Class-Specific Kernel Fusion of Multiple Descriptors for Face Verification Using Multiscale Binarised Statistical Image Features
- Submitting institution
-
The University of Surrey
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9000586_3
- Type
- D - Journal article
- DOI
-
10.1109/TIFS.2014.2359587
- Title of journal
- IEEE Transactions on Information Forensics and Security
- Article number
- -
- First page
- 2100
- Volume
- 9
- Issue
- 12
- ISSN
- 1556-6013
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- Year of publication
- 2014
- 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
-
-
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The method pioneered a new approach to face recognition by conducting deformable image-to-image matching based on an MRF model to handle pose induced geometric distortion of face appearance. It defined the state of the art in 2014 by achieving top ranking face recognition performance as measured on the Labelled-Faces-in-the-Wild benchmarking dataset. It provided an underpinning approach for the £6m EPSRC Programme Grant (2016-2021) for research in unconstrained face recognition that has delivered world leading face recognition technology, e.g.10.1109/TBIOM.2020.3007356, for use in security systems, digital economy and for access control in smart cities.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
