Is 2D Unlabeled Data Adequate for Recognizing Facial Expressions?
- Submitting institution
-
University of Central Lancashire
- Unit of assessment
- 12 - Engineering
- Output identifier
- 14174
- Type
- D - Journal article
- DOI
-
10.1109/MIS.2016.25
- Title of journal
- IEEE Intelligent Systems
- Article number
- -
- First page
- 19
- Volume
- 31
- Issue
- 3
- ISSN
- 1541-1672
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- 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)
-
H - Computer Vision and Machine Learning Group
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper investigates significance of data representation methodologies on analysis of facial expressions. It demonstrates that it is possible to achieve a suitable recognition accuracy using only simple 2D landmark features, making it feasible for implementation on low-cost portable devices. The reported research contributed to an FP7 €5,383,126 project, Semeiotic Oriented Technology for Cardiometabolic Self-Assessment and Self-monitoring, in collaboration with 9 European institutions. Most recently, it has been also instrumental in setting up collaboration between UCLan and the East Lancashire NHS Hospitals Trust in investigation of facial features for identifying patients’ state in a hospital environment.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
