AN AUTHENTICATION SYSTEM USING FINGERPRINT MINUTIAE EXTRACTION AND NEURAL NETWORK

Abstract

Fingerprints have been the mostly used biometrics for human authentication, based on theminutiae or bifurcation. In this paper, the triangle shapes are used to extract features based onminutiae point. The features have been used as a set of descriptors for the fingerprint data. This setof descriptors is fed to the backpropagation neural network for the purpose of fingerprintrecognition. It is found that the process of preprocessing and the method of constructing geometricshapes has great effects on producing good results in the recognition rate.