Detection of Bifurcation of Nerve in Exudates in Diabetic Retinopathy Images using Digital Image Processing Algorithms

doi:10.3850/978-981-08-7618-0_1416

Detection of Bifurcation of Nerve in Exudates in Diabetic Retinopathy Images using Digital Image Processing Algorithms

N. GopalaKrishnan and P. Arun Srinivas

SSN College of Engineering, Kalavakkam, Chennai, India.

ABSTRACT

Exudates are the primary sign of Diabetic Retinopathy. Early detection can potentially reduce the risk of blindness. An automatic method to detect exudates from low contrast digital images of retinopathy patients is proposed here. Images undergo preprocessing for the removal of noise. Segmentation stage clusters the image into two distinct classes by the use of fuzzy c-means algorithm. Advanced Modified cross point number (AMCN) methods are employed for a window size of 7x7 in order to detect the detection of bifurcation and crossover points in fundus images so that exudates can be identified properly. This method has been tested using 100 images and the performance is satisfactory.

Keywords: Exudates, Diabetic retinopathy, MCN (modified cross point number), Fuzzy c-means algorithm.

Back to TOC

FULL TEXT(PDF)