A.S.Jadhav and Pushpa B Pati

Retina images are obtained from the fundus camera and graded by skilled professionals. However there is considerable shortage of expert observers has encouraged computer assisted monitoring. Evaluation of blood vessels network plays an important task in a variety of medical diagnosis. Manifestations of numerous vascular disorders, such as diabetic retinopathy, depend on detection of the blood vessels network. In this work the fundus RGB image is used for obtaining the traces of blood vessels and areas of blood vessels are used for detection of Diabetic Retinopathy (DR). The algorithm developed uses morphological operation to extract blood vessels. Mainly two steps are used: firstly enhancement operation is applied to original retina image to remove noise and increase contrast of retinal blood vessels. Secondly morphology operations are used to take out blood vessels. Experiments are conducted on publicly available DIARETDB1 database. Experimental results obtained by using gray-scale images have been presented.

Blood Vessels, Fundus Images, Morphological operations.