Abstract-We propose shiny analysis framework accompanied with makeup deterioration using normalized facial images (MaVIC and the corresponding makeup-deteriorated data sets). These images are analyzed and reconstructed based on principal component analysis (PCA) and then the differential ones between the reconstruction images with different numbers of PCA components can be generated. The shiny Eigen-faces contributing to large shiny transition can automatically be selected according to the total variances of the difference images, and then variances of the reconstructed images with only the shiny Eigen-faces can be used as measurement of shine degree. In addition, we execute PCA analysis in several color spaces, and explore the possibility of the color space, which can best manifest the shine existing in the facial images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.