Diabetic Retinopathy Analysis using Retinal Image Matching  
  Authors : Asha Mundhe; Dr. M.S. Nagmode


In development of automated screening systems for diabetic retinopathy, main step is Optic disc detection and vascular feature extraction. Here, we propose a method for diagnosis of Diabetic Retinopathy using optic disc and vascular features based retinal image matching. This method can be used for Person identification using retinal images or automatic detection of Diabetic Retinopathy. Optic disc and vascular features are the two important features extracted from the retinal image. On the basis of these features, corresponding images are matched. Image matching method identifies the same blood vessel in the corresponding images and compare the desired features. Initial results are good and demonstrate that the proposed method is suitable for Diagnosis of Diabetic Retinopathy.


Published In : IJCAT Journal Volume 1, Issue 7

Date of Publication : 31 August 2014

Pages : 371 - 377

Figures :21

Tables : --

Publication Link : Diabetic Retinopathy Analysis using Retinal Image Matching




Asha Mundhe : Department of E&TC Engineering, University of Pune, MIT College of Engineering, Pune, Maharashtra, India

Dr. M.S. Nagmode : Department of E&TC Engineering, University of Pune, MIT College of Engineering, Pune, Maharashtra, India








Diabetic Retinopathy

Retinal Image

Optic Disc

Vessel Bifurcation

Branch and Crossover Points

Retinal Image Matching

This paper presents feature based retinal image matching. The method is highly suitable for diabetic retinopathy analysis. It is efficient in matching the retinal images and searching the corresponding vascular features set. Applying the method, the medical practitioners can examine significantly changes on different vascular features for each of the vesselsegments in retinal fundus images. For biometric security application, this method requires simple modification. We are in process of gathering multiple images forthe same person to have a large scale analysis and next validation of the method.










[1] Alauddin Bhuiyan, Baikunth Nath, Kotagiri Ramamohanara and Tien Y. Wong “Retinal Image Matching Using Hierarchical Vascular Features” The University of Melbourne, VIC 3002,Australia.

[2] U.M. Akram and A.S. Khan. “Automated Detection of Dark and Bright Lesions in Retinal Images for Early Detection of Diabetic Retinopathy.” Journal of Medical Systems, Volume 36, Issue 5,November 2012.

[3] S. Sekhar, W. Al-Nuaimy and A. K. Nandi “Automated Localisation of Optic Disk and Fovea in Retinal Fundus Images” 16th European Signal 2008.

[4] Niall Patton, Tariq M. Aslam, Thomas MacGillivray Ian J Deary, Baljean Dhillon “Retinal image analysis: Concepts, and potential” Progress in Retinal and Eye Research 25 2006.

[5] Acharya, U. R., Lim, C. M., Ng, E. Y. K., Chee, C., and Tamura, T., “Computer based detection of diabetes retinopathy stages using 2009. Digital fundus images”. J. Eng. Med .223(H5): 545 –553.

[6] Ch. Adi Babu, B. J.V.K. Ratnam, “Feature-Based Retinal Image Registration” (IJATER) Volume 2, Issue 4,July 2012.

[7] Amin Dehghani, Hamid Abrishami Moghaddam and Mohammad Shahram Moin “Optic disc localization in retinal images using histogram matching” EURASIP Journal on Image and Video Processing 2012, 2012:19

[8] Jaspreet Kaur, Dr.H.P.Sinha “Automated Localisation of Optic Disc and Macula from Fundus Images” IJARCSSE, Volume 2, Issue 4, April 2012.

[9] B.Hima Bindu “Bifurcation Structures for Retinal Image Registration & Vessel Extraction” IJES Vol. 1, Issue 4 (October 2012).

[10] J. Liu, D. W. K. Wong, J.H. Lim, X. Jia , F. Yin , H. Li , W. Xiong, T. Y. Wong “Optic Cup and Disk Extraction from Retinal Fundus Images for Determination of Cup-to-Disc Ratio” 2008 IEEE.

[11] Alberto Martin and Sabri Tosunoglu “Image Processing Techniques for Machine Vision”Florida.

[12] S. Wild, G. Roglic, A. Green et al., “Global prevalence of diabetes: estimates for the year 2000 and projections for 2030,” Diabetes Care 27, 2004, pp.1047-1053.