An assessment of the human performance of iris identification
An assessment of the human performance of iris identification
Biometric iris recognition systems are widely used for a range of identity recognition applications and have been shown to perform with high accuracy. For large-scale deployments, however, system enhancements leading to a reduction in error rates are continually sought. In this paper we investigate the performance of human verification of iris images and compare against a standard computer-based method. Our results suggest that performance using the computer-based system is no better than performance of the human participants. Additionally and importantly, however, performance can be improved through incorporation of the human as a `second decision maker'. This fusion system yields a false acceptance rate of just 9% when disagreements are resolved in line with strengths of each `decision-maker'. The results are presented as an illustration of the benefits that can be gained when combining human and automated systems in biometric processing.
978-1-4799-3963-3
623-626
Guest, Richard M
93533dbd-b101-491b-83cc-39ccfdc18165
He, Hongmei
8b11615a-058c-4ca3-b68f-d63790e0cc85
Stevenage, Sarah V.
493f8c57-9af9-4783-b189-e06b8e958460
Neil, Greg J.
85453750-0611-48d9-a83e-da95cd4e80b3
Guest, Richard M
93533dbd-b101-491b-83cc-39ccfdc18165
He, Hongmei
8b11615a-058c-4ca3-b68f-d63790e0cc85
Stevenage, Sarah V.
493f8c57-9af9-4783-b189-e06b8e958460
Neil, Greg J.
85453750-0611-48d9-a83e-da95cd4e80b3
Guest, Richard M, He, Hongmei, Stevenage, Sarah V. and Neil, Greg J.
(2013)
An assessment of the human performance of iris identification.
2013 IEEE International Conference on Technologies for Homeland Security (HST), United States, United States.
12 - 14 Nov 2013.
.
(doi:10.1109/THS.2013.6699076).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Biometric iris recognition systems are widely used for a range of identity recognition applications and have been shown to perform with high accuracy. For large-scale deployments, however, system enhancements leading to a reduction in error rates are continually sought. In this paper we investigate the performance of human verification of iris images and compare against a standard computer-based method. Our results suggest that performance using the computer-based system is no better than performance of the human participants. Additionally and importantly, however, performance can be improved through incorporation of the human as a `second decision maker'. This fusion system yields a false acceptance rate of just 9% when disagreements are resolved in line with strengths of each `decision-maker'. The results are presented as an illustration of the benefits that can be gained when combining human and automated systems in biometric processing.
Text
Guest et al HST 2013 Human computer iris matching.doc
- Accepted Manuscript
More information
e-pub ahead of print date: November 2013
Venue - Dates:
2013 IEEE International Conference on Technologies for Homeland Security (HST), United States, United States, 2013-11-12 - 2013-11-14
Organisations:
Psychology
Identifiers
Local EPrints ID: 374181
URI: http://eprints.soton.ac.uk/id/eprint/374181
ISBN: 978-1-4799-3963-3
PURE UUID: 5d0f2499-b939-40e2-b942-160d479d1013
Catalogue record
Date deposited: 10 Feb 2015 11:29
Last modified: 24 Apr 2024 02:10
Export record
Altmetrics
Contributors
Author:
Richard M Guest
Author:
Hongmei He
Author:
Greg J. Neil
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