人脸亲子关系验证研究综述

吴晓婷; 冯晓毅; 黄安; 张雪毅; 董晶; 刘丽

doi:10.16383/j.aas.c201023

人脸亲子关系验证研究综述

doi: 10.16383/j.aas.c201023

吴晓婷^{1, 2,},
冯晓毅^1,,
黄安^3,,
张雪毅^3,,
董晶^4,,
刘丽^{2, 3,}

1.
西北工业大学电子信息学院西安 710129 中国
2.
奥卢大学机器视觉与信号分析中心奥卢 90570 芬兰
3.
国防科技大学系统工程学院长沙 410073 中国
4.
中国科学院自动化研究所智能感知与计算研究中心北京 100190 中国

基金项目: 国家自然科学基金(61872379, 91846301), 湖南省重点领域研发计划(2019GK2131), 陕西省科技计划重点项目(2020GY-050)资助

详细信息

作者简介:
吴晓婷：西北工业大学电子信息学院与芬兰奥卢大学机器视觉与信号分析中心博士研究生. 主要研究方向为人脸亲子关系验证, 计算机视觉, 深度学习方向. E-mail: wuxt14@mail.nwpu.edu.cn

冯晓毅：西北工业大学电子信息学院教授. 主要研究方向为计算机视觉, 图像处理, 雷达成像和识别. E-mail: fengxiao@nwpu.edu.cn

黄安：国防科技大学系统工程学院硕士研究生. 主要研究方向为计算机视觉, 模式识别. E-mail: huangan99@nudt.edu.cn

张雪毅：国防科技大学系统工程学院硕士研究生. 主要研究方向为计算机视觉, 模式识别. E-mail: zhangxy1998@nudt.edu.cn

董晶：中国科学院自动化研究所智能感知与计算研究中心研究员. 主要研究方向为模式识别与图像处理, 计算机视觉, 多媒体内容安全. E-mail: jdong@nlpr.ia.ac.cn

刘丽：国防科技大学系统工程学院教授. 主要研究方向为图像理解, 计算机视觉, 模式识别. 本文通信作者. E-mail: liuli_nudt@nudt.edu.cn

计量
- 文章访问数: 2293
- HTML全文浏览量: 1058
- PDF下载量: 329
- 被引次数: 0
出版历程
- 收稿日期: 2020-12-09
- 录用日期: 2021-03-02
- 网络出版日期: 2021-05-19
- 刊出日期: 2022-12-23

Survey on Facial Kinship Verification

WU Xiao-Ting^{1, 2
,},
FENG Xiao-Yi^1
,,
HUANG An^3
,,
ZHANG Xue-Yi^3
,,
DONG Jing^4
,,
LIU Li^{2, 3
,}

1.
School of Electronics and Information, Northwestern Polytechnical University, Xi＇an 710072, China
2.
Center for Machine Vision and Signal Analysis, University of Oulu, Oulu 90570 Finland
3.
College of System Engineering, National University of Defense Technology, Changsha 410073, China
4.
Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China

Funds: Supported by National Natural Science Foundation of China (61872379, 91846301), Key Research and Development Program of Hunan Province (2019GK2131), and Key Research and Development Program of Shaanxi (2020GY-050)

More Information

Author Bio:
WU Xiao-Ting　Ph.D. candidate at the School of Electronics and Information, Northwestern Polytechnical University and Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland. Her research interest covers facial kinship verification, computer vision, and deep learning

FENG Xiao-Yi　Professor at the School of Electronics and Information, Northwestern Polytechnical University. Her research interest covers computer vision, image process, and radar imagery and recognition

HUANG An　Master student at the College of Electronic Science, National University of Defense Technology. His research interest covers computer vision and pattern recognition

ZHANG Xue-Yi　Master student at the College of Electronic Science, National University of Defense Technology. His research interest covers computer vision and pattern recognition

DONG Jing　Research fellow at the Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences. Her research interest covers pattern recognition, image processing, computer vision, and digital image forensics

LIU Li　Professor at the College of System Engineering, National University of Defense technology. Her research interest covers image understanding, computer vision, and pattern recognition. Corresponding author of this paper

摘要

摘要: 人脸亲子关系验证即通过给定的不同人的两幅人脸图像判断其是否具有亲子关系, 是计算机视觉和机器学习领域中一个重要的研究问题, 在丢失儿童寻找、社会媒体分析、图像自动标注等领域具有广泛的应用价值. 随着人脸亲子关系验证问题受到越来越多的关注, 其在多个方面都得到了相应的发展, 本文对人脸亲子关系验证方法做了综述整理. 首先, 简要介绍了人脸亲子关系验证在近十年的研究现状, 随后对问题进行了定义并讨论其面临的挑战. 接下来, 汇总了常用的亲子数据库, 对数据库属性做了详细的总结和对比. 然后, 对人脸亲子关系验证方法进行了分类总结、对比, 以及不同方法的性能表现. 最后, 展望了人脸亲子关系验证今后可能的研究方向.
- 人脸亲子关系验证 /
- 人脸分析 /
- 相似度计算 /
- 亲子数据集 /
- 深度学习
Abstract: Facial kinship verification aims to verify whether two facial images have kin relations or not. It is an important research topic in computer vision and machine learning domain. Kinship verification has a wide range of applications in fields of missing children finding, social media analysis and image automatic labelling. It receives more and more attention and has been developed in many directions. In this paper, we do a survey on the kinship verification. First, we briefly introduce the kinship verification’s state of research within last ten years. Then we define the problem and discuss the challenges. Then, we summarize and compare the attributes of public kinship databases. Kinship verification algorithms are categorized and reviewed as well. We also analysis different kinship verification methods and compare their performance. Finally, we discuss the future possible research directions of kinship verification.
- Facial kinship verification /
- face analysis /
- similarity computation /
- kinship databases /
- deep learning
注释:

1) ¹ https://web.northeastern.edu/smilelab/RFIW2017/² Kaggle是一个数据建模和数据分析竞赛平台, 信息来自维基百科.³ https://www.kaggle.com/c/Recognizing-Faces-in-the-Wild

2) Kaggle是一个数据建模和数据分析竞赛平台, 信息来自维基百科.

