人脸表情合成算法综述  

Survey on Facial Expression Synthesis Algorithms

作　　者：郭迎春 王静洁 刘依 夏伟毅 张吉俊 李学博 王天瑞 GUO Yingchun;WANG Jingjie;LIU Yi;XIA Weiyi;ZHANG Jijun;LI Xuebo;WANG Tianrui(School of Artificial Intelligence,Hebei University of Technology,Tianjin 300400,China)

机构地区：[1]河北工业大学人工智能与数据科学学院,天津300400

出　　处：《数据采集与处理》2021年第5期898-920,共23页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(60302018,61806071)资助项目;河北省自然科学基金(F2019202381,F2019202464)资助项目。

摘　　要：人脸表情合成技术旨在保留人脸身份信息的情况下,对人脸表情进行重建,从而生成具有新表情的源人脸图像。深度学习的发展为表情合成提供了全新的解决方案,本文从特征提取、生成对抗网络的表情合成和实验评估方面综述了人脸表情合成技术的发展。首先,介绍了人脸特征的提取,这是表情合成任务中的一项关键技术,人脸特征可客观全面地描述人脸表情状态。其次,分析了表情合成领域中主流的基于深度学习的方法,主要针对生成对抗网络(Generative adversarial network,GAN)的发展现状,探讨了基于生成对抗网络的表情合成方法。通过对人脸数据集及实验评估方法的深入研究,总结出广泛使用的人脸表情合成数据集以及多种客观评价方法。最后根据现有方法所存在的问题,提出了未来工作的研究方向。Facial expression synthesis technology is designed to reconstruct face image with new expressions while retaining identity information.The development of deep learning provides a new solution for the synthesis of facial expressions.This paper introduces the development of facial expression synthesis technology from the aspects of feature extraction,expression synthesis of generated antagonistic networks and experimental evaluation.Firstly,extraction of facial features is introduced,which is the key technology in expression synthesis.Facial features can describe facial expressions objectively and comprehensively.Secondly,the state-of-the-art facial expression synthesis methods based on deep learning are analyzed,in which methods based on generative adversarial network(GAN)are mainly discussed.By research on facial expression datasets and evaluation methods,the widely used facial expression datasets and objective evaluation methods are given in this paper.Finally,future work is discussed according to the existing problems of facial expression synthesis methods.

关 键 词：表情合成 深度学习 生成对抗网络 表情数据库 客观评价方法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]