Special Issue on 2 nd International Conference on Electronics & Computing Technologies-2015 Conference Held at K.C. College of Engineering & Management Studies & Research, Maharashtra, India Biometric Security Systems Based on Eye Veins

Retinal images play vital role inseveral applications such as disease diagnosis and human recognition. They also play a major role in early detection of diabetics by comparing the states of the retinal blood vessels. The detection of blood vessels from the retinal images is a tedious process. In this work a new algorithm to detect the blood vessels effectively has been proposed. Initially enhancement of the image is carried out using curve let transform and modification of the curve let coefficients. Since the blood vessels are distributed in various directions, morphology processing with multidirectional structuring elements are used to extract the blood vessel from the retinal images. Afterwards, morphological operator by reconstruction using multistructure elements eliminates the ridgesnot belonging to the vessel tree. A simple thresholding along with connected component analysis (CCA) indicates the remained ridges belonging to vessel tree. Finally applying length filter on the connected components all residual ridges are refined from the images. Experimental results show that the blood vessels are extracted from the retinal images with better PSNR and 96% accuracy than enhancement using other techniques.