3) https://www.kaggle.com/c/Recognizing-Faces-in-the-Wild

4) ⁴ http://chenlab.ece.cornell.edu/projects/KinshipVerification/⁵ http://www1.ece.neu.edu/yunfu/research/Kinface/Kinface.htm

5) http://www1.ece.neu.edu/yunfu/research/Kinface/Kinface.htm

6) ⁶ http://www.kinfacew.com/

7) ⁷ http://chenlab.ece.cornell.edu/projects/KinshipClassification/index.html⁸ http://www.uva-nemo.org/

8) http://www.uva-nemo.org/

9) ⁹ http://parnec.nuaa.edu.cn/xtan/data/TSKinFace.html¹⁰ https://web.northeastern.edu/smilelab/fiw/¹¹ https://sites.google.com/a/mix.wvu.edu/namankohli/resources¹² https://www.kinfacew.com/datasets.html

10) ¹⁰ https://web.northeastern.edu/smilelab/fiw/¹¹ https://sites.google.com/a/mix.wvu.edu/namankohli/resources

11) https://sites.google.com/a/mix.wvu.edu/namankohli/resources

12) ¹² https://www.kinfacew.com/datasets.html

13) ¹³ http://iab-rubric.org/resources/KIVI.html

HTML全文

图 1 正样本对(具有亲子关系)和负样本对(不具有亲子关系)示意图 (© (2018) IEEE^[29]授权修改版)

Fig. 1 The illustration of positive pairs (with kin relations) and negative pairs (without kin relations) (© (2018) IEEE. Modified, with permission, from [29])

下载: 全尺寸图片幻灯片

图 2 亲子关系任务示意图

Fig. 2 The illustration of kinship related tasks

下载: 全尺寸图片幻灯片

图 3 亲子关系验证的一般流程

Fig. 3 The general framework of kinship verification

下载: 全尺寸图片幻灯片

图 4 基于显著性区域的亲子关系验证算法框架图

Fig. 4 The architecture of saliency based kinship verification

下载: 全尺寸图片幻灯片

图 5 LBP算法

Fig. 5 The algorithm of LBP

下载: 全尺寸图片幻灯片

图 6 LBP可视化特征

Fig. 6 The visualization of LBP feature

下载: 全尺寸图片幻灯片

图 7 彩色纹理特征提取方法

Fig. 7 The method of color-texture feature extraction

下载: 全尺寸图片幻灯片

图 8 NRML算法框架图

Fig. 8 The architecture of NRML algorithm

下载: 全尺寸图片幻灯片

图 9 大裕量多维度量学习算法示意图

Fig. 9 The illustration of LM3L

下载: 全尺寸图片幻灯片

图 10 基于基本CNN的亲子关系验证框架图

Fig. 10 The architecture of the basic CNN based kinship verification

下载: 全尺寸图片幻灯片

图 11 基于孪生网络的亲子关系验证框架

Fig. 11 The Siamese network based kinship verification

下载: 全尺寸图片幻灯片

图 12 三元损失函数示意图

Fig. 12 The illustration of triplet loss

下载: 全尺寸图片幻灯片

图 13 自编码器框架图

Fig. 13 The architecture of auto-encoder

下载: 全尺寸图片幻灯片

图 14 基于自编码器的亲子验证/图像合成框架图

Fig. 14 The architecture of auto-encoder based kinship verification/kin face synthesis

下载: 全尺寸图片幻灯片

图 15 注意力机制示意图

Fig. 15 The illustration of attention mechanism

下载: 全尺寸图片幻灯片

表 1 现有人脸亲子关系验证综述论文总结

Table 1 The summary of the existing facial kinship verification survey papers

综述	问题定义	难点与挑战	数据集总结	人脸亲子关系验证算法	性能分析	未来的研究方向	侧重点
[21]	$\times$	$\times$	$\checkmark$	对早期的人脸亲子关系验证算法进行了总结.	$\times$	$\times$	对人脸亲子关系验证问题的基础介绍.
[22]	$\times$	$\checkmark$	$\checkmark$	对早期的人脸亲子关系验证算法进行了归类、总结.	$\times$	$\checkmark$	对人脸亲子关系验证问题做了较为全面的总结.
[23]	$\checkmark$	$\checkmark$	$\checkmark$	主要就亲子特征提取方法进行了对比.	$\checkmark$	$\checkmark$	侧重阐述人脸亲子关系验证问题的衍生、定义、研究意义以及难点与挑战.
[24]	$\times$	$\times$	$\checkmark$	对人脸亲子关系验证算法作了分类、汇总.	$\checkmark$	$\times$	将人脸亲子关系验证任务和人脸衰老问题结合, 分析了其之间的相互关系.
[25]	$\checkmark$	$\checkmark$	$\checkmark$	对人脸亲子关系验证算法作了分类、汇总.	$\checkmark$	$\checkmark$	对亲子关系验证问题作了全面总结, 但是缺乏近期深度学习相关方法的汇总.
[26]	$\checkmark$	$\checkmark$	$\checkmark$	对 RFIW 系列比赛中的方法进行了归纳.	$\checkmark$	$\checkmark$	侧重于总结 RFIW 系列比赛, 包括比赛任务介绍、现阶段性能对比及今后可能的研究方向.
本文	$\checkmark$	$\checkmark$	$\checkmark$	对近十年来的亲子验证算法进行了全面的归纳、总结与分析.	$\checkmark$	$\checkmark$	文章从问题的数学定义出发, 对人脸亲子关系验证问题进行了全方位的总结、剖析与展望.

下载: 导出CSV

表 2 人脸亲子关系验证方法的优缺点总结

Table 2 The summary of advantages and disadvantages of the facial kinship verification methods

人脸亲子关系验证方法		代表性方法	针对的问题	优势	不足
传统方法	基于特征表示	基于显著特征^[31−35], 手工特征^{[14, 36−39]}, 基于颜色的特征变换^{[13, 29, 40−41]}, 特征选择^[42−45], ···	为了解决亲子特征的有效表达问题, 从传统手工设计规则出发, 依据形状、颜色、纹理等特性描述亲子的相关特征.	算法复杂度低, 特征提取速度快.	对光照、人脸角度等因素敏感, 在自然条件下性能较差.
传统方法	基于度量学习	邻域驳斥度量学习^{[15, 46−47]}, 基于双线性相似度^[48−49], 图构造^[50−51], 迁移子空间学习^[52−54], 余弦相似度^[55−56], ···	就一般距离度量不能很好地描述类内聚敛性和类间分离性问题, 提出度量学习优化亲子图像对间的距离衡量.	优化亲子图像的距离度量方式, 使得亲子间距离缩小, 并且拉大非亲子间的距离.	依赖于特征的有效表示, 距离优化程度有限.
基于深度学习的方法		基本卷积神经网络^[57], 深度度量学习^{[17, 58−62]}, 基于自编码器^{[18−19, 63−64]}, 基于注意力机制^[65], ···	传统方法固化于特定的规则, 很难适应于复杂情况, 深度网络针对问题自适应的学习数据的有效特征表示.	依据损失函数训练网络参数, 特征表达能力强.	需要大量的训练数据, 算法模型复杂, 训练时间长.

