[1675-1680]

Retinal Blood Vessel segmentation is much required for detecting the cardiovascular diseases like ophthalmic pathologies, hypertension etc. The available techniques not having the features like measuring the individual blood vessel length, blood vessel diameter, count of the true blood vessels. This paper presents a new method for identifying the true vessels by segmenting blood vessels in retinal images. The proposed novel technique automatically tracks true vessels from retinal images without the need of user invention and produces the better result for detection of low vision with the help of diameter calculation as well as count of true vessels. Isotropic un-decimated wavelet with threshold based two level decomposition is applied for the image taken from the DRIVE data base for segmentation. The proposed algorithm being simple and easy to implement and the detection of low vision problem is done in a successful manner