Fingerprint Recognition on Various Authentication Sensors

Fingerprint is a very popular and an ancient biometric technology to uniquely identify a person. In this paper, a fingerprint matcher is proposed which uses the global and local adaptive binarization and global minutia features. The fingerprint data is collected using three different authentication devices based on optical sensors. The experimental results are compared with the National Institute of Standards and Technology (NIST) Bozorth algorithm and various authentication fingerprint sensors. The accuracy of the proposed algorithm has been improved significantly compared with that of the NIST Bozorth algorithm.