下载: 导出CSV

表 3 亲子关系数据库属性总结

Table 3 Characteristics of kinship databases

数据集, 年份	数据集大小	属性	分辨率 (像素)	有无多幅图像/ 视频	年龄变化	有无家庭结构	录制环境	数据集特点	针对的问题
CornellKin^[6], 2010	300 幅图像 150 对亲子	图像	100×100	无	无	无	自然环境	第一个亲子数据集	1V1
UB Kinface^[52-53], 2011	600 幅图像 200 组亲子	图像	89×96	无	有	无	自然环境	包含年轻与年老的父母图像的数据集	1V1
UvA-NEMO Smile^[66-67], 2012	1240 段视频	视频	1920×1080	有	无	无	约束环境	第一个亲子视频数据集	1V1
Family 101^[30], 2013	14816 幅图像 101 个家庭树	图像	120×150	有	有	有	自然环境	第一个有家庭结构的数据集	1V1, 家庭识别
KinFaceW-I^[15], 2014	1066 幅图像 533 对亲子	图像	64×64	无	无	无	自然环境	常用的数据集, 图像来自不同照片	1V1
KinFaceW-II^[15], 2014	2000 幅图像 1000 对亲子	图像	64×64	无	无	无	自然环境	常用的数据集, 图像来自同一照片	1V1
TSKinFace^[68], 2015	787 幅图像 1015 组亲子	图像	64×64	无	无	有	自然环境	同时包含父亲和母亲的人脸图像	2V1
FIW^[18], 2016	11193 幅图像 1000 个家庭	图像	108×124	有	有	有	自然环境	当前规模最大的亲子数据集	1V1, 2V1 家庭识别, 检索
WVU^[69], 2017	904 幅图像 113 对亲子	图像	32×32	有	未知	无	自然环境	每人均有4幅图像不同的图片	1V1
KFVW^[70], 2018	836 段视频 418 对亲子	视频	900×500	无	无	无	自然环境	第一个无表情约束视频数据集	1V1
FFVW^[71], 2018	300 段视频 100 组亲子	视频	未知	无	无	有	自然环境	可用于三人组视频亲子关系验证	2V1
KIVI^[72], 2019	503 段视频 211 个家庭	视频	未知	无	无	有	自然环境	无约束的亲子视频数据集	1V1
TALKIN^[73], 2019	800 段视频 400 对亲子	视频音频	1920×1080	无	无	无	自然环境	第一个多模态数据集	1V1
表中简写含义: 1V1表示两输入的亲子关系验证, 2V1表示三人组, 即父亲−母亲−孩子的亲子关系验证.

下载: 导出CSV

表 4 基于深度学习的亲子关系验证方法总结

Table 4 The summary of deep learning based kinship verification

方法	特征	图学习	距离度量	自编码器	数据类型	针对的问题
DKV^[16] MMSP2015)	全局特征	否	马氏距离	是	图像	针对亲子验证中的非线性问题, 提出用自编码器及深度度量学习改进图像特征和距离度量.
CNN-Points^[57] (BMVC2015)	局部特征	否	神经网络	否	图像	对比于传统手工特征, 第一个提出端到端的深度学习算法, 并将面部分块作为网络输入.
CMDAE^[104] (IJCAI2016)	全局特征	否	欧氏距离	是	图像	将父母和子女看做两个不同的域, 年轻时父母作为中间桥梁, 减小由年龄带来的差异性.
SMCNN^[17] (ICIAR2016)	全局特征	否	L1范数	否	图像	将深度学习网络和度量学习结合, 提出使用L1范数作为距离度量, 端到端的更新网络参数.
AdvNet^[58] (RFIW2017)	全局特征	否	欧氏距离	否	图像	大数据下的亲子关系验证问题, 提出使用多个对抗对比残差网络提取图像的多角度特征.
DDML^[59] (TIP2017)	全局特征	否	欧氏距离	否	图像	针对传统度量学习大多为线性变换, 提出多特征的深度度量学习, 将亲子面部特征映射到非线性平面.
CFT^[105] (ICCVW2017)	全局特征	否	欧氏距离	否	图像	针对亲子关系数据量小时, CNN 网络容易过拟合问题, 提出人脸迁移学习方法.
KinNet^[60] (RFIW2017)	全局特征	否	马氏距离	否	图像	引入 Triplet 损失函数训练网络, 并通过改变分辨率、加噪声等操作增加训练数据量.
DRF^[106] (CCCV2017)	局部特征	否	神经网络	是	图像	对于大部分方法都基于相似度度量, 提出使用自编码器度量亲子间距离.
SCCAE^[18] (ICCV2017)	全局特征	否	后验概率	是	视频	对于亲子间具有相似的表情, 通过表情匹配方法, 分析亲子间表情的关联性.
Appearance+Shape^[107] (ICIP2019)	全局特征	否	内积	否	图像	将面部的外观模型和几何模型进行分离, 从两个维度考虑亲子对的相似性.
KML^[61] (Inf Fusion2019)	全局特征	否	余弦相似度	否	图像	针对隔代因素间的差异性, 提出紧凑型深度度量学习方法. 方法使用四输入比较其相似性与非相似性.
Attention^[65] (PRL2019)	局部特征	否	神经网络	否	图像	针对亲子特征往往存在于人脸区域中, 并非全脸, 提出注意力机制的亲子关系验证方法.
SMNAE^[72] (TIP2019)	全局特征	否	神经网络	是	视频	为解决亲子关系验证问题大都从静止图像分析, 提出空间−时间的亲子关系验证框架.
Fusion Kinship^[67] (ICB2019)	全局特征	否	余弦相似度	否	视频+语音	针对现有亲子关系验证仅从视觉信息入手, 论文融合声音信号来提高模型的性能.
AdvKin^[62] (TCYB2020)	局部特征	否	欧氏距离	否	图像	提出细粒度和更加严格的度量方法. 将人脸图像进行分块, 结合对比损失函数与对抗函数优化网络.
GKR^[109] (ICME2020)	全局特征	是	神经网络	否	图像	针对如何进行特征融合及亲子关系推理. 对 CNN 输出的特征向量, 通过图结构分析两幅图像相似性.
KINMIX^[110] (ICME2020)	全局特征	否	神经网络	否	图像	就数据量不足的问题, 在图像特征级上进行线性变换进行数据扩充, 数据可靠性高.

