A study on evaluating the uniqueness of fingerprints using statistical analysis

Authors:
Y. Han;C. Ryu;J. Moon;H. Kim;H. Choi
Affiliations:
School of Information and Communication Eng., Inha University, Incheon, Korea;School of Information and Communication Eng., Inha University, Incheon, Korea;School of Information and Communication Eng., Inha University, Incheon, Korea;School of Information and Communication Eng., Inha University, Incheon, Korea;Dept. of Information Eng., Myongji University, Kyungkido, Korea
Venue:
ICISC'04 Proceedings of the 7th international conference on Information Security and Cryptology
Year:
2004

Citing 2
Cited 0

Twin Test: On Discriminability of Fingerprints

AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
A fast fingerprint matching algorithm using Parzen density estimation

ICISC'02 Proceedings of the 5th international conference on Information security and cryptology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Biometrics-based methods for personal authentication assume that the biometric characteristics used for the verification of an individual’s identity are unique from person to person. The purpose of this study is to verify the uniqueness of fingerprints, by analyzing the similarity of live-scanned fingerprints for all ten fingers of twins and family members. In order to maintain the consistency and to guarantee the repeatability of the analysis, we established an evaluation framework, and studied the uniqueness of fingerprints from two points of view, namely the similarity between fingerprint types and the distribution of the similarity scores produced by a minutia-based matching algorithm. Preliminary experiments were carried out using the live-scanned ten-finger fingerprints of sixty-six twins and fifty-two families consisting of the parents and two children. The results demonstrate that fingerprints are sufficiently unique to distinguish one person from another, with an insignificant decrease in the recognition accuracy for identical twins.