From clothing to identity; manual and automatic soft biometrics
- Submitting institution
-
University of Southampton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 17202294
- Type
- D - Journal article
- DOI
-
10.1109/TIFS.2016.2584001
- Title of journal
- IEEE Transactions on Information Forensics and Security
- Article number
- 7498567
- First page
- 2377
- Volume
- 11
- Issue
- 10
- ISSN
- 1556-6013
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2016
- URL
-
-
- 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
-
1
- Research group(s)
-
-
- Citation count
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Prior to this work, no-one had used clothing for automated identification. It adds a devastating cannon to the array of biometrics for identification, since clothing is very diverse and has high invariant characteristics (unlike the face), and earlier shown in spoofing analysis on Discovery’s Planet Earth https://www.sciencedirect.com/science/article/pii/S0969476511701254 . As described in the BIOSIG 2017 keynote https://fg-biosig.gi.de/veranstaltung/biosig-2017 it is implicitly short term since clothes are easily changed. The labels were developed from our early comparative ones in IEEE TPAMI, 36(6), pp.1216-1228 https://ieeexplore.ieee.org/abstract/document/6654143.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -