Efficient Fingerprint Recognition System using Pseudo 2D Hidden Markov Model
Parvathi R1, Shanthi Saravanan D2
1Parvathi R, Assistant Professor, Department of Information Technology, PSNA College of Engineering and Technology, Dindigul.
2Shanthi Saravanan D, Professor, Department of Computer Science and Engineering, PSNA College of Engineering and Technology, Dindigul.
Manuscript received on June 03, 2013. | Revised Manuscript received on June 29, 2013. | Manuscript published on July 05, 2013. | PP: 169-173 | Volume-3 Issue-3, July 2013. | Retrieval Number: C1689073313/2013©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: Fingerprint can only uniquely identify a person when compared to other types of biometric features. The existing system used the combination of bayes classifier and Henry classifier to increase the speed of authentication process and to provide accurate classification system respectively. But, the combination of those classifiers in real time systems becomes difficult to implement. This fingerprint recognition system uses the pseudo 2D hidden markov model which considers each types of fingerprint as separate states with different levels of markov chain. During the recognition process, the markov model verifies each super states to identify which types of fingerprint, then it can match the given fingerprint image with the image which are kept in database. The proposed work will improve the speed and recognition rate by using the pseudo 2D hidden markov model.
Keywords: Fingerprint recognition, hidden markov model, viterbi algorithm, fingerprint classification.