下载: 导出CSV

表 5 人脸亲子关系验证方法识别准确率对比 (%)

Table 5 The comparison of accuracies or kinship verification methods (%)

数据集	方法类别	方法	特征	度量/分类器	FS	FD	MS	MD	平均值
Cornell KinFace	特征提取方法	计算模型^[6]	低层次特征	SVM	72.9	54.6	73.8	61.3	65.7
	度量学习方法	PDFL^[46]	LBP, SPLE, SIFT	SVM	74.8	69.1	77.5	66.1	71.9
	度量学习方法	DMML^[78]	LBP, SPLE, SIFT	SVM	76.0	70.5	77.5	71.0	73.8
KinFaceW-I		D-CBFD^[39]	LBP	阈值	79.6	73.6	76.1	81.5	77.6
	特征提取方法	特征选择^[86]	LBP, LPQ, SIFT	高斯概率	75.4	63.8	69.9	74.6	70.9
	特征提取方法	PML-COV^[38]	HOG, LBP	SVM	91.0	84.3	87.1	90.2	88.2
	度量学习方法	MNRML^[15]	LBP, SIFT, LE, TPLBP	SVM	72.5	66.5	66.2	72.0	69.9
		PDFL^[46]	LBP, SPLE, SIFT	SVM	73.5	67.5	66.1	73.1	70.1
		ESL^[48]	LBP	双线性相似度	81.7	71.1	69.6	74.3	74.1
		DMML^[78]	LBP, SPLE, SIFT	SVM	74.5	69.5	69.5	75.5	72.3
		WGEML^[51]	LBP, HOG, SIFT, CNN	KNN	78.5	73.9	80.6	81.9	78.7
	深度学习方法	CNN-points^[57]	深度特征	神经网络	71.8	76.1	84.1	78.0	77.5
		SMCNN^[17]	深度特征	阈值	75.0	75.0	72.2	68.7	72.7
		DDML^[59]	深度特征	阈值	86.4	79.1	81.4	87.0	83.5
		AdvKin^[62]	深度特征	阈值	76.6	77.3	78.4	86.2	79.6
		Attention^[65]	深度特征	神经网络	81.2	85.9	78.2	85.2	82.6
KinFaceW-II	特征提取方法	D-CBFD^[39]	LBP	阈值	81.0	76.2	77.4	79.3	78.5
		特征选择^[86]	LBP, LPQ, SIFT	高斯概率	82.4	76.2	76.6	73.2	70.0
		PML-COV^[38]	HOG, LBP	SVM	88.6	85.8	87.2	91.0	88.2
	度量学习方法	MNRML^[15]	LBP, SIFT, LE, TPLBP	SVM	76.9	74.3	77.4	77.6	76.5
		PDFL^[46]	LBP, SPLE, SIFT	SVM	77.3	74.7	77.8	78.0	77.0
		LM3L^[90]	LBP, SIFT, LE, TPLBP	阈值	82.4	78.2	78.8	80.4	80.0
		ESL^[48]	LBP	双线性相似度	80.5	72.2	72.8	71.6	74.3
		DMML^[78]	LBP, SPLE, SIFT	SVM	78.5	76.5	78.5	79.5	78.3
		WGEML^[51]	LBP, HOG, SIFT, CNN	KNN	88.6	77.4	83.4	81.6	82.8
	深度学习方法	CNN-points^[57]	深度特征	神经网络	81.9	89.4	92.4	89.9	88.4
		SMCNN^[17]	深度特征	阈值	79.0	75.0	85.0	78.0	79.3
		DDML^[59]	深度特征	阈值	87.4	83.8	83.2	83.0	84.3
		AdvKin^[62]	深度特征	阈值	91.6	85.2	90.2	92.4	89.9
		Attention^[65]	深度特征	神经网络	91.8	89.8	92.8	93.4	92.0
TSKinFace	特征提取方法	颜色特征^[12]	BSIF-HSV	阈值	81.5	81.4	79.9	82.0	81.2
	度量学习方法	WGEML^[51]	LBP, HOG, SIFT, CNN	KNN	90.3	89.8	91.4	90.4	90.5
	深度学习方法	DDML^[59]	深度特征	阈值	88.5	87.0	87.9	87.8	87.8
UBKinFace	度量学习方法	DMML^[78]	LBP, SPLE, SIFT	SVM	年轻父母−孩子		年老父母−孩子		72.3
UBKinFace	度量学习方法	DMML^[78]	LBP, SPLE, SIFT	SVM	74.5	70.0			72.3
FIW	深度学习方法	AdvKin^[62]	深度特征	阈值	68.8	67.8	67.3	69.9	68.5
Smile		SCCAE^[18]	自编码器隐含层	阈值	93.4	93.8	92.2	93.6	93.3
KIVI		SMNAE^[72]	自编码器隐含层	SVM	80.0	81.8	77.8	92.3	83.0
TALKIN		模态融合^[73]	深度特征	阈值	80.0	70.5	73.5	72.5	74.1

下载: 导出CSV

参考文献(128)

