TY - GEN
T1 - A robust feature selection method for noncontact biometrics based on laser doppler vibrometry
AU - Lai, Po Hsiang
AU - O'Sullivan, Joseph A.
AU - Chen, Mei
AU - Sirevaag, Erik J.
AU - Kaplan, Alan D.
AU - Rohrbaugh, John W.
PY - 2008
Y1 - 2008
N2 - We propose a new biometric approach based on cardiovascular signals recorded using Laser Doppler Vibrometry (LDV) with a robust feature selection method. A novel feature selection method provides robustness against physiological variability of a given individual. LDV signals were collected from 191 individuals under controlled conditions during three sessions, each at intervals of one week to six months. The methods described here are based on a time-frequency decomposition of the LDV signal in which the log-power of the decomposition values are used as features. In identity verification tasks, equal error rates in the single digits can be achieved with testing periods as short as 4 s.
AB - We propose a new biometric approach based on cardiovascular signals recorded using Laser Doppler Vibrometry (LDV) with a robust feature selection method. A novel feature selection method provides robustness against physiological variability of a given individual. LDV signals were collected from 191 individuals under controlled conditions during three sessions, each at intervals of one week to six months. The methods described here are based on a time-frequency decomposition of the LDV signal in which the log-power of the decomposition values are used as features. In identity verification tasks, equal error rates in the single digits can be achieved with testing periods as short as 4 s.
UR - https://www.scopus.com/pages/publications/56749105628
U2 - 10.1109/BSYM.2008.4655524
DO - 10.1109/BSYM.2008.4655524
M3 - Conference contribution
AN - SCOPUS:56749105628
SN - 9781424425679
T3 - 2008 Biometrics Symposium, BSYM
SP - 65
EP - 70
BT - 2008 Biometrics Symposium, BSYM
T2 - 2008 Biometrics Symposium, BSYM
Y2 - 23 September 2008 through 25 September 2008
ER -