ANALYSIS OF RETINAL BLOOD VESSELS USING IMAGE PROCESSING TECHNIQUES Dr. M.Renuka Devi B.HariniPriyaDharsini Associate professor in MCA Part Time Research Scholar SNS College of technology Bharathiar University Coimbatore. Coimbatore. Abstract —Assessment of blood vessels in human eye allows earlier detection of eye diseases such as glaucoma and diabetic retinopathy. Digital image processing techniques play a vital role in retinal blood vessel detection , Several image processing methods and filters are in practise to detect and extract the attributes of retinal blood vessels such as length ,width, pattern and angles. Automated Digital image processing techniques and methods has to undergo more of improvisation to achieve precise accuracy to study the condition of Retinal Vessels especially in cases of Glaucoma and retinopathy; we have explained various Templates based matched filters, Thresholding Methods, Segmentation methods, and functional approaches to isolate the blood vessels. Keywords— Glaucoma; Retinopathy; Digital Image Processing; Segmentation Methods. I. INTRODUCTION In the past years, many approaches for extracting retinal image vessels have been developed and applied. The matched filter approach is a widely used template-based method, which was firstly proposed by Chaudhuri in the year XXXXXXXXXXand further extended by Hoover in the year 2000. This method usually uses a two-dimensional linear structural element that has a Gaussian cross-profile section, extruded or rotated into three dimensions to identify the cross profile of the blood vessels. The resulted image is finally thresholded to produce a binary segmentation of the vasculature. However, with this method in the detected images, the junction points are not always detected, small vessels are missed and the validity of the detected vessels is not checked. Besides, the threshold selection is also critical. To improve the performance of the conventional matched filter, Rawi in the year 2007 proposed an improved matched filter by using an optimizing procedure to search for the best parameters for the method. Another technique for vessel extraction is the vessel tracking method (in 1999 by Kochner) , in which each vessel segment is defined by three attributes: direction, width, and centre point Thedensity distribution of the cross section of a blood vessel is estimated using a Gaussian shaped function. Individual segments are identified using a search procedure, which keeps track of the Centre of the vessel and makes some decisions about the future path of the vessel based on certain vessel properties. However, the vessel-tracking method requires a user intervention and may be confused by vessel crossing and bifurcations. To deal with the problem of the central light reflex area in the tracking method, Gao in the year 2001 supposed the vessel intensity profiles can be modeled as twin Gaussian functions, and Chutatape in the year 1998 proposed a new method in which the tracking process started from the circumference of the optic disc and applied a Kalman filter as the base to estimate the next search location. Others have proposed the use of pixel classification approaches, which involve two steps. Firstly, a low-level algorithm produces a segmentation of spatially connected regions. These candidate regions are then classified as being vessel or non-vessel. A drawback of these methods is that the large-scale properties of vessels cannot be applied to the classification until the low-level segmentation has already been finished. To overcome the drawback of the pixel classification method, Jorge in 2003 presented a novel way by combining multiscaleanalyzing with supervised classifiers. Recently, some researchers have used neural networks and Knearest neighbour classifiers in vessel segme
ntation through classifying the