Title :
A novel approach for the detection of new vessels in the retinal images for screening Diabetic Retinopathy
Author :
Saranya, K. ; Ramasubramanian, B. ; Mohideen, S. Kaja
Author_Institution :
Dept. of Electron. & Commun. Eng., B.S. Abdur Rahman Univ., Chennai, India
Abstract :
Diabetic Retinopathy is a major cause of blindness. It is mainly due to the development of abnormal new blood vessels in the retina. In this approach, we proposed an efficient method to detect the abnormal new blood vessels. The retinal images are pre-processed using Adaptive Histogram Equalization (AHE) and the blood vessels are enhanced by applying Top-hat and Bottom-hat transforms. The enhanced image is segmented using Fuzzy C Means Clustering (FCM) technique. Features based on shape, brightness, position and contrast are extracted from the segmented image and classified as normal or abnormal using K Nearest Neighbour (KNN) Classifier. The performance was evaluated on DRIVE and MESSIDOR database and an accuracy of 96.5% was obtained.
Keywords :
feature extraction; image enhancement; image segmentation; medical image processing; object detection; pattern clustering; transforms; AHE; DRIVE database; FCM technique; KNN; MESSIDOR database; abnormal new blood vessels detection; adaptive histogram equalization; bottom-hat transforms; brightness; contrast; feature extraction; fuzzy c means clustering technique; image enhancement; image segmentation; k nearest neighbour classifier; position; retinal images; screening diabetic retinopathy; shape; top-hat transforms; Accuracy; Biomedical imaging; Image segmentation; Indexes; Optimization; Retina; Shape; Diabetic Retinopathy (DR); Fuzzy C Means Clustering (FCM); K Nearest Neighbour (KNN); Moment Invariants;
Conference_Titel :
Communications and Signal Processing (ICCSP), 2012 International Conference on
Conference_Location :
Chennai
Print_ISBN :
978-1-4673-1621-7
DOI :
10.1109/ICCSP.2012.6208394
