Analysis and Synthesis of Facial Color Using Color Image Processing

Abstract

The natural color of five representative areas of the human face, the lip, brow, nose, left cheek and right cheek, is analyzed using the HSV(hue, saturation, value)color space that is fitted with human color sense.From the relationships among the HSV parameters for these areas, it is found that the hue of lip is not correlated with that of the other areas.This suggests that the hue of the lip in a virtual facial image can be treated independently from other facial colors.A virtual facial color image is synthesized using the average facial color in HSV color space determined from 64 males.On the basis of the difference in color of each pixel between the average facial image and the individual one, a method for emphasizing the individual characteristics in facial color is proposed.The effectiveness of the method is demonstrated through sensory evaluation by paired comparisons of enhanced virtual facial images.