Detection of face spoofing using visual dynamics
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 344
- Type
- D - Journal article
- DOI
-
10.1109/TIFS.2015.2406533
- Title of journal
- IEEE Transactions on Information Forensics and Security
- Article number
- -
- First page
- 762
- Volume
- 10
- Issue
- 4
- ISSN
- 1556-6013
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- Year of publication
- 2015
- URL
-
http://eprints.mdx.ac.uk/15313/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 106
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Spoof attacks on facial recognition systems , such as a photograph used to falsely gain access have recently become a severe problem for deep learning. The significance of this paper lies in the fact that it was one of the very first to address this problem, and in its proposal of leveraging the unique characteristics of Dynamic Mode Decomposition (DMD) to do so. DMD had not hitherto been used in machine-learning, but, its ability to encode changing temporal information as a single image with the same dimensions as images contained in video sequences, proved to be suited to the task.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -