Vessels Extraction from Retinal Images

Abstract

The main cause of eye diseases in the working human is Diabetic retinopathy. Eye disease can be prevented if detects early. The extraction of blood vessels from retinal images is an essential and challenging task in medical diagnosis and analysis. This paper describes the effective and efficient extraction of blood vessels from retinal image by using Kirsch's templates. The Kirsch's edge operators detect the edges using eight filters, generated by the compass rotation mechanism. The method is used to automatic detection of landmark features of the fundus, such as the optic disc, fovea and blood vessels. I. Introduction The extraction of Retinal blood vessel is an essential step for the diagnosis of various eye diseases. Retinal images of humans play a crucial role in the detection and diagnosis of several eye diseases for the oculists (1-2). Color retinal images are used in mass screen systemic diseases such as Diabetic Retinopathy (DR). The risk of the Diabetic Retinopa-thy increases with age and small eye blood vessels damaged the due to this disease. The information about blood vessels, such as length, width, diameter and branching pattern, can help to diagnose the symptom of diseases (3-4). The oculists may examine retinal images and give the diagnostic results by searching the possible anomalies like diabetic retinopathy, glaucoma and retinal artery occlusion. With the help of computer aided diagnosis (CAD), the success rate of the treatment of these diseases may increase significantly. If the retinopathy detects in early stage (5-6), the probability of visual loss resulting from diabetic retinopathy can be prevented. The filtering based method which is used for the effective extraction the blood vessels of retinal images are described in (7-8). In the past various techniques are used to extract the blood vessels from retinal images. One technique not only finds the blood vessels that originate from a set of primary starting point but also finds all branches off of the primary vessels. The second method use Matched Filter (MF) for the extraction of blood vessels. This method will respond not only to vessels but also to non-vessel edges (9). The third method is the novel hybrid automatic approach for the extraction of retinal image vessels which reduce the weak edges and noise, and finally results the blood vessels extraction. In this paper a method is proposed which uses the Kirsch's templates for the extraction of the blood vessels from retinal images. The rest of paper is organized into 5 Sections. The Kirsch's edge operators are described in Section 2. Section 3 explains proposed method for the extraction of blood vessels from retinal images. Section 4 shows the results and discussion and finally, the conclusion is given in Section 5.