In this paper, we apply principal component analysis to pigmentation distribution in whole face and obtain feature values. Furthermore, we estimate the relationship between the obtained vectors and the ages and simulate the changes of women facial image from in her 20s to in her any age by multiple regression analysis. Human faces is the well-known part which receive a lot of attention in the body. Changing the small quantity of the features in faces make large differences in their appearance. The features which we can receive divide broadly into two categories. One is the physical feature such as skin condition and its shape, and another one is the psychological features such as the ages and the health. In the beauty industry it is required to synthesize the skin texture based on the two kinds of the feature values. Previous works remain in the analysis of the skin texture using small area. By morphing shape of facial images to that of average face and extending the analyzed area to whole face, our method can analyze pigmentation distribution in whole face and simulate appearance of face by changing the age.
Saori Toyota, Izumi Fujiwara, Misa Hirose, Nobutoshi Ojima, Keiko Ogawa-Ochiai, Norimichi Tsumura, "Principal component analysis for pigmentation distribution in whole facial image and prediction of the facial image in various ages" in Proc. IS&T 21st Color and Imaging Conf., 2013, pp 148 - 153, https://doi.org/10.2352/CIC.2013.21.1.art00026