Development of the RIKEN database for dynamic facial expressions with multiple angles
Shushi Namba1,2, Wataru Sato3, Saori Namba4
1RIKEN, Psychological Process Research Team, Guardian Robot Project, Kyoto, 6190288, Japan. nashushi@hiroshima-u.ac.jp.
Scientific Reports
|December 8, 2023
Summary
Researchers created a new facial expression database capturing multi-angle and depth information. This resource aids understanding of emotion, facial movements, and internal states for improved sensing systems.
Area of Science:
- Psychology
- Affective Computing
- Cognitive Science
Background:
- Facial expression research spans multiple disciplines.
- Existing facial expression datasets lack multi-angle, depth, and individualized emotional context.
- A comprehensive database is needed to advance sensing technologies and psychological studies.
Purpose of the Study:
- To develop a novel facial expression database incorporating multi-angle and depth information.
- To integrate multiple theoretical perspectives on emotion and individual emotional events.
- To provide a resource for advancing research in affective computing and cognitive science.
Main Methods:
- Collected data from 48 Japanese participants across 25 distinct emotional events.
- Utilized ten Kinect cameras to capture multi-angle and depth information of facial expressions.
- Developed the RIKEN facial expression database.
Main Results:
- Identified several facial patterns associated with emotional valence.
- Findings demonstrated consistency with prior research on facial movements and internal states.
- The database provides rich, multi-dimensional data on emotional expression.
Conclusions:
- The RIKEN facial expression database is a significant advancement for emotion research.
- This resource supports the development of new sensing systems and psychological experiments.
- It offers a deeper understanding of the complexity of human emotional events.
