Ali, Asad, Deravi, Farzin, Hoque, Sanaul (2013) Directional Sensitivity of Gaze-Collinearity Features in Liveness Detection. In: Emerging Security Technologies (EST), 2013 Fourth International Conference on, 9-11 September 2013, Cambridge, England. (doi:10.1109/EST.2013.7) (KAR id:43220)
PDF
Author's Accepted Manuscript
Language: English |
|
Download this file (PDF/326kB) |
![]() |
Request a format suitable for use with assistive technology e.g. a screenreader | |
Official URL: http://dx.doi.org/10.1109/EST.2013.7 |
Abstract
To increase the trust in using face recognition systems, these need to be capable of differentiating between face images captured from a real person and those captured from photos or similar artifacts presented at the sensor. Methods have been published for face liveness detection by measuring the gaze of a user while the user tracks an object on the screen, which appears at pre-defined, places randomly. In this paper we explore the sensitivity of such a system to different stimulus alignments. The aim is to establish whether there is such sensitivity and if so to explore how this may be exploited for improving the design of the stimulus. The results suggest that collecting feature points along the horizontal direction is more effective than the vertical direction for liveness detection.
Item Type: | Conference or workshop item (Paper) |
---|---|
DOI/Identification number: | 10.1109/EST.2013.7 |
Subjects: | T Technology |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts |
Depositing User: | Tina Thompson |
Date Deposited: | 08 Oct 2014 09:43 UTC |
Last Modified: | 16 Nov 2021 10:17 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/43220 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):