Robustness of biometric gait authentication against impersonation attack

  • Authors:
  • Davrondzhon Gafurov;Einar Snekkenes;Tor Erik Buvarp

  • Affiliations:
  • Norwegian Information Security Lab, Department of Computer Science and Media Technology, Gjovik University College, Gjovik, Norway;Norwegian Information Security Lab, Department of Computer Science and Media Technology, Gjovik University College, Gjovik, Norway;Norwegian Information Security Lab, Department of Computer Science and Media Technology, Gjovik University College, Gjovik, Norway

  • Venue:
  • OTM'06 Proceedings of the 2006 international conference on On the Move to Meaningful Internet Systems: AWeSOMe, CAMS, COMINF, IS, KSinBIT, MIOS-CIAO, MONET - Volume Part I
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a gait authentication based on time-normalized gait cycles Unlike most of the previous works in gait recognition, using machine vision techniques, in our approach gait patterns are obtained from a physical sensor attached to the hip Acceleration in 3 directions: up-down, forward-backward and sideways of the hip movement, which is obtained by the sensor, is used for authentication Furthermore, we also present a study on the security strength of gait biometric against imitating or mimicking attacks, which has not been addressed in biometric gait recognition so far.