Retinal Blood Vessel Segmentation using combination of top-hat and h-maxima methods

the diagnosis of retinal image is a basic and important concept for Diabetic Retinopathy detection and analysis. The important role play in digital retinal image is Vessel segmentation in diagnosis of various diseases. In this paper we have been working on most important portion which is segmentation of blood vessel. Blood vessels are segmented via top-hat and h-maxima methods and for classification Convolutional Neural Networks (CNN) technique can be used to get better accuracy. The network is trained in such a manner that it automatically segments the blood vessels and classify weather it is normal or abnormal. High-end graphics processor unit i.e. GPU system is used for training on largely available images and display the outputs, and this also works for high-level classification task. We have implemented this on two publicly available databases (DRIVE and STARE). The performance parameter involves during classification are accuracy, sensitivity, and specificity [4].