Automated Retinal Vessel Segmentation Using fuzzy Mathematical Morphology an‎d double Threshold

Assessment of retinal vessel is an important factor for the many medical disorders. The retinal vessel analysis can be done by first extracting the retinal images from the background. The changes in the retinal vessels due to the pathologies can be easily identified by segmenting the retinal vessels. In this paper we describe an automatic method for retinal vessel segmentation. Segmentation of retinal vessels is done to identify the early diagnosis of the disease like diabetic retinopathy, hypertensive retinopathy and arteriosclerosis. In this the blood vessel is segmented using fuzzy morphological operation with the disc shaped structuring element and double thresholding. This method is applied on the publicly available DRIVE database. Experimental results obtained by using green-channel images have been presented. The proposed algorithm has been shown to be a highly effective method for classifying retinal blood vessels. The proposed algorithm being simple and easy to implement, is best suited for fast processing applications.