Identity-aware CycleGAN for face photo-sketch synthesis and recognition

PATTERN RECOGNITION

卷:102

Article

Fang, Yuke¹  Deng, Weihong¹  Du, Junping¹  Hu, Jiani¹ 

[1] Beijing Univ Posts & Telecommun, Beijing 100876, Peoples R China

关键词: Convolutional neural network;    Generative adversarial network;    Photo-sketch synthesis;    Photo-sketch recognition;    Identity-aware training;   

DOI  :  10.1016/j.patcog.2020.107249

来源: Elsevier

【 摘 要 】

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. (C) 2020 Elsevier Ltd. All rights reserved.

【 授权许可】

Free