A real-time personalized face modeling method for peking opera with depth vision device. (July 2021)

• Record Type: Journal Article
• Authors: Zhang, Fengquan; Li, Pingzhe; Gao, Yahui; Xu, Liuqing; Cao, Duo
• Is Part Of: Computers & electrical engineering. Volume 93(2021)
• Publication Date: 2021-07
• Subjects: Peking Opera face -- Laplacian deformation -- Face detection -- BlendShape -- Depth camera; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107236
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Personalized modeling of Peking Opera faces is a challenging question in computer vision due to the artistry of painted faces, which is more challenging on natural human faces. To address this issue, in this paper, we propose a personalized modeling method for Peking Opera faces based on a depth camera device. Firstly, to solve the abnormal deformation of unrelated areas on 3D standard Peking Opera faces, a method that divide the Action Unit (AU) according to the face painting is designed, and the shape bases are constructed using local deformation based on the Laplacian algorithm. Secondly, to complete the linear fusion of different shape bases and model a natural and vivid personalized Peking Opera face, we design a method that calculates the weight of different shape bases based on the BlendShape algorithm to solve the conflicts between different shape bases. In addition, a real-time interactive method is proposed to calculate the weight value of each shape base based on 3D information of facial feature points captured by a depth camera. The results show that our method can achieve personalized modeling of Peking Opera faces with vivid expression in real-time, while reducing the complexity of the vectorization pattern database used in the existing personalized modeling of Peking Opera faces.