What is it about?
Most image databases of facial expressions show only a small subset of expressions, usually the basic emotions (fear, disgust, surprise, happiness, sadness, anger). To overcome these limitations, we introduce an image database of facial expressions reflecting the richness of mental states. 93 expressions of mental states were interpreted by two professional actors, and high-quality pictures were taken under controlled conditions in front and side view. The database was validated in two experiments. Results show a high degree of accuracy human viewers exhibit when identifying complex mental states, even in faces shown in side view, i.e. partially visible facial features. The McGill Face Database provides a wide range of facial expressions that can be linked to mental state terms and can be accurately characterized in terms of arousal and valence.
Featured Image
Photo by Lesly Juarez on Unsplash
Why is it important?
We present a new image database and results from validation experiments that reveal some interesting and novel insights into the high degree of accuracy human viewers exhibit when identifying complex mental states, even from only partially visible facial features. The McGill Face Database provides a wide range of facial expressions that can be linked to mental state terms and can be accurately characterized in terms of arousal and valence.
Perspectives
Developing this database was an unexpected and interesting experience. For instance, the actors were selected via a theatre improvisation performance audition, which I have never seen before. Interestingly, we started with only a couple of facial expressions and ended up with 93, which makes it the largest image database with respect to the number of facial expressions of mental states.
Dr Gunnar Schmidtmann
University of Plymouth
Read the Original
This page is a summary of: The McGill Face Database: Validation and Insights Into the Recognition of Facial Expressions of Complex Mental States, Perception, February 2020, SAGE Publications,
DOI: 10.1177/0301006620901671.
You can read the full text:
Contributors
The following have contributed to this page
