Comparative Analysis of Edge Detection Techniques for Extracting Blood Vessels in Diabetic Retinopathy
Diabetic retinopathy (DR) is one of the serious complications caused by diabetes. It damages the small blood vessel of the retina, which leads to loss of vision. Accurate extraction of retinal blood vessels is an important task in computer-aided diagnosis of DR. The edge detection technique has been greatly benefited in interpreting the information contents in the retinal blood vessel. The preprocessing of retinal image may help in detecting the early stage of symptoms in DR. In this article, we compared the results of Sobel and Canny edge operators for finding the abnormalities in retinal blood vessels. The Canny operator is found to be more accurate in detecting even tiny blood vessels compared to Sobel operator for an affected diabetic retinal image. The peak signal-to-noise ratio (PSNR) is also found to be high in the Canny operator.
KeywordsDiabetic retinopathy Edge detection Sobel Canny operator
The authors thank the doctors and administrator of L.V. Prasad Eye Institute for providing the retinal images used in this work.
- 1.Basu, S., Vellakkal, S., Agrawal, S., Struckler, D., Popkin B., Ebrahim, S.: Averting obesity and type 2 diabetes in India through sugar-sweetened beverage taxation: an economic-epidemiologic modelling study. PLoS Med. 11, (2014)Google Scholar
- 2.Jason, G.: India’s Diabetes Epidemic Cuts Down Millions Who Escape Poverty, Bloomberg. Retrieved 8 Jun 2012Google Scholar
- 3.Diabetes and Eye Disease, http://www.ncbi.nlm.nih.gov. Retrieved on 21 Apr 2012
- 7.Ramalho, M., Curtis, K.M.: Edge detection using neural network arbitration. In: 5th Int. Conf. on Image Processing and its Applications, pp. 514–518 (1995)Google Scholar
- 11.Yin, Y., Adel, M., Bourennane, S.: Automatic segmentation and measurement of vasculature in retinal fundus images using probabilistic formulation. Comput Math Methods Med: 1–16 (2013)Google Scholar
- 12.Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell., PAMI-8(6), 679–698 (1986)Google Scholar