Identity-aware CycleGAN for face photo-sketch synthesis and recognition. (June 2020)

• Record Type: Journal Article
• Authors: Fang, Yuke; Deng, Weihong; Du, Junping; Hu, Jiani
• Is Part Of: Pattern recognition. Volume 102(2020:Jun.)
• Publication Date: 2020-06
• Subjects: Convolutional neural network -- Generative adversarial network -- Photo-sketch synthesis -- Photo-sketch recognition -- Identity-aware training; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107249
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Jointly solve synthesis and recognition problem by their close relationship. Identity-Aware CycleGAN (IACycleGAN) model with a perceptual loss in CycleGAN to supervise the image generation network. A mutual optimization procedure between the synthesis model and recognition model. Extensive experiments are performed on both photo-to-sketch and sketch-to-photo tasks using the widely used CUFS and CUFSF databases. Abstract: Face photo-sketch synthesis and recognition has many applications in digital entertainment and law enforcement. Recently, generative adversarial networks (GANs) based methods have significantly improved the quality of image synthesis, but they have not explicitly considered the purpose of recognition. In this paper, we first propose an Identity-Aware CycleGAN (IACycleGAN) model that applies a new perceptual loss to supervise the image generation network. It improves CycleGAN on photo-sketch synthesis by paying more attention to the synthesis of key facial regions, such as eyes and nose, which are important for identity recognition. Furthermore, we develop a mutual optimization procedure between the synthesis model and the recognition model, which iteratively synthesizes better images by IACycleGAN and enhances the recognition model by the triplet loss of the generated and real samples. Extensive experiments are performed on both photo-to-sketch and sketch-to-photo tasks using the widely used CUFS and CUFSF databases. The results show that the proposed method performs better than several state-of-the-art methods in terms of both synthetic image quality and photo-sketch recognition accuracy.