A PCA-Based Active Appearance Model for Characterising Modes of Spatiotemporal Variation in Dynamic Facial Behaviours

Watson, David M.; Johnston, Alan

doi:10.3389/fpsyg.2022.880548

A PCA-Based Active Appearance Model for Characterising Modes of Spatiotemporal Variation in Dynamic Facial Behaviours

Watson, David M.; Johnston, Alan

Authors

David M. Watson

ALAN JOHNSTON Alan.Johnston@nottingham.ac.uk
Professor of Psychology

Abstract

Faces carry key personal information about individuals, including cues to their identity, social traits, and emotional state. Much research to date has employed static images of faces taken under tightly controlled conditions yet faces in the real world are dynamic and experienced under ambient conditions. A common approach to studying key dimensions of facial variation is the use of facial caricatures. However, such techniques have again typically relied on static images, and the few examples of dynamic caricatures have relied on animating graphical head models. Here, we present a principal component analysis (PCA)-based active appearance model for capturing patterns of spatiotemporal variation in videos of natural dynamic facial behaviours. We demonstrate how this technique can be applied to generate dynamic anti-caricatures of biological motion patterns in facial behaviours. This technique could be extended to caricaturing other facial dimensions, or to more general analyses of spatiotemporal variations in dynamic faces.

Citation

Watson, D. M., & Johnston, A. (2022). A PCA-Based Active Appearance Model for Characterising Modes of Spatiotemporal Variation in Dynamic Facial Behaviours. Frontiers in Psychology, 13, Article 880548. https://doi.org/10.3389/fpsyg.2022.880548

Journal Article Type	Article
Acceptance Date	Apr 22, 2022
Online Publication Date	May 26, 2022
Publication Date	May 26, 2022
Deposit Date	Jun 1, 2022
Publicly Available Date	Jun 1, 2022
Journal	Frontiers in Psychology
Electronic ISSN	1664-1078
Publisher	Frontiers Media
Peer Reviewed	Peer Reviewed
Volume	13
Article Number	880548
DOI	https://doi.org/10.3389/fpsyg.2022.880548
Keywords	dynamic faces; facial caricaturing; ambient faces; computational neuroscience; face perception
Public URL	https://nottingham-repository.worktribe.com/output/8308791
Publisher URL	https://www.frontiersin.org/articles/10.3389/fpsyg.2022.880548/full