Resourceful Retinal Vessel segmentation for Early Exposure of Vision Threatening Diseases

Blood Vessels play a major role in our vision process. Likewise, the segmentation of theses vascular structure of blood vessels segmentation projects as a critical part in diagnosis of the various vision threatening diseases including Glaucoma and Diabetic Retinopathy (DR). The accurate way of doing the segmentation of retinal blood vessel is a critical part of analysis of retinal images pertaining to the fundus. Image Processing play a vital role in the medical field. Medical image processing provides very appropriate to diagnoses the various vision threatening diseases like Glaucoma and Diabetic Retinopathy (DR). Nowadays, it is a very growing and challenging field. We proposed a simple supervised approach by using deep learning Convolutional Neural Network. The steps that include in our proposed system are Preprocessing, Segmentation, Feature Extraction, and Classification. Wiener filter is used to de-noise the retinal image. OTSU for segmentation, which separate the foreground and the background and ACO for optimization which enhance the filtered image from Wiener filter. GLCM for feature extraction of the segmented image. For classification, we used a deep learning convolution neural network which provides more iterations. So it will give an appropriate classification for vision threatening diseases. After that a MATLAB software core is implemented.