[1]	Dal Martello M F, Maloney L T. Where are kin recognition signals in the human face? Journal of Vision, 2006, 6(12): 1356−1366
[2]	Dal Martello M F, Maloney L T. Lateralization of kin recognition signals in the human face. Journal of Vision, 2010, 10(8): Article No. 9 doi: 10.1167/10.8.9
[3]	DeBruine L M, Smith F G, Jones B C, Roberts S C, Petrie M, Spector T D. Kin recognition signals in adult faces. Vision Research, 2009, 49(1): 38-43 doi: 10.1016/j.visres.2008.09.025
[4]	Maloney L T, Dal Martello M F. Kin recognition and the perceived facial similarity of children. Journal of Vision, 2006, 6(10): 1047-1056
[5]	Alvergne A, Perreau F, Mazur A, Mueller U, Raymond M. Identification of visual paternity cues in humans. Biology Letters, 2014, 10(4): Article No. 20140063 doi: 10.1098/rsbl.2014.0063
[6]	Fang R G, Tang K D, Snavely N, Chen T. Towards computational models of kinship verification. In: Proceedings of the 2010 IEEE International Conference on Image Processing. Hong Kong, China: IEEE, 2010. 1577−1580
[7]	Lu J W, Hu J L, Zhou X Z, Zhou J, Castrillón-Santana M, Lorenzo-Navarro J, et al. Kinship verification in the wild: The first kinship verification competition. In: Proceedings of the 2014 IEEE International Joint Conference on Biometrics. Clearwater, USA: IEEE, 2014. 1−6
[8]	Lu J W, Hu J L, Liong V E, Zhou X Z, Bottino A, Islam I U, et al. The FG 2015 kinship verification in the wild evaluation. In: Proceedings of the 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG). Ljubljana, Slovenia: IEEE, 2015. 1−7
[9]	Robinson J P, Yin Y, Khan Z, Shan M, Xia S Y, Stopa M, et al. Recognizing families in the wild (RFIW): The 4th edition. In: Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020). Buenos Aires, Argentina: IEEE, 2020.
[10]	Robinson J P, Shao M, Fu Y. To recognize families in the wild: A machine vision tutorial. In: Proceedings of the 26th ACM International Conference on Multimedia. Seoul, Republic of Korea: ACM, 2018. 2096−2097
[11]	Robinson J P, Shao M, Wu Y, Liu H F, Gillis T, Fu Y. Visual kinship recognition of families in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(11): 2624-2637 doi: 10.1109/TPAMI.2018.2826549
[12]	Wu X T, Boutellaa E, López M B, Feng X Y, Hadid A. On the usefulness of color for kinship verification from face images. In: Proceedings of the 2016 IEEE International Workshop on Information Forensics and Security (WIFS). Abu Dhabi, United Arab Emirates: IEEE, 2016. 1−6
[13]	Liu Q F, Puthenputhussery A, Liu C J. A novel inheritable color space with application to kinship verification. In: Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Placid, USA: IEEE, 2016. 1−9
[14]	Puthenputhussery A, Liu Q F, Liu C J. SIFT flow based genetic fisher vector feature for kinship verification. In: Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP). Phoenix, USA: IEEE, 2016. 2921−2925
[15]	Lu J W, Zhou X Z, Tan Y P, Shang Y Y, Zhou J. Neighborhood repulsed metric learning for kinship verification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(2): 331-345 doi: 10.1109/TPAMI.2013.134
[16]	Wang M Y, Li Z C, Shu X B, Jingdong, Tang J H. Deep kinship verification. In: Proceedings of the 17th International Workshop on Multimedia Signal Processing (MMSP). Xiamen, China: IEEE, 2015. 1−6
[17]	Li L, Feng X Y, Wu X T, Xia Z Q, Hadid A. Kinship verification from faces via similarity metric based convolutional neural network. In: Proceedings of the 13th International Conference on Image Analysis and Recognition. Póvoa de Varzim, Portugal: Springer, 2016. 539−548
[18]	Dibeklioglu H. Visual transformation aided contrastive learning for video-based kinship verification. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. 2478−2487
[19]	Gao P Y, Xia S Y, Robinson J, Zhang J K, Xia C, Shao M, et al. What will your child look like? DNA-Net: Age and gender aware kin face synthesizer. arXiv preprint arXiv: 1911.07014, 2019.
[20]	Ghatas F S, Hemayed E E. GANKIN: Generating kin faces using disentangled GAN. SN Applied Sciences, 2020, 2(2): Article No. 166 doi: 10.1007/s42452-020-1949-3
[21]	Dandekar A R, Nimbarte M S. A survey: Verification of family relationship from parents and child facial images. In: Proceedings of the 2014 IEEE Students’ Conference on Electrical, Electronics and Computer Science. Bhopal, India: IEEE, 2014. 1−6
[22]	Wu X T, Boutellaa E, Feng X Y, Hadid A. Kinship verification from faces: Methods, databases and challenges. In: Proceedings of the 2016 IEEE International Conference on Signal Processing (ICSPCC). Hong Kong, China: IEEE, 2016. 1−6
[23]	Almuashi M, Hashim S Z M, Mohamad D, Alkawaz M H, Ali A. Automated kinship verification and identification through human facial images: A survey. Multimedia Tools and Applications, 2017, 76(1): 265-307 doi: 10.1007/s11042-015-3007-5
[24]	Georgopoulos M, Panagakis Y, Pantic M. Modeling of facial aging and kinship: A survey. Image and Vision Computing, 2018, 80: 58-79 doi: 10.1016/j.imavis.2018.05.003
[25]	Qin X Q, Liu D K, Wang D. A literature survey on kinship verification through facial images. Neurocomputing, 2020, 377: 213-224 doi: 10.1016/j.neucom.2019.09.089
[26]	Robinson J P, Shao M, Fu Y. Survey on the analysis and modeling of visual kinship: A decade in the making. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(8): 4432v4453
[27]	Dal Martello M F, DeBruine L M, Maloney L T. Allocentric kin recognition is not affected by facial inversion. Journal of Vision, 2015, 15(13): Article No. 5 doi: 10.1167/15.13.5
[28]	Fasolt V, Holzleitner I, Lee A J, O’Shea K J, DeBruine L M. Facial expressions influence kin recognition accuracy. Human Ethology Bulletin, 2018, 33(4): 19-27 doi: 10.22330/heb/334/019-027
[29]	Wu X T, Feng X Y, Boutellaa E, Hadid A. Kinship verification using color features and extreme learning machine. In: Proceedings of the 3rd IEEE International Conference on Signal and Image Processing (ICSIP). Shenzhen, China: IEEE, 2018. 187−191
[30]	Fang R G, Gallagher A C, Chen T, Loui A. Kinship classification by modeling facial feature heredity. In: Proceedings of the 2013 IEEE International Conference on Image Processing. Melbourne, Australia: IEEE, 2013. 2983−2987
[31]	Guo G D, Wang X L. Kinship measurement on salient facial features. IEEE Transactions on Instrumentation and Measurement, 2012, 61(8): 2322-2325 doi: 10.1109/TIM.2012.2187468
[32]	Wang X L, Kambhamettu C. Leveraging appearance and geometry for kinship verification. In: Proceedings of the 2014 International Conference on Image Processing (ICIP). Paris, France: IEEE, 2014. 5017−5021
