Deep neural network augmentation: generating faces for affect analysis
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1354
- Type
- D - Journal article
- DOI
-
10.1007/s11263-020-01304-3
- Title of journal
- International Journal of Computer Vision
- Article number
- -
- First page
- 1455
- Volume
- 128
- Issue
- 5
- ISSN
- 0920-5691
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2020
- URL
-
http://eprints.mdx.ac.uk/30336/
- 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
-
4
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents a novel approach for synthesizing facial affect either in terms of the six basic expressions (anger, disgust, fear, joy, sadness and surprise), or in terms of valence (positive or negative) and arousal (power of the emotion activation). It is significant because the affect is generated by fitting a 3D Morphable Model on a neutral image, deforming the reconstructed face, adding the inputted affect, and blending the new affect face into the original image. Qualitative experiments illustrate the generation of realistic images as augmented data, leading to improved performance for deep learning networks.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -