Retina based Personal Identification System using Skeletonization and Similarity Transformation

摘要

Biometric security has become more important because of the increasing activities of terrorists and hackers. One of the most reliable biometric security systems is retina biometric security system, because no two people have the same retinal pattern. The proposed system consist of four modules viz, retina fundus acquisition, Preprocessing, Detection of bifurcation points and Feature matching. In the preprocessing step retinal blood vessels are enhanced and segmented. From the segmented image bifurcation points are detected, with the help of skeleton process. Using this bifurcation points, it check similarity with bifurcation points of reference images in database using similarity transformation. The proposed system has extremely lower error rate and quick response.