[33]	Goyal A, Meenpal T. Detection of facial parts in kinship verification based on edge information. In: Proceedings of the 2018 Conference on Information and Communication Technology (CICT). Jabalpur, India: IEEE, 2018. 1−6
[34]	Asthana A, Zafeiriou S, Cheng S Y, Pantic M. Robust discriminative response map fitting with constrained local models. In: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA: IEEE, 2013. 3444−3451
[35]	Canny J. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679-698 doi: 10.1109/TPAMI.1986.4767851
[36]	Zhou X Z, Hu J L, Lu J W, Shang Y Y, Guan Y. Kinship verification from facial images under uncontrolled conditions. In: Proceedings of the 19th ACM International Conference on Multimedia. Scottsdale, USA: ACM, 2011. 953−956
[37]	Zhou X Z, Lu J W, Hu J L, Shang Y Y. Gabor-based gradient orientation pyramid for kinship verification under uncontrolled environments. In: Proceedings of the 20th ACM International Conference on Multimedia. Nara, Japan: ACM, 2012. 725−728
[38]	Moujahid A, Dornaika F. A pyramid multi-level face descriptor: Application to kinship verification. Multimedia Tools and Applications, 2019, 78(7): 9335-9354 doi: 10.1007/s11042-018-6517-0
[39]	Yan H B. Learning discriminative compact binary face descriptor for kinship verification. Pattern Recognition Letters, 2019, 117: 146-152 doi: 10.1016/j.patrec.2018.05.027
[40]	Laiadi O, Ouamane A, Boutellaa E, Benakcha A, Taleb-Ahmed A, Hadid A. Kinship verification from face images in discriminative subspaces of color components. Multimedia Tools and Applications, 2019, 78(12): 16465-16487 doi: 10.1007/s11042-018-7027-9
[41]	Liu Q F, Puthenputhussery A, Liu C J. Inheritable fisher vector feature for kinship verification. In: Proceedings of the 7th International Conference on Biometrics Theory, Applications and Systems (BTAS). Arlington, USA: IEEE, 2015. 1−6
[42]	Alirezazadeh P, Fathi A, Abdali-Mohammadi F. A genetic algorithm-based feature selection for kinship verification. IEEE Signal Processing Letters, 2015, 22(12): 2459-2463 doi: 10.1109/LSP.2015.2490805
[43]	Bottinok A, Islam I U, Vieira T F. A multi-perspective holistic approach to kinship verification in the wild. In: Proceedings of the 11th International Conference and Workshops on Automatic Face and Gesture Recognition (FG). Ljubljana, Slovenia: IEEE, 2015. 1−6
[44]	Cui L Y, Ma B. Adaptive feature selection for kinship verification. In: Proceedings of the 2017 IEEE International Conference on Multimedia and Expo (ICME). Hong Kong, China: IEEE, 2017. 751−756
[45]	Chen X J, An L, Yang S F, Wu W M. Kinship verification in multi-linear coherent spaces. Multimedia Tools and Application, 2017, 76(3): 4105-4122 doi: 10.1007/s11042-015-2930-9
[46]	Yan H B, Lu J W, Zhou X Z. Prototype-based discriminative feature learning for kinship verification. IEEE Transactions on Cybernetics, 2015, 45(11): 2535-2545 doi: 10.1109/TCYB.2014.2376934
[47]	Xu M, Shang Y Y. Kinship measurement on face images by structured similarity fusion. IEEE Access, 2016, 4: 10280-10287 doi: 10.1109/ACCESS.2016.2635147
[48]	Zhou X Z, Shang Y Y, Yan H B, Guo G D. Ensemble similarity learning for kinship verification from facial images in the wild. Information Fusion, 2016, 32: 40-48
[49]	Zhou X Z, Yan H B, Shang Y Y. Kinship verification from facial images by scalable similarity fusion. Neurocomputing, 2016, 197: 136-142 doi: 10.1016/j.neucom.2016.02.039
[50]	Guo Y H, Dibeklioglu H, Van Der Maaten L. Graph-based kinship recognition. In: Proceedings of the 22nd International Conference on Pattern Recognition. Stockholm, Sweden: IEEE, 2014. 4287−4292
[51]	Liang J Q, Hu Q H, Dang C Y, Zuo W M. Weighted graph embedding-based metric learning for kinship verification. IEEE Transactions on Image Processing, 2019, 28(3): 1149-1162 doi: 10.1109/TIP.2018.2875346
[52]	Shao M, Xia S Y, Fu Y. Genealogical face recognition based on UB KinFace database. In: Proceedings of the CVPR 2011 WORKSHOPS. Colorado Springs, USA: IEEE, 2011. 60−65
[53]	Xia S Y, Shao M, Fu Y. Kinship verification through transfer learning. In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence. Barcelona, Spain: AAAI Press, 2011. 2539−2544
[54]	Zhang Y L, Ma B, Huang L H, Hu H W. Transfer metric learning for kinship verification with locality-constrained sparse features. In: Proceedings of the 22nd International Conference on Neural Information Processing. Istanbul, Turkey: Springer, 2015. 234−243
[55]	Yan H B, Zhou X Z, Ge Y X. Neighborhood repulsed correlation metric learning for kinship verification. In: Proceedings of the 2015 Visual Communications and Image Processing (VCIP). Singapore: IEEE, 2015. 1−4
[56]	Yan H B. Kinship verification using neighborhood repulsed correlation metric learning. Image and Vision Computing, 2017, 60: 91-97 doi: 10.1016/j.imavis.2016.08.009
[57]	Zhang K H, Huang Y Z, Song C F, Wu H, Wang L. Kinship verification with deep convolutional neural networks. In: Proceedings of the 2015 British Machine Vision Conference. Swansea, UK: BMVA Press, 2015.
[58]	Duan Q Y, Zhang L. AdvNet: Adversarial contrastive residual net for 1 million kinship recognition. In: Proceedings of the 2017 Workshop on Recognizing Families in the Wild. Mountain View, USA: ACM, 2017.
[59]	Lu J W, Hu J L, Tan Y P. Discriminative deep metric learning for face and kinship verification. IEEE Transactions on Image Processing, 2017, 26(9): 4269-4282 doi: 10.1109/TIP.2017.2717505
[60]	Yong L, Zeng J B, Zhang J, Dai A B, Kan M N, Shan S G, et al. KinNet: Fine-to-coarse deep metric learning for kinship verification. In: Proceedings of the 2017 Workshop on Recognizing Families in the Wild. Mountain View, USA: ACM, 2017.
[61]	Zhou X Z, Jin K, Xu M, Guo G D. Learning deep compact similarity metric for kinship verification from face images. Information Fusion, 2019, 48: 84-94 doi: 10.1016/j.inffus.2018.07.011
[62]	Zhang L, Duan Q Y, Zhang D, Jia W, Wang X Z. AdvKin: Adversarial convolutional network for kinship verification. IEEE Transactions on Cybernetics, 2021, 51(12): 5883-5896 doi: 10.1109/TCYB.2019.2959403
[63]	Wang S Y, Ding Z M, Fu Y. Cross-generation kinship verification with sparse discriminative metric. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(11): 2783-2790 doi: 10.1109/TPAMI.2018.2861871
[64]	Ozkan S, Ozkan A. Kinshipgan: Synthesizing of kinship faces from family photos by regularizing a deep face network. In: Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). Athens, Greece: IEEE, 2018. 2142−2146
