Principal component analysis for surface reflection components and structure in the facial image and synthesis of the facial image in various ages

In this paper, principal component analysis is applied to pigmentation distributions, surface reflectance components and facial landmarks in the whole facial images to obtain feature values. Furthermore, the relationship between the obtained feature vectors and age is estimated by multiple regression analysis to modulate facial images in woman of ages 10 to 70. In our previous work, we analyzed only pigmentation distributions and the reproduced images looked younger than the reproduced age by the subjective evaluation. We considered that this happened because we did not modulate the facial structures and detailed surfaces such as wrinkles. By analyzing landmarks represented facial structures and surface reflectance components, we analyzed the variation of facial structures and fine asperity distributions as well as pigmentation distributions in the whole face. As a result, our method modulate the appearance of a face by changing age more appropriately.