Deep face recognition using imperfect facial data
- Submitting institution
-
The University of Bradford
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 27
- Type
- D - Journal article
- DOI
-
10.1016/j.future.2019.04.025
- Title of journal
- Future Generation Computer Systems
- Article number
- -
- First page
- 213
- Volume
- 99
- Issue
- -
- ISSN
- 0167-739X
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2019
- URL
-
https://www.sciencedirect.com/science/article/pii/S0167739X18331133?via%3Dihub
- 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
- 15
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper experimentally quantifies how various parts of the human face responds to the challenge of face recognition using deep learning. This work is significant because it has, for the first time, described a novel framework for building face recognition systems for more accurate face matching tasks, using partial faces. The results of this work have been utilised in many international criminal investigations including the unmasking of the real identities of the suspects in the Salisbury poisoning and the suspects involved in the disappearance of the journalist Jamal Khashoggi at the Saudi Embassy in Turkey.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -