2014 Volume 20 Issue 1 Pages 59-64
Facial expression recognition for emotional communication between humans and machines has been investigated in recent studies. Previously, we proposed a method for generating a person-specific emotional feature space using self-organizing maps and counter propagation networks (CPN). The feature space expresses the correspondence between the changes in facial expression patterns and the degree of emotions in a two-dimensional space centered on "pleasantness" and "arousal." In this study, we investigated the number of dimensions and the size of the CPN mapping space for generating a facial expression feature space that allows detailed emotion quantification.
