Classifying Facial Action

The Facial Action Coding System, (FACS), devised by Ekman and Friesen (1978), provides an objective meanS for measuring the facial muscle contractions involved in a facial expression. In this paper, we approach automated facial expression analysis by detecting and classifying facial actions. We generated a database of over 1100 image sequences of 24 subjects performing over 150 distinct facial actions or action combinations. We compare three different ap(cid: 173) proaches to classifying the facial actions in these images: Holistic spatial analysis based on principal components of graylevel images; explicit measurement of local image features such as wrinkles; and template matching with motion flow fields. On a dataset contain(cid: 173) ing six individual actions and 20 subjects, these methods had 89%, 57%, and 85% performances respectively for generalization to novel subjects. When combined, performance improved to 92%.

Authors

• Marian Bartlett
• Paul Viola and Andrew McCallum
• Terrence Sejnowski
• Beatrice Golomb
• Jan Larsen
• Joseph Hager
• Paul Ekman

Keywords

No keywords are indexed for this paper.