Improvement of the Mouth Part Extraction in Facial Caricaturing System PICASSO-2

We exhibited a facial caricaturing robot fabricated by means of PICASSO-2 system at Aichi EXPO2005. This system takes a couple of facial images with CCD camera, extracts the facial features from the images, and generates the facial caricature. We conducted an experimental evaluation of the quality of the face recognition based on the EXPO field test, (it was clarified that the detection of mouth outline are extremely poor in performance.) In this paper, we proposed an improved method for mouth outline recognition by using CIE L*a*b* color space. As a result, we showed experimentally that the outline of the lip was smoothly recognized in this paper.