Sketch to portrait generation with generative adversarial networks and edge constraint. (October 2021)

• Record Type: Journal Article
• Authors: Liu, Qingyun; Zhao, Huihuang; Wang, Ying; Zhang, Feng; Ramasamy, Manimaran; Qiao, Zhijun
• Is Part Of: Computers & electrical engineering. Volume 95(2021)
• Publication Date: 2021-10
• Subjects: Sketch to portrait -- Conditional GANs -- Edge constraint -- Pix2Pix -- Laplace operator; 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.2021.107338
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Over similar data sets constrain the generating ability of neural networks. The loss function will affect the generation ability of the network. Laplacian can provide edge constraint in loss function. Edge constraint helps to generate portraits with clear boundary. Abstract: A novel method for generating color portraits from sketch images using the edge constraint algorithm and generative adversarial networks (GANs) is proposed in this paper. In converting sketches into color portraits, the details of portrait output by GANs are often blurred and unrealistic. A new method with edge constraint is proposed in this work to address this issue. The image generated from generator network and its edge generated from the followed edge network are combined and provided to the discriminator for authenticity identification. Experiments show that the portrait output by the proposed method provides a more clear and realistic edge than a Pix2Pix model and has a better ability to generate color portraits from sketches compared with other common methods. The average structural similarity index measure (SSIM) value of the proposed method is 82.78%, while the values obtained by other methods and Pix2Pix are 42.99% and 78.60%, respectively. Graphical abstract: Image, graphical abstract