[65]	Yan H B, Wang S W. Learning part-aware attention networks for kinship verification. Pattern Recognition Letters, 2019, 128: 169-175 doi: 10.1016/j.patrec.2019.08.023
[66]	Dibeklioğlu H, Salah A A, Gevers T. Are you really smiling at me? Spontaneous versus posed enjoyment smiles. In: Proceedings of the 12th European Conference on Computer Vision. Florence, Italy: Springer, 2012. 525−538
[67]	Dibeklioglu H, Salah A A, Gevers T. Like father, like son: Facial expression dynamics for kinship verification. In: Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney, Australia: IEEE, 2013. 1497−1504
[68]	Qin X Q, Tan X Y, Chen S C. Tri-subject kinship verification: Understanding the core of a family. IEEE Transactions on Multimedia, 2015, 17(10): 1855-1867 doi: 10.1109/TMM.2015.2461462
[69]	Kohli N, Vatsa M, Singh R, Noore A, Majumdar A. Hierarchical representation learning for kinship verification. IEEE Transactions on Image Processing, 2017, 26(1): 289-302 doi: 10.1109/TIP.2016.2609811
[70]	Yan H B, Hu J L. Video-based kinship verification using distance metric learning. Pattern Recognition, 2018, 75: 15-24 doi: 10.1016/j.patcog.2017.03.001
[71]	Sun Y, Li J C, Wei Y W, Yan H B. Video-based parent-child relationship prediction. In: Proceedings of the 2018 IEEE Visual Communications and Image Processing (VCIP). Taichung, China: IEEE, 2018. 1−4
[72]	Kohli N, Yadav D, Vatsa M, Singh R, Noore A. Supervised mixed norm autoencoder for kinship verification in unconstrained videos. IEEE Transactions on Image Processing, 2019, 28(3): 1329-1341 doi: 10.1109/TIP.2018.2840880
[73]	Wu X T, Granger E, Kinnunen T H, Feng X Y, Hadid A. Audio-visual kinship verification in the wild. In: Proceedings of the 2019 International Conference on Biometrics (ICB). Crete, Greece: IEEE, 2019. 1−8
[74]	吴晓婷. 基于颜色纹理特征与度量学习的亲子关系验证研究 [硕士学位论文], 西北工业大学, 中国, 2016. Wu Xiao-Ting. Kinship Verification Based on Color Texture Features and Metric Learning [Master dissertation], Northwestern Polytechnical University, China, 2016.
[75]	Zhang K P, Zhang Z P, Li Z F, Qiao Y. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 2016, 23(10): 1499-1503 doi: 10.1109/LSP.2016.2603342
[76]	Kazemi V, Sullivan J. One millisecond face alignment with an ensemble of regression trees. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014. 1867−1874
[77]	Xing E P, Ng A Y, Jordan M I, Russell S J. Distance metric learning, with application to clustering with side-information. In: Proceedings of the 15th International Conference on Neural Information Processing Systems. Vancouver, Canada: MIT Press, 2002. 521−528
[78]	Yan H B, Lu J W, Deng W H, Zhou X Z. Discriminative multimetric learning for kinship verification. IEEE Transactions on Information Forensics and Security, 2014, 9(7): 1169-1178 doi: 10.1109/TIFS.2014.2327757
[79]	Xia S Y, Shao M, Fu Y. Toward kinship verification using visual attributes. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012). Tsukuba, Japan: IEEE, 2012. 549−552
[80]	Xia S Y, Shao M, Luo J B, Fu Y. Understanding kin relationships in a photo. IEEE Transactions on Multimedia, 2012, 14(4): 1046-1056 doi: 10.1109/TMM.2012.2187436
[81]	Kohli N, Singh R, Vatsa M. Self-similarity representation of Weber faces for kinship classification. In: Proceedings of the IEEE 5th International Conference on Biometrics: Theory, Applications and Systems (BTAS). Arlington, USA: IEEE, 2012. 245−250
[82]	Tola E, Lepetit V, Fua P. DAISY: An efficient dense descriptor applied to wide-baseline stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 815-830 doi: 10.1109/TPAMI.2009.77
[83]	Patel B, Maheshwari R P, Raman B. Evaluation of periocular features for kinship verification in the wild. Computer Vision and Image Understanding, 2017, 160: 24-35 doi: 10.1016/j.cviu.2017.04.009
[84]	Ojala T, Pietikäinen M, Harwood D. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 1996, 29(1): 51-59 doi: 10.1016/0031-3203(95)00067-4
[85]	Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987 doi: 10.1109/TPAMI.2002.1017623
[86]	Duan X D, Tan Z H. A feature subtraction method for image based kinship verification under uncontrolled environments. In: Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP). Québec City, Canada: IEEE, 2015. 1573−1577
[87]	Bessaoudi M, Ouamane A, Belahcene M, Chouchane A, Boutellaa E, Bourennane S. Multilinear side-information based discriminant analysis for face and kinship verification in the wild. Neurocomputing, 2019, 329: 267-278 doi: 10.1016/j.neucom.2018.09.051
[88]	Laiadi O, Ouamane A, Benakcha A, Taleb-Ahmed A, Hadid A. Tensor cross-view quadratic discriminant analysis for kinship verification in the wild. Neurocomputing, 2020, 377: 286-300 doi: 10.1016/j.neucom.2019.10.055
[89]	Hu J L, Lu J W, Yuan J S, Zhou X P. Large margin multi-metric learning for face and kinship verification in the wild. In: Proceedings of the 12th Asian Conference on Computer Vision. Singapore: Springer, 2014. 252−267
[90]	Hu J L, Lu J W, Tan Y P, Yuan J S, Zhou J. Local large-margin multi-metric learning for face and kinship verification. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(8): 1875-1891 doi: 10.1109/TCSVT.2017.2691801
[91]	Kou L, Zhou X Z, Xu M, Shang Y Y. Learning a genetic measure for kinship verification using facial images. Mathematical Problems in Engineering, 2015, 2015: Article No. 472473
[92]	Wei Z Q, Xu M, Geng L, Liu H M, Yin H. Adversarial similarity metric learning for kinship verification. IEEE Access, 2019, 7: 100029-100035 doi: 10.1109/ACCESS.2019.2929939
[93]	Xu M, Shang Y Y. Kinship verification using facial images by robust similarity learning. Mathematical Problems in Engineering, 2016, 2016: Article No. 4072323
[94]	Qin X Q, Tan X Y, Chen S C. Mixed bi-subject kinship verification via multi-view multi-task learning. Neurocomputing, 2016, 214: 350-357 doi: 10.1016/j.neucom.2016.06.027
[95]	Fang Y, Yan Y, Chen S, Wang H Z, Shu C. Sparse similarity metric learning for kinship verification. In: Proceedings of the 2016 Visual Communications and Image Processing (VCIP). Chengdu, China: IEEE, 2016. 1−4
[96]	Lei X H, Li B, Xie J. Locality discriminative canonical correlation analysis for kinship verification. In: Proceedings of the 12th IEEE Conference on Industrial Electronics and Applications (ICIEA). Siem Reap, Cambodia: IEEE, 2017.
