Hidden Markov Random Field and Gaussian Mixture Model Based Hidden Markov Random Field for Contour Labelling of Exudates in Diabetic Retinopathy—A Comparative Study

  • E. Revathi Achan
  • T. R. SwapnaEmail author
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 30)


Diabetic Retinopathy (DR) is one of the important causes of blindness in diabetic patients. Diabetes that affects the retina is called diabetic retinopathy. Diabetic retinopathy occurs due to the damage of blood vessels in retina and increase in the level of glucose. Different pathologies are normally seen in DR such as microaneurysms, hard exudates, soft exudates, cotton wool spots and haemorrhages. We have done a comparative study of Hidden Markov Random Field (HMRF) and Gaussian Mixture Model (GMM) based HMRF for automatic segmentation of exudates and the performance analysis of both methods. The preprocessing consists of candidate extraction step using greyscale morphological operation of closing and initial labelling of exudates using K-means clustering followed by contour detection. In contour detection, we have analysed two approaches, one is GMM-based HMRF and the other is HMRF. DIARETDB1 is the dataset used.


Diabetic retinopathy Colour fundus Exudates Hidden Markov random field Gaussian mixture model 


  1. 1.
    Ram P, Swapna TR (2018) Profiling of hard exudates and microaneurysms to evaluate the progress of diabetic retinopathy. Int J Pure Appl Math 118(Special Issue 8):127–131Google Scholar
  2. 2.
    Ahmad A et al (2014) Image processing and classification in diabetic retinopathy: a review. In: 2014 5th European workshop on visual information processing (EUVIP). IEEEGoogle Scholar
  3. 3.
    Hussain F, Nandi Jaafar AK, Al-Nuaimy W (2010) Automated detection of exudates in retinal images using a splitand-merge algorithm. In: European signal processing conference, EUSIPCOGoogle Scholar
  4. 4.
    Choudhury S et al (2016) Fuzzy C means based feature extraction and classification of diabetic retinopathy using support vector machines. In: 2016 International conference on communication and signal processing (ICCSP). IEEEGoogle Scholar
  5. 5.
    Harini R, Sheela N (2016) Feature extraction and classification of retinal images for automated detection of diabetic retinopathy. In: 2016 Second international conference on cognitive computing and information processing (CCIP). IEEEGoogle Scholar
  6. 6.
    Priya R, Aruna P (2012) SVM and neural network based diagnosis of diabetic retinopathy. Int J Comput Appl 41(1)Google Scholar
  7. 7.
    Pires R et al (2014) Automatic diabetic retinopathy detection using BossaNova representation. In: 2014 36th Annual International Conference of the IEEE Engineering in medicine and biology society (EMBC). IEEEGoogle Scholar
  8. 8.
    Maher R, Kayte S, Bhable S, Kayte J (2015) Automated detection of diabetic retinopathy in fundus images. Inter J Emer Res Manag Tech 4(11):137–145Google Scholar
  9. 9.
    Kusakunniran W, Rattanachoosin J, Sutassananon K, Anekkitphanich P (2016) Automatic quality assessment and segmentation of diabetic retinopathy images. In: Region 10 conference (TENCON), 2016 IEEE, pp 997–1000Google Scholar
  10. 10.
    Shilpa BV, Nagabhushan TN (2015) An ensemble approach to detect exudates in digital fundus images. In: 2016 Second international conference on cognitive computing and information processing (CCIP). IEEE. Sing fuzzy C means. Int J Comput Appl 113(11)Google Scholar
  11. 11.
    Gandhi M, Dhanasekaran R (2013) Diagnosis of diabetic retinopathy using morphological process and SVM classifier. In: 2013 International conference on communications and signal processing (ICCSP). IEEEGoogle Scholar
  12. 12.
    Ganesh S, Basha AM (2015) Automated detection of diabetic retinopathy using retinal optical images. Int J Sci Technol Manage 4(2)Google Scholar
  13. 13.
    Sindhura A, Deva Kumar S, Ramakrishna Sajja V, Gnaneswara Rao N (2016) Identifying exudates from diabetic retinopathy images. In: 2016 International conference on advanced communication control and computing technologies (ICACCCT). IEEE, pp 132–136Google Scholar
  14. 14.
    Kaur G (2015) Review on: detection of diabetic retinopathy using SVM and MDA. Int J Comput Appl 117(20)Google Scholar
  15. 15.
    Deshmukh AV et al (2015) Features based classification of hard exudates in retinal images. In: 2015 International conference on advances in computing, communications and informatics (ICACCI). IEEEGoogle Scholar
  16. 16.
    Chowdhury AR, Banerjee S (2015) Detection of cotton wool spots from retinal images using fuzzy C means. Int J Comput Appl 113(11)Google Scholar
  17. 17.
    Rakshitha TR, Devaraj D, Prasanna Kumar SC (2016) Comparative study of imaging transforms on diabetic retinopathy images. In: IEEE international conference on recent trends in electronics, information and communication technology (RTEICT). IEEE, pp 118–122Google Scholar
  18. 18.
    Zhao Y et al (2017) Intensity and compactness enabled saliency estimation for leakage detection in diabetic and malarial retinopathy. IEEE Trans Med Imaging 36(1):51–63CrossRefGoogle Scholar
  19. 19.
    Vijayan M, Jose R, Jose S, Abraham S, Joy J (2017) Study on quality of life assessment in diabetic retinopathy among patients with type 2 diabetes. Asian J Pharm Clin Res 10:116. Scholar
  20. 20.
    Roychowdhury, S, Koozekanani DD, Parhi KK (2014) Dream: diabetic retinopathy analysis using machine learning. IEEE J Biomed Health Inform 18(5):1717–1728CrossRefGoogle Scholar
  21. 21.
    Kayte SN, Maher RS, Kayte CN (2015) Automated identification of hard exudates and cotton wool spots using biomedical image processing. Int J Comput Appl 131(5)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringAmrita School of Engineering, Amrita Vishwa VidyapeethamCoimbatoreIndia

Personalised recommendations