Biometric acknowledgment gives a characteristic and solid answer for the issue of individual distinguishing proof. One of the biometric ID framework utilized with high exactness is the retinal verification as a result of its many-sided quality in spoofing. However in these frameworks, acknowledgment rate is enormously influenced by the vasculature multifaceted nature of retinal images. This vascular example turns out to be exceptionally perplexing in sick retinal pictures because of the nearness of obsessive signs. In this manner, we require a computerized productive calculation which can evacuate these abnormalities before matching and decision making. The proposed novel hybrid clustering algorithm Adaptive Weighted Neighbour (AWN) Classification Algorithm classifies the input retinal image based on the features extracted and match the features with the trained features. The proposed feature vector consists of blood vessel structure, bifurcation points, bifurcation angles and vessel width. Results from the AWN are compared with state of the art classifier. It enables high security, good performance and greater accuracy. Also it provides better FAR, FRR and decreases the error rate.
Accurate vessel width measurement from fundus photographs: a new concept.