Extracting subtle facial expression for emotional analysis

Humans convey emotions with subtle facial expressions. The interpretation of these expressions not only depends on that expression, but on how it developed. Exposing this development enables a better analysis of the ambiguity experienced when analyzing the underlying emotion. Subtle facial expressions can be objectively measured in terms of action units as defined in the facial action coding system. This paper presents a facial expression language based on FACS which provides a continues stream of expressions for measuring the growth of expression. The development of the emotion surprise which requires two action units is used as a test case