Learning Bases of Activity for Facial Expression Recognition
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 468
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2017.2662237
- Title of journal
- IEEE TRANSACTIONS ON IMAGE PROCESSING
- Article number
- -
- First page
- 1965
- Volume
- 26
- Issue
- 4
- ISSN
- 1057-7149
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2017
- 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
-
2
- Research group(s)
-
-
- Citation count
- 37
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The first learnt facial expression coding system that is applicable to a wide range of movements (from micro to strong expressions) and is robust to temporal inconsistencies. The intensity of each elementary facial movement is measured by the magnitude of the coefficient of a learnt basis of the dictionary. The system is currently used by psychologists at the Center for Autism Research at the Children?s Hospital of Philadelphia and University of Pennsylvania (contact: Dr. E. Sariyanidi, sariyanide@email.chop.edu) to analyse facial expressions of children with autism spectrum disorder (see https://www.centerforautismresearch.org/).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -