Comparison of two different types of morphological method for feature extraction of retinal vessels in colour fundus images
This paper presents an automated blood vessel detection method from the fundus image. The method first performs some basic image preprocessing tasks on the green channel of the retinal image. A combination of morphological operations like top- hat and bottom-hat transformations are applied on the preprocessed image to highlight the blood vessels. Finally, the Kohonen Clustering Network is applied to cluster the input image into two clusters namely vessel and non-vessel. The performance of the proposed method is tested by applying it on retinal images from Digital Retinal Images for Vessel Extraction (DRIVE)database. The results obtained from the proposed method are compared with three other state of the art methods. The sensitivity, false-positive fraction (FPF) and accuracy of the proposed method is found to be higher than the other methods which imply that the proposed method is more efficient and accurate.