alidastgheib/VesSeg_2019

Retinal diseases are already the most common cause of childhood blindness worldwide. Accordingly, it would be extensively beneficial to populations and health-related communities if we can automate the procedure of diagnosis thoroughly or at least partially by exploiting capabilities of computer-aided diagnosis (CAD). This paper proposes two segmentation methods, a supervised method and an unsupervised one, which shall expertly tackle the problem of vessel segmentation in retinal fundus images. Dataset used in this research is the so-called DRIVE dataset which is public and has been established to enable comparative studies on segmentation of blood vessels, hence containing 2 groups that each group constitutes of 20 colour images for the purpose of train and test. Our supervised method has achieved a higher accuracy of 94.47% by exploiting support-vector-machine technique (SVM) as its intellect, and our unsupervised method has achieved an ample accuracy of 94.28%, with a response time of 1.65 second providing operators and/or systems with fast and reliable results.