A study on multi-unit fingerprint verification

Authors:
Kangrok Lee;Kang Ryoung Park;Jain Jang;Sanghoon Lee;Jaihie Kim
Affiliations:
Biometrics Engineering Research Center(BERC), Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea;Biometrics Engineering Research Center(BERC), Division of Media Technology, Sangmyung University, Seoul, Korea;Biometrics Engineering Research Center(BERC), Division of Computer and Information Engineering, Yonsei University, SEOUL, Korea;Biometrics Engineering Research Center(BERC), Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea;Biometrics Engineering Research Center(BERC), Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea
Venue:
AVBPA'05 Proceedings of the 5th international conference on Audio- and Video-Based Biometric Person Authentication
Year:
2005

Citing 5
Cited 0

On-Line Fingerprint Verification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Integrating Faces and Fingerprints for Personal Identification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Expert Conciliation for Multi Modal Person Authentication Systems by Bayesian Statistics

AVBPA '97 Proceedings of the First International Conference on Audio- and Video-Based Biometric Person Authentication
Algorithm for Detection and Elimination of False Minutiae in Fingerprint Images

AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
A Robust Fingerprint Matching Algorithm Using Local Alignment

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3

Quantified Score

Hi-index	0.00

Visualization

Abstract

Previous fingerprint verification systems have achieved good results, but these have been affected by the quality of input data. Fingerprint verification systems that use many fingers or multiple impressions of the same finger are more efficient and reliable than systems that use a single finger. However, multiple impressions give inconvenience to the user and increase the overall verification time. Therefore, we use only two fingers (multi-unit fusion) to improve performance of the fingerprint verification system. We show that performance can be improved by selecting a better quality fingerprint image of two fingerprints. Also, we propose a new quality checking algorithm composed of three stages. Our experimental results show that when the quality checking algorithm is performed by selecting a better quality fingerprint image of two fingerprints, there is a significance improvement in performance of the fingerprint verification system.