Canonical Correlation Analysis For Long-Term Changes Of Facial Images Based On The Frequency Of Uv Protection, Physical And Psychological Features

In this paper, we analyze the relationship between impression of facial skin and skin component distribution by applying canonical coefficient analysis (CCA) to multiple physical and psychological features obtained from facial images. Based on the acquired relationship, we modulate the skin pigment features, and appearances of the face with arbitrary psychological features are reproduced. In our previous work, we applied principal component analysis (PCA) to the melanin pigment variation of the facial skin, and we obtained individual differences in it occurring over 7 years. In the previous method, as the factor causing individual difference, we considered the frequency of UV protection. However, actual skin appearance is thought to depend not only on melanin but also on several other factors. Therefore, in this study, we captured facial images of females aged from 10s to 80s at intervals of 12 years, and we obtained not only physical but also psychological features. As physical features, melanin and hemoglobin pigment and shading distributions, and the frequency of UV protection for 12 years were obtained. Psychological feature values were acquired as subjective evaluation. As a result of CCA on the physical features only, it was found that the whole face can be made lighter in appearance by performing UV protection every day continuously for 6 years or more. As a result on both physical and psychological features, pigment features greatly affecting the impression of the skin and multiple skin aging patterns were obtained. According to this result, the pigment features were modulated, and facial appearances with arbitrary psychological features were reproduced. (C) 2019 Society for Imaging Science and Technology.