Emotion recognition: The role of facial movement and the relative importance of upper and lower areas of the face.

Abstract

In order to investigate the role of facial movement in the recognition of emotions, faces were covered with black makeup and white spots. Video recordings of such faces were played back so that only the white spots were visible. The results demonstrated that moving displays of happiness, sadness, fear, surprise, anger and disgust were recognized more accurately than static displays of the white spots at the apex of the expressions. This indicated that facial motion, in the absence of information about the shape and position of facial features, is informative about these basic emotions. Normally illuminated dynamic displays of these expressions, however, were recognized more accurately than displays of moving spots. The relative effectiveness of upper and lower facial areas for the recognition of these six emotions was also investigated using normally illuminated and spots-only displays. In both instances the results indicated that different facial regions are more informative for different emitions. The movement patterns characterizing the various emotional expressions as well as common confusions between emotions are also discussed.

Cites (1)

1. Facial action coding system
   Ekman, Paul, Friesen, Wallace V. · 2019 · PsycTESTS Dataset

Show all 1 references

Cited by (26)

1. Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions
   Zhao, Guoying, Pietikainen, Matti · 2007 · IEEE Transactions on Pattern Analysis and Machine Intelligence
2. Emotion recognition in human-computer interaction
   Cowie, R., Douglas-Cowie, E., Tsapatsoulis, N., Votsis, G., Kollias, S., Fellenz, W., Taylor, J.G. · 2001 · IEEE Signal Processing Magazine
3. Toward machine emotional intelligence: analysis of affective physiological state
   Picard, R.W., Vyzas, E., Healey, J. · 2001 · IEEE Transactions on Pattern Analysis and Machine Intelligence
4. Facial expression recognition based on Local Binary Patterns: A comprehensive study
   Shan, Caifeng, Gong, Shaogang, McOwan, Peter W. · 2009 · Image and Vision Computing
5. Emotional expressions reconsidered: Challenges to inferring emotion from human facial movements
   Barrett, Lisa Feldman, Adolphs, Ralph, Marsella, Stacy, Martinez, Aleix M., Pollak, Seth D. · 2019 · Psychological Science in the Public Interest

See all 653