Facial Color Image Analysis and Synthesis for the Virtual Face Image in Emotional Change.

Abstract

Human facil color can be applied to the display of virtual face image, emotional evaluation, individual identification, and remote health care. We already developed a method for emphasizing the individual characteristics in facial color based on a virtual face image using the HSV (hue, saturation, value) color space. To make virtual face images more natural and richer, the clarification of the relation between facial color and emotion would be expected. In this paper, we propose a synthetic method for the virtual face image based on the analysis of facial color in emotional change. First, the facial colors under the emotion of joy or anger are determined quantitatively by using the HSV color space. Secondly, we examined the relation between the facial color and the physiological index of facial skin temperature, which indicates the change of blood flux, in drinking for the emotion of joy. Also, we examined the relation between the change of facial color and that of skin temperature under the joy in laughing. Finally, on the basis of these results, we synthesized seven enhanced facial color images based on an average facial color image from 68 females, and evaluated the effectiveness of these images through sensory evaluation by paired comparison.