Abstract
The retina is the important and only part of the human body from which the blood vessel information can be clearly obtained. The information about blood vessels in the retina plays an important role in the finding and efficient treatment of diseases such as glaucoma, macular degeneration, degenerative myopia, diabetic retinopathy, etc. The structure of the retinal vessels is a significant way to predict the presence of eye diseases such as hypertension, diabetic retinopathy, glaucoma, hemorrhages, retinal vein occlusion, and neovascularization. Ophthalmologists find it difficult when the diameter and turns for the retinal blood vessel or shape of the optic disk structures are complicated or a huge number of eye images are acquired to be marked by hand, all of which eventually leads to error. Therefore, an automated method for retinal blood vessel extraction and optic disk segmentation, which preserves various vessel and optic disk characteristics, is presented in this work and is attractive in computer-based diagnosis. Here, we implement a new competent method for detection of diseases using the retinal fundus image. In this anticipated work the first step is the extraction of retinal vessels by graph cut technique. The retinal vessel information is then used to calculate approximately the position of the optic disk. These results are given to an ANN classifier for the detection and classification of diseases. By robotically identifying the disease from normal images, the workload and its costs will be reduced.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call