An Efficient Person Authentication method based on the Extraction of Retinal Bifurcations

An efficient method for person authentication based on the retinal blood vessel pattern is presented in this paper. The method initially involves a segmentation process to identify blood vessel intersection points in the retina, then the generation of template consisting of the bifurcation points in the blood vessels and finally matching of the intersection points in two different patterns. This approach differs from previously known methods, in that it uses a retinal minucode centered feature extraction algorithm based on the bifurcation points present in retina. Then the number of matched blood vessel intersection points between the two patterns is used to quantify the degree of matching. The validity of our approach is verified with the experimental results obtained using the publicly available databases, namely DRIVE and STARE. We found that the proposed retinal recognition method gives 100% and 90.1% recognition rates respectively for the above databases.