Retinal Blood Vessel Segmentation Using Graphical User Interface (GUI) for Diagnosis of Disease

The blood vessel detection and segmentation technique plays a useful clinical role in an automated retinopathy analysis system. But manual segmentation of vessels requires expertise. It is a very tedious and time consuming task. Employing computational intelligence for this purpose would help in efficient retinal analysis. An user friendly graphical user interface (GUI) that is MATLAB based tool used to segments the blood vessels by means of several operations applied on the retinal image including Grayscale conversion , Gabor filtering , Image Binarization , Principal component analysis , Fuzzy c-means clustering proposed in this paper. The paper is validated on images from publicly available DRIVE database and achieves an accuracy of 94.61 % with sensitivity of 73.38% and specificity of 98.20%, which is comparable with the existing blood vessel segmentation technique.