A robust feature selection method for noncontact biometrics based on laser doppler vibrometry

  • Po Hsiang Lai
  • , Joseph A. O'Sullivan
  • , Mei Chen
  • , Erik J. Sirevaag
  • , Alan D. Kaplan
  • , John W. Rohrbaugh

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publication2008 Biometrics Symposium, BSYM
Pages65-70
Number of pages6
DOIs
StatePublished - 2008
Event2008 Biometrics Symposium, BSYM - Tampa, FL, United States
Duration: Sep 23 2008Sep 25 2008

Publication series

Name2008 Biometrics Symposium, BSYM

Conference

Conference2008 Biometrics Symposium, BSYM
Country/TerritoryUnited States
CityTampa, FL
Period09/23/0809/25/08

Fingerprint

Dive into the research topics of 'A robust feature selection method for noncontact biometrics based on laser doppler vibrometry'. Together they form a unique fingerprint.

Cite this