The Effect of Time on the Performance of Gait Biometrics
The Effect of Time on the Performance of Gait Biometrics
Many studies have shown that it is possible to recognize people by the way they walk. However, there are a number of covariate factors that affect recognition performance. The time between capturing the gallery and the probe has been reported to affect recognition the most. To date, no study has shown the isolated effect of time, irrespective of other covariates. Here we present the first principled study that examines the effect of elapsed time on gait recognition. Using empirical evidence we have shown for the first time that elapsed time does not affect recognition significantly in the short to medium term. By controlling clothing, a Correct Classification Rate (CCR) of 95% has been achieved over 9 months, on a dataset of nearly 2000 gait sequences/samples. We have created a new multimodal temporal database to enable the research community to investigate various gait and face covariates in a formal manner. Our results show that gait can be used as a reliable biometric over time and at a distance. We have demonstrated that clothing drastically affects performance regardless of elapsed time. A move towards developing appearance invariant recognition algorithms is essential.
Matovski, Darko
33c2d81d-3a4e-4163-814e-513d4f09ae5b
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Mahmoodi, Sasan
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Carter, John
e05be2f9-991d-4476-bb50-ae91606389da
September 2010
Matovski, Darko
33c2d81d-3a4e-4163-814e-513d4f09ae5b
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Mahmoodi, Sasan
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Carter, John
e05be2f9-991d-4476-bb50-ae91606389da
Matovski, Darko, Nixon, Mark, Mahmoodi, Sasan and Carter, John
(2010)
The Effect of Time on the Performance of Gait Biometrics.
IEEE Fourth Conference on Biometrics: Theory, Applications and Systems, Washington DC, United States.
Record type:
Conference or Workshop Item
(Other)
Abstract
Many studies have shown that it is possible to recognize people by the way they walk. However, there are a number of covariate factors that affect recognition performance. The time between capturing the gallery and the probe has been reported to affect recognition the most. To date, no study has shown the isolated effect of time, irrespective of other covariates. Here we present the first principled study that examines the effect of elapsed time on gait recognition. Using empirical evidence we have shown for the first time that elapsed time does not affect recognition significantly in the short to medium term. By controlling clothing, a Correct Classification Rate (CCR) of 95% has been achieved over 9 months, on a dataset of nearly 2000 gait sequences/samples. We have created a new multimodal temporal database to enable the research community to investigate various gait and face covariates in a formal manner. Our results show that gait can be used as a reliable biometric over time and at a distance. We have demonstrated that clothing drastically affects performance regardless of elapsed time. A move towards developing appearance invariant recognition algorithms is essential.
Text
BTAS2010.pdf
- Other
More information
Published date: September 2010
Additional Information:
Event Dates: September
Venue - Dates:
IEEE Fourth Conference on Biometrics: Theory, Applications and Systems, Washington DC, United States, 2010-09-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 271506
URI: http://eprints.soton.ac.uk/id/eprint/271506
PURE UUID: 1ca46608-0989-4c4b-9dc2-eba1f86632ad
Catalogue record
Date deposited: 01 Sep 2010 11:38
Last modified: 15 Mar 2024 02:35
Export record
Contributors
Author:
Darko Matovski
Author:
Sasan Mahmoodi
Author:
John Carter
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
