人脸年龄合成的生成对抗网络方法综述  

Overview of human-facial-related age syntheis based generative adversarial network methods

作　　者：王艺博 张珂[1,2] 孔英会[1,2] 于婷婷 赵士玮 Wang Yibo;Zhang Ke;Kong Yinghui;Yu Tingting;Zhao Shiwei(Department of Electronic and Communication Engineering,North China Electric Power University,Baoding 071003,China;Hebei Key Laboratory of Power Internet of Things Technology,North China Electric Power University,Baoding 071003,China)

机构地区：[1]华北电力大学电子与通信工程系,保定071003 [2]华北电力大学河北省电力物联网技术重点实验室,保定071003

出　　处：《中国图象图形学报》2023年第10期3004-3024,共21页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62076093,62206095,61871182);中央高校基本科研业务费专项资金资助(2023JG002,2022MS078,2023JC006)。

摘　　要：年龄信息作为人类生物特征识别的重要组成部分,在社会保障和数字娱乐等领域具有广泛的应用前景。人脸年龄合成技术由于其广泛的应用价值,受到了越来越多学者的重视,已经成为计算机视觉领域的重要研究方向之一。随着深度学习的快速发展,基于生成对抗网络的人脸年龄合成技术已成为研究热点。尽管基于生成对抗网络的人脸年龄合成方法取得了不错的成果,但生成的人脸年龄图像仍存在图像质量较差、真实感较低、年龄转换效果和多样性不足等问题。主要因为当前人脸年龄合成研究仍存在以下困难:1)现有人脸年龄合成数据集的限制;2)引入人脸年龄合成的先验知识不足;3)人脸年龄图像的细粒度性被忽视;4)高分辨率下的人脸年龄合成问题;5)目前人脸年龄合成方法的评价标准不规范。本文对目前人脸年龄合成技术进行全面综述,以人脸年龄合成方法为研究对象,阐述其研究现状。通过调研文献,对人脸年龄合成方法进行分类,重点介绍了基于生成对抗网络的人脸年龄合成方法。此外,本文还讨论了常用的人脸年龄合成数据集及评价指标,分析了各种人脸年龄合成方法的基本思想、特点及其局限性,对比了部分代表方法的性能,指出了该领域目前存在的挑战并提供了一些具有潜力的研究方向,为研究者们解决存在的问题提供便利。Human-biometric age information has been widely used for such domains like public security and digital enter⁃tainment.Such of human-facial-related age synthesis methods are mainly divided into traditional image processing methods and machine learning-based methods.Traditional image processing methods are divided into physics-based methods and prototype-based methods.Machine learning based method is focused on the model-based method,which can be divided into parametric linear model method,deep generative model method based on the time frame and generative adversarial net⁃work(GAN)-based method.The physics-based methods are focused on intuitive facial features only,for which some subtle changes are inevitably ignored,resulting in the irrationality of synthetic images.In addition,it requires a large number of facial samples for the same person at several of ages,which is costly and labor-intensive to be collected.The aging patterns generated by the prototype-based method are obtained by faces-related averaging value,and some important personalized features may be averaged,resulting in the loss of personal identity.Severe ghosting artifacts will be appeared in their syn⁃thetic images while some dictionary-based learning methods are used to preserve personalized features to some extent.Its related parametric linear model method and the deep generative model method based on the time frame are still challenged to find a general model suitable for a specific age group,and its following model established is still linear,so the quality of its synthetic image is deficient as well.The emerging GAN-based method can be used to train models using deep convolu⁃tion network.Aging patterns-related age groups is learnt in terms of the generative adversarial learning mechanism,differ⁃ent types of loss functions are introduced for various problems appearing in the image,and the minimum value of the per⁃ceptual loss of the original image is sorted out.Aging mode can be realized in the input face image,and identity informa�

关 键 词：人脸年龄合成 图像生成 人脸图像数据集 人脸老化 深度生成方法 生成对抗网络(GAN) 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]