For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
In modern days the crucial challenges for society in world is color blindness which is caused for diabetic retinopathy. The disease gradually enhance everywhere. This work is performed for OD classification in several stages of retinopathy as severe, mild, moderate etc. Early detection and treatment is become important for more prevention of probability of color blindness. The main objectives are to efficiently segmentation of blood vessels and OD in retinal area and to detect and classify the areas of abnormalities present in eye. The work is based on threshold based segmentation, morphological segmentation, and edge detection and classifier is used for classification of diseases. Image Preprocessing is used for working with color image required computational time more than gray image. Then contrast of images are enhanced with some histogram based methods. Here according to the situation of damaged retina the stages are classified with SVM classifier. These methods, the segmentation methods are efficiently used to identify that optical nerve, blood vessel, abnormalities are present in retina image or not. The algorithm efficiently detect the different regions of the vessels and other components of damaged retina and classify the images are normal or not according to severity of OD ratio. The methods produce more than 85' of accuracy for classification of diseases for datasets as DRIVE, DIARECT DB0-2. The performance parameters like sensitivity, precision are also gives more than 80 percent accuracy for our proposed approach.
Inspec keywords: edge detection; learning (artificial intelligence); eye; image segmentation; diseases; blood vessels; medical image processing; image classification; support vector machines; image colour analysis; biomedical optical imaging
Subjects: Support vector machines; Anatomy and optics of the eye; Image recognition; Optical and laser radiation (medical uses); Computer vision and image processing techniques; Biology and medical computing; Neural nets; Optical and laser radiation (biomedical imaging/measurement); Patient diagnostic methods and instrumentation