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

TL;DR

This paper introduces an Identity-Aware CycleGAN that enhances face photo-sketch synthesis and recognition by focusing on key facial features and jointly optimizing both tasks for improved accuracy.

Contribution

The paper proposes a novel Identity-Aware CycleGAN with a perceptual loss and a mutual optimization process for better face photo-sketch synthesis and recognition.

Findings

Outperforms state-of-the-art methods in synthesis quality

Achieves higher recognition accuracy on CUFS and CUFSF datasets

Effectively focuses on key facial regions for identity preservation

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-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.