A principal component analysis of facial expressions

Pictures of facial expressions from the Ekman and Friesen set (Ekman, P., F riesen, W. V., (1976). Pictures of facial affect. Pale Alto. California: Co nsulting Psychologists Press) were submitted to a principal component analy sis (PCA) of their pixel intensities. The output of the PCA was submitted t o a series of linear discriminant analyses which revealed three principal f indings: (1) a PCA-based system can support facial expression recognition, (2) continuous two-dimensional models of emotion (e.g. Russell, J. A. (1980 ). A circumplex model of affect. Journal of Personality and Social Psycholo gy, 39, 1161-1178) are reflected in the statistical structure of the Ekman and Friesen facial expressions, and (3) components for coding facial expres sion information are largely different to components for facial identity in formation. The implications for models of face processing are discussed. (C ) 2001 Elsevier Science Ltd. All rights reserved.