Detection of Exudates in Color Fundus Image

International Journal of Electronics and Communication Engineering

© 2015 by SSRG - IJECE Journal

Volume 2 Issue 11

Year of Publication : 2015

Authors : S.Bibiana Vincy and Dr. C. Chitra

10.14445/23488549/IJECE-V2I11P102

How to Cite?

S.Bibiana Vincy and Dr. C. Chitra, "Detection of Exudates in Color Fundus Image," SSRG International Journal of Electronics and Communication Engineering, vol. 2,  no. 11, pp. 1-10, 2015. Crossref, https://doi.org/10.14445/23488549/IJECE-V2I11P102

Abstract:

A new method for the detection of blood vessels that improves the detection of exudates in fundus photographs. The pre-processing method is used to enhance the input image and also for noise removal. The initial estimation of exudates is obtained by segmenting the optic disc and blood vessels from the fundus image. In order to segment the optic disc and blood vessel separate algorithms are used. First, circular Hough transform is used for segmenting the optic disc inorder to find the circular object from an image. Then vessel detection algorithm is used to detect the blood vessel in the image. The extracted blood vessel tree and optic disc could be subtracted from the over segmented image to get an initial estimate of exudates. The final estimation of exudates can then be obtained by morphological reconstruction based on the appearance of exudates.

Keywords:

Pre-processing, Optic disc, Blood vessel, Exudates.

References:

[1] Fong D. S.( 2003) et al., “Diabetic Retinopathy”, Diabetes Care, vol. 26, no. 1, pp.226-229.
[2] A. Sopharak, and B. Uyyanonvara, (2009) “Automatic Exudates Detection from Non- dilated Diabetic Retinopathy Retinal Images Using Fuzzy C-means Clustering”, Sensor, vol. 9(3). pp. 2148-2161.
[3] Z. Xiaohui and O. Chutatape, (2004) “Detection and Classification of Bright Lesions in Color Fundus Images”, IEEE International Conference on Image Processing (ICIP), vol. 1, pp. 139-142.
[4] G. Kande, P. Subbaiah and T. Savithri, (2008.)“Segmentation of Exudates and Optic Disk in Retinal Images”, IEEE Sixth Indian Conference on Computer Vision, Graphic & Image Processing,
[5] A. Osareh, M. Mirmehdi, B. Thomas and R. Markham (2003) “Automated identification of diabetic retinal exudates in digital colour images”, Ophthalmol, vol. 87, pp. 1220-23.
[6] Olson.J.A, Strachana.F.M, Hipwell.J.H, (2003) “A comparative evaluation of digital imaging, retinal photography and optometrist examination in screening for diabetic retinopathy”, Diabetic Medicine, vol. 20, pp. 528– 534.
[7] Solouma.N.H,Youssef.A.B, Badr.Y.A, Kadah.Y.M,(2002) ”A new real-time retinal tracking system for image-guided laser treatment”, IEEE Transaction on Biomedical vol. 49, pp. 1059–1067.
[8] Gagnon.L, Lalonde.M, Beaulieu.M, Boucher.M.C,(2001) “Procedure to detect anatomical structures in optical fundus images”, in Proceeding, SPIE Medical Imaging: Image Processing, vol.10, no.7, pp. 1218–1225.
[9] Mitra.S.K, Lee.T.W, Goldbaum.M, (2005) “Bayesian network based sequential inference for diagnosis of diseases from retinal images”, Pattern Recognition Letters vol.26 , pp. 459–470.
[10] Mabrouk.M.S, Solouma.N.H, Kadah.Y.M, (2006), “Survey of retinal image segmentation and registration”, GVIP Journal ,pp. 23-37
[11] Atul Kumar, Abhishek Kumar Gaur, Manish Srivastava (2012), “A segment based technique for detecting exudates from retinal fundus image”, 2nd International Conference on Communication, Computing & Security.
[12] Akita.K, Kuga.H, (1982), “A computer method of understanding ocular fundus images, Pattern Recognition” vol 15, pp. 431–443.