Fingerprint Authentication System using Hybrid Classifiers
Parvathi R1, Sankar M2
1Parvathi R, Assistant Professor, Department of Information Technology, PSNA College of Engineering and Technology, Dindigul,Tamilnadu, India
2Sankar M, Assistant Professor,Department of Electrical and Electronics Engineering,RVS College of Engineering and Technology, Dindigul, Tamilnadu, India.
Manuscript received on July 01, 2012. | Revised Manuscript received on July 04, 2012. | Manuscript published on July 05, 2012. | PP: 185-190 | Volume-2, Issue-3, July 2012. | Retrieval Number: C0752062312/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Fingerprints are considered as the most widely accepted biometric feature for uniquely identify a person in the field of biometrics. The existing system only contains bayes classifier to improve the retrieval speed and to perform one to many fingerprint matching. When compared to proposed system, the previous work degrades with performance features like accuracy, consistency and retrieval speed. This fingerprint authentication system uses the combination of Henry classification system at enrollment process and Bayes classification system at authentication process. This paper mainly focuses on fingerprint classification and presents an approach to speed up the matching process by classifying the fingerprint pattern into different groups using Henry classification system. By the speed of Bayes classifier, this system does not depend on the huge amount of fingerprint images in database, one can capture large number of training samples per finger. It can improve the performance features like retrieval speed, consistency and accuracy by using the combination of classifiers.
Keywords: Biometrics, fingerprint authentication, Henry classification, Bayes classifier, probabilistic recognition.