Mapping peking opera facial makeup onto a human face image based on facial landmarks

Abstract

Peking Opera facial makeup is a form of art, which is also a form of handicraft art. Mapping Peking Opera facial makeup onto human faces in images could let more people get access to Peking Opera, which is a meaningful way to bring the traditional art into digital world. Some researches built vector-based libraries of the patterns of the facial makeup and covered the facial makeup onto human faces in a vector way. However, their method is difficult to do the points and curves control and is not efficient enough. In this paper, we present a method for mapping the Peking Opera facial makeup onto a frontal human face in an image based on modified Active Shape Model (ASM), Delaunay triangulation and affine transformation. Our approach is tested with different images of human faces and types of facial makeup. The result shows that the facial makeup fits the human face tightly and naturally with eyes and mouth revealed. Comparing with other methods, our method is more efficient and user friendly, which would be beneficial for those who are interested in Peking Opera and it's facial makeup.