International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 3 Issue: 3 927 - 930 _______________________________________________________________________________________________ 927 IJRITCC | March 2015, Available @ http://www.ijritcc.org _______________________________________________________________________________________ Retinal Blood Vessel Segmentation Algorithm for Diabetic Retinopathy using Wavelet: A Survey Chandani Nayak M.Tech Scholar(Digital Electronics) RCET Bhilai, CSVTU Bhilai, India Chandni.nayak90@gmail.com Ms. Lakhwinder Kaur Reader, ECE Department RCET Bhilai, CSVTU Bhilai, India Lakhwinder20063@gmail.com Mrs. Smriti Kumar Asst. Professor, ECE Department RCET Bhilai, CSVTU Bhilai, India sksmriti@yahoo.com Abstract—Blood vessel structure in retinal images have an important role in diagnosis of diabetic retinopathy. There are several method present for automatic retinal vessel segmentation. For developing retinal screening systems blood vessel segmentation is the basic foundation since vessels serve as one of the main retinal landmark features. The most common signs of diabetic retinopathy include hemorrhages, cotton wool spots, dilated retinal veins, and hard exudates. A patient with diabetic retinopathy disease has to undergo periodic screening of eye. For the diagnosis, doctors use color retinal images of a patient required from digital fundus camera. We present a method that uses Gabor wavelet for vessel enhancement due to their ability to enhance directional structures and euclidean distance technique for accurate vessel segmentation. Retinal angiography images are mainly used in the diagnosis of diseases such as diabetic retinopathy and hypertension etc. In diabetic retinopathy structure of retinal blood vessels change that leads to adult blindness. To overcome this problem automatic biomedical diagnosis system is required. The main stage of diabetic retinopathy are Non-proliferative diabetic retinopathy (NPDR) and proliferative diabetic retinopathy (PDR). Eye care specialist can screen vessel abnormalities using an efficient and effective computer based approach to the automated segmentation of blood vessels in retinal images. Automated segmentation reduces the time required by a physician or a skilled technician for manual labeling. Thus a reliable method of vessel segmentation would be valuable for the early detection and characterization of changes due to such diseases. This article presents the automated vessel enhancement and segmentation technique for colored retinal images. Segmentation of blood vessels from image is a difficult task due to thin vessels and low contrast between vessel edges and background. The proposed method enhances the vascular pattern using Gabor wavelet and then it uses euclidean distance technique to generate gray level segmented image. Keywords-Diabetic Retinopathy, Retinal Blood Vessel, Segmentation, Wavelet. __________________________________________________*****_________________________________________________ I. INTRODUCTION One of the most important diseases that causes blood vessels structure to change is diabetic retinopathy that leads to adults blindness. Diabetic affects almost 31.7 million Indian, and has associated complications such as vision loss, heart failure and stroke. Diabetic disease which occurs when the pancreas does not secrete enough insulin or the body is unable to process it properly. This disease affects slowly the circulatory system including that of the retina. As diabetes progresses, the vision of a patient may start to deteriorate and lead to diabetic retinopathy. Diabetic retinopathy (DR) is a common cause of blindness among the diabetic population. Despite various advances in diabetes care over the years, loss of vision is still a potentially devastating complication in people with diabetes. The risk of severe vision loss can be reduced significantly by timely diagnosis and treatment of DR. Blood vessel structure in retinal images have an important role in diagnosis of diabetic retinopathy. There are several method present for automatic retinal vessel segmentation. For developing retinal screening systems blood vessel segmentation is the basic foundation since vessels serve as one of the main retinal landmark features. The most common signs of diabetic retinopathy include hemorrhages, cotton wool spots, dilated retinal veins, and hard exudates. A patient with diabetic retinopathy disease has to undergo periodic screening of eye. For the diagnosis, doctors use color retinal images of a patient required from digital fundus camera. We present a method that uses gabor wavelet for vessel enhancement due to their ability to enhance directional structures and euclidean distance technique for accurate vessel segmentation. Figure1.1 Difference between normal and diabetic retina