3D Face Image Inpainting with Generative Adversarial Nets. (14th December 2020)

• Record Type: Journal Article
• Authors: Wei, Tongxin; Li, Qingbao; Liu, Jinjin; Zhang, Ping; Chen, Zhifeng
• Other Names: Yuan Gonglin Academic Editor.
• Is Part Of: Mathematical problems in engineering. Volume 2020(2020)
• Publication Date: 2020-12-14
• Subjects: Engineering mathematics -- Periodicals; 510.2462
• DOI: 10.1155/2020/8882995
• Languages: English
• ISSNs: 1024-123X

Abstract

Abstract : In the process of face recognition, face acquisition data is seriously distorted. Many face images collected are blurred or even missing. Faced with so many problems, the traditional image inpainting was based on structure, while the current popular image inpainting method is based on deep convolutional neural network and generative adversarial nets. In this paper, we propose a 3D face image inpainting method based on generative adversarial nets. We identify two parallels of the vector to locate the planer positions. Compared with the previous, the edge information of the missing image is detected, and the edge fuzzy inpainting can achieve better visual match effect. We make the face recognition performance dramatically boost.