Automated detection of diseases by nicking quantification in retinal images

Digital retinal imaging uses high-resolution imaging systems to take pictures of the inside of your eye. This helps the doctors to access the retina and helps them to detect and manage health conditions like glaucoma, diabetes and macular degeneration. The risk of cardio vascular diseases can be identified by measuring the retinal blood vessel. The identification of the wrong blood vessel may lead to a wrong diagnosis result. A retinal image provides a good diagnostic approach of what is happening inside the human body. By analyzing the humans retinal image one can able to identify cardio vascular condition of the body. To overcome that we are using the following proposed method. This paper proposes a novel technique that collects information about all blood vessels that present in the retinal image and identifies the true vessel in a retinal image. In the proposed method, first the input image is choose and the blood vessels are segmented. From that the crossover point detection is applied to detect the vessels which are crossing each other by using the window with the neighboring pixels. Then, by applying the graph tracer method the vessels are identified and represented them in the form of subsequent vessel measurements. Then, the venular and the artery are identified and the width is calculated by measuring the arterio-venous crossings. Thus, from this the diseases is identified and the performance is calculated by comparing our proposed method with various retinal images.