Facial Asymmetry and Emotional Expression

This project is about facial asymmetry, its connection to emotional expression, and methods of measuring facial asymmetry in videos of faces. The research was motivated by two factors: firstly, there was a real opportunity to develop a novel measure of asymmetry that required minimal human involvement and that improved on earlier measures in the literature; and secondly, the study of the relationship between facial asymmetry and emotional expression is both interesting in its own right, and important because it can inform neuropsychological theory and answer open questions concerning emotional processing in the brain. The two aims of the research were: first, to develop an automatic frame-by-frame measure of facial asymmetry in videos of faces that improved on previous measures; and second, to use the measure to analyse the relationship between facial asymmetry and emotional expression, and connect our findings with previous research of the relationship. The project is best described as 80% investigatory and 20% software development. Since submitting the research review, the main accomplishments have been: • the original research review (which forms part of Chapter 2) has been expanded with greater detail on Active Shape Models (Section 2.4.1) and Active Appearance Models (Section 2.4.2) and a new section (2.4.3) on Procrustes analysis. (However, it should be noted that the time spent on Chapter 2 was no greater than 25% of the total time spent on the project.) • two original measures of asymmetry were devised and implemented using an Active Appearance Model library and OpenCV (Sections 3.4.1 and 3.4.2). One of these measures achieved our first aim; i.e., it was automatic and improved on previous measures in the literature. • a measure of left-sided and right-sided facial movement (relative to a neutral face) was devised and implemented (Section 4.3.1) and used as a novel measurement of the strength of a subject's emotional expression. The measure was also used to investigate whether one side of the face moved more than the other during the expression of positive emotions (Section 4.3.2). • the relationship between strength of emotional expression and degree of asymmetry was plotted for subjects expressing laughter and happiness (Figures 4.7 and 4.9). The results gave rise to a hypothesis for future research: that magnitude of facial asymmetry increases with strength of emotional expression , with the increases larger for strong expressions (such as laughter). • a thorough critical evaluation of the project was conducted (Section 5.2) and …