[97]	Zhang J K, Xia S Y, Pan H, Qin A K. A genetics-motivated unsupervised model for tri-subject kinship verification. In: Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP). Phoenix, USA: IEEE, 2016. 2916−2920
[98]	Liu H J, Cheng J, Wang F. Kinship verification based on status-aware projection learning. In: Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP). Beijing, China: IEEE, 2017. 1072−1076
[99]	Liu H J, Zhu C. Status-aware projection metric learning for kinship verification. In: Proceedings of the 2017 IEEE International Conference on Multimedia and Expo (ICME). Hong Kong, China: IEEE, 2017. 319−324
[100]	Wu Y, Ding Z M, Liu H F, Robinson J, Yun F. Kinship classification through latent adaptive subspace. In: Proceedings of the 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2018). Xi＇an, China: IEEE, 2018. 143−149
[101]	Zhao Y G, Song Z, Zheng F, Shao L. Learning a multiple kernel similarity metric for kinship verification. Information Sciences, 2018, 430-431: 247-260 doi: 10.1016/j.ins.2017.11.048
[102]	Deng J, Berg A C, Fei-Fei L. Hierarchical semantic indexing for large scale image retrieval. In: Proceedings of the 2011 Computer Vision and Pattern Recognition. Colorado Springs, USA: IEEE, 2011. 785−792
[103]	Gao X Y, Hoi S C H, Zhang Y D, Wan J, Li J T. SOML: Sparse online metric learning with application to image retrieval. In: Proceedings of the 28th AAAI Conference on Artificial Intelligence. Québec City, Canada: ACM, 2014. 1206−1212
[104]	Wang S Y, Ding Z M, Fu Y. Coupled marginalized auto-encoders for cross-domain multi-view learning. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. New York, USA: IJCAI/AAAI Press, 2016. 2125−2131
[105]	Duan Q Y, Zhang L, Zuo W M. From face recognition to kinship verification: An adaptation approach. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCVW). Venice, Italy: IEEE, 2017. 1590−1598
[106]	Liang J Y, Guo J L, Lao S Y, Li J. Using deep relational features to verify kinship. In: Proceedings of the 2nd CCF Chinese Conference on Computer Vision. Tianjin, China: Springer, 2017. 563−573
[107]	Zhang H M, Wang X L, Kuo C C J. Deep kinship verification VIA appearance-shape joint prediction and adaptation-based approach. In: Proceedings of the 2019 IEEE International Conference on Image Processing. Taipei, China: IEEE, 2019. 3856−3860
[108]	Wu T, Turaga P, Chellappa R. Age estimation and face verification across aging using landmarks. IEEE Transactions on Information Forensics and Security, 2012, 7(6): 1780-1788 doi: 10.1109/TIFS.2012.2213812
[109]	Li W H, Zhang Y Q, Lv K C, Lu J W, Feng J J, Zhou J. Graph-based kinship reasoning network. In: Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME). London, UK: IEEE, 2020. 1−6
[110]	Song C H, Yan H B. KINMIX: A data augmentation approach for kinship verification. In: Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME). London, UK: IEEE, 2020. 1−6
[111]	Suh Y, Han B, Kim W, Lee K M. Stochastic class-based hard example mining for deep metric learning. In: Proceedings of the 2019 IEEE/CVF Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 7251−7259
[112]	Ertugrul I Ö, Dibeklioglu H. What will your future child look like? Modeling and synthesis of hereditary patterns of facial dynamics. In: Proceedings of the 12th International Conference on Automatic Face and Gesture Recognition. Washington, USA: IEEE, 2017. 33−40
[113]	Dehghan A, Ortiz E G, Villegas R, Shah M. Who do I look like? Determining parent-offspring resemblance via gated autoencoders. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014. 1757−1764
[114]	Wang S Y, Robinson J P, Fu Y. Kinship verification on families in the wild with marginalized denoising metric learning. In: Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG2017). Washington, USA: IEEE, 2017. 216−221
[115]	López M B, Boutellaa E, Hadid A. Comments on the “kinship face in the wild” data sets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(11): 2342-2344 doi: 10.1109/TPAMI.2016.2522416
[116]	何星辰, 郭勇, 李奇龙, 高唱. 基于深度学习的抗年龄干扰人脸识别. 自动化学报, 2022, 48(3): 877-886 doi: 10.16383/j.aas.c190256 He Xing-Chen, Guo Yong, Li Qi-Long, Gao Chang. Age invariant face recognition based on deep learning. Acta Automatica Sinica, 2022, 48(3): 877-886 doi: 10.16383/j.aas.c190256
[117]	张婷, 李玉鑑, 胡海鹤, 张亚红. 基于跨连卷积神经网络的性别分类模型. 自动化学报, 2016, 42(6): 858-865 doi: 10.16383/j.aas.2016.c150658 Zhang Ting, Li Yu-Jian, Hu Hai-He, Zhang Ya-Hong. Gender classification model based on cross-connected convolutional neural networks. Acta Automatica Sinica, 2016, 42(6): 858-865 doi: 10.16383/j.aas.2016.c150658
[118]	罗浩, 姜伟, 范星, 张思朋. 基于深度学习的行人重识别研究进展. 自动化学报, 2019, 45(11): 2032-2049 doi: 10.16383/j.aas.c180154 Luo Hao, Jiang Wei, Fan Xing, Zhang Si-Peng. A survey on deep learning based person re-identification. Acta Automatica Sinica, 2019, 45(11): 2032-2049 doi: 10.16383/j.aas.c180154
[119]	李琛. 人脸本征图像分解及其应用 [博士学位论文], 浙江大学, 中国, 2017. Li Chen. Facial Intrinsic Image Decomposition and its Application [Ph.D. dissertation], Zhejiang University, China, 2017.
[120]	Sataloff R T. Genetics of the voice. Journal of Voice, 1995, 9(1): 16-19 doi: 10.1016/S0892-1997(05)80218-8
[121]	Van Gysel W D, Vercammen J, Debruyne F. Voice similarity in identical twins. Acta Oto-Rhino-Laryngologica Belgica, 2001, 55(1): 49-55
[122]	Whiteside S P, Rixon E. Speech tempo and fundamental frequency patterns: A case study of male monozygotic twins and an age-and sex-matched sibling. Logopedics Phoniatrics Vocology, 2013, 38(4): 173-181 doi: 10.3109/14015439.2012.742562
[123]	Debruyne F, Decoster W, Van Gijsel A, Vercammen J. Speaking fundamental frequency in monozygotic and dizygotic twins. Journal of Voice, 2002, 16(4): 466-471 doi: 10.1016/S0892-1997(02)00121-2
[124]	Nolan F, McDougall K, Hudson T. Some acoustic correlates of perceived (Dis) similarity between same-accent voices. In: Proceedings of the 17th International Congress of Phonetic Sciences. Hong Kong, China: ICPhS, 2011. 1506−1509
[125]	Weirich M, Lancia L. Perceived auditory similarity and its acoustic correlates in twins and unrelated speakers. In: Proceedings of the 17th International Congress of Phonetic Sciences. Hong Kong, China: ICPhS, 2011. 2118−2121
[126]	Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada: ACM, 2014. 2672−2680
[127]	Pan S J, Yang Q. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359 doi: 10.1109/TKDE.2009.191
[128]	Wang Y Q, Yao Q M, Kwok J T, Ni L M. Generalizing from a few examples: A survey on few-shot learning. ACM Computing Surveys, 2021, 53(3): Article No. 63