  8. 8.
    Burman R, Paul S, Das S (2013) A differential evolution approach to multi-level image thresholding using type II fuzzy sets. In: Swarm, evolutionary, and memetic computing. Springer, Switzerland, pp 274–285Google Scholar
  9. 9.
    Storn R, Price K (1997) Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J Global Optim 11:341–359CrossRefMATHMathSciNetGoogle Scholar
  10. 10.
    Zadeh LA (1965) Fuzzy sets. Inf Control 8:338–353CrossRefMATHMathSciNetGoogle Scholar
  11. 11.
    MESSIDOR: Methods for evaluating segmentation and indexing technique dedicated to retinal ophthalmology. (2004)

Copyright information

© Springer India 2015

Authors and Affiliations

  • R. Burman
    • 1
  • A. Almazroa
    • 2
  • K. Raahemifar
    • 3
  • V. Lakshminarayanan
    • 2
    • 4
  1. 1.Department of Electronics and Telecommunication EngineeringJadavpur UniversityKolkataIndia
  2. 2.School of Optometry and Vision ScienceUniversity of WaterlooWaterlooCanada
  3. 3.Department of Electrical and Computer EngineeringRyerson UniversityTorontoCanada
  4. 4.Department of PhysicsUniversity of WaterlooWaterlooCanada

Personalised recommendations