Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition

About

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-tosketch 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.

Yuke Fang, Jiani Hu, Weihong Deng• 2021

Related benchmarks

TaskDatasetResultRank
Heterogeneous Face RecognitionIRIS Thermal Visible Face Database
Recall@172.89
16
Sketch-to-Photo Face RecognitionCUFSF
Rank-1 Accuracy64.94
8
Showing 2 of 2 rows

Other info

Follow for update