Human Centric Facial Expression Recognition
- Submitting institution
-
University of Sunderland
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 959
- Type
- E - Conference contribution
- DOI
-
10.14236/ewic/HCI2018.44
- Title of conference / published proceedings
- Proceedings of the BCS Human Computer Interaction Conference
- First page
- 1
- Volume
- 32
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- July
- Year of publication
- 2018
- URL
-
http://sure.sunderland.ac.uk/id/eprint/9584/
- 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
- Yes
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- "
This cross-disciplinary paper explored current understanding of human visual perception to inform and enhance automated facial expression recognition. It incorporated knowledge of both spatial facial feature saliency, and the frequencies at which humans interpret emotions most effectively, into a regional, hierarchical convolutional neural network architecture. The findings have implications for real time processing and affective computing. The second author is now at Heriott Watt (Department of Psychology) and has a funded PhD studentship to continue this research, which has been built on in Turkey (10.1109/TIPTEKNO.2019.8895215), Libya (https://doi.org/10.1186/s42492-019-0034-5) and India (https://doi.org/10.1016/j.jksuci.2018.09.002)."
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -