2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于流形结构的人脸民族特征研究

王存睿 张庆灵 段晓东 王元刚 李泽东

王存睿, 张庆灵, 段晓东, 王元刚, 李泽东. 基于流形结构的人脸民族特征研究. 自动化学报, 2018, 44(1): 140-159. doi: 10.16383/j.aas.2018.c160585
引用本文: 王存睿, 张庆灵, 段晓东, 王元刚, 李泽东. 基于流形结构的人脸民族特征研究. 自动化学报, 2018, 44(1): 140-159. doi: 10.16383/j.aas.2018.c160585
WANG Cun-Rui, ZHANG Qing-Ling, DUAN Xiao-Dong, WANG Yuan-Gang, LI Ze-Dong. Research of Face Ethnic Features from Manifold Structure. ACTA AUTOMATICA SINICA, 2018, 44(1): 140-159. doi: 10.16383/j.aas.2018.c160585
Citation: WANG Cun-Rui, ZHANG Qing-Ling, DUAN Xiao-Dong, WANG Yuan-Gang, LI Ze-Dong. Research of Face Ethnic Features from Manifold Structure. ACTA AUTOMATICA SINICA, 2018, 44(1): 140-159. doi: 10.16383/j.aas.2018.c160585

基于流形结构的人脸民族特征研究

doi: 10.16383/j.aas.2018.c160585
基金项目: 

国家自然科学基金 61370146

国家自然科学基金 61672132

详细信息
    作者简介:

    张庆灵 东北大学教授.主要研究方向为网络控制与生物数学.E-mail:zhangql@mail.neu.edu.cn

    段晓东 大连民族大学教授.主要研究方向为模式识别与数据挖掘.E-mail:duanxd@dlnu.cn

    王元刚 大连理工大学博士研究生.主要研究方向为人脸识别技术.E-mail:wangyg@mail.neu.edu.cn

    李泽东 东北大学博士研究生.主要研究方向为模式识别与机器智能.E-mail:lizd@mail.neu.edu.cn

    通讯作者:

    王存睿 大连民族大学副教授.主要研究方向为数据挖掘与模式识别.本文通信作者.E-mail:cunrui@mail.neu.edu.cn

Research of Face Ethnic Features from Manifold Structure

Funds: 

National Natural Science Foundation of China 61370146

National Natural Science Foundation of China 61672132

More Information
    Author Bio:

    Professor at Northeastern University. His research interest covers network control and biological mathematics

    Professor at Dalian Minzu University. His research interest covers pattern recognition and data mining

    Ph. D. candidate at Dalian University of Technology. His main research interest is face recognition technology

    Ph. D. candidate at Northeastern University. His research interest covers pattern recognition and machine intelligence

    Corresponding author: WANG Cun-Rui Associate professor at Dalian Minzu University. His research interest covers data mining and pattern recognition. Corresponding author of this paper
  • 摘要: 人脸民族特征选取与分析是人脸识别与人类学重要研究方向之一.本文建立了中国三个民族人脸数据库,通过流形结构来研究和分析人脸的民族特征.首先,在体质人类学定义的人脸几何特征指标进行流形分析,未形成按语义分布的子流形.因此本文将人脸特征扩至全部组合的长度、角度和比例特征进行分析,利用mRMR算法对2926个长度特征、21万余个角度特征、427万个比例特征中冗余特征进行筛选,加上人类学指标及混合筛选的数据集共形成5个数据集.利用LPP、Isomap、LE、PCA和LDA等流形方法分析5数据集,其中的4个数据集都形成了民族语义的子流形分布.为验证筛选特征指标的有效性,本文利用分类算法J48、SVM、RBF network、Naive Bayes、Bayes network在Weka平台对数据集以族群语义作为类别进行交叉验证实验,实验结果表明混合特征的人脸数据集族群分类平均准确率最高,且比例特征分类指标优于其他特征数据集.本文通过大量实验揭示了民族人脸数据可在子空间内形成按民族语义分布的子流形结构.中国三个民族人脸特征在低维空间存在不同民族语义的子流形,通过流形分析和特征筛选构建的人脸测量指标不仅可为人脸族群分析提供方法,同时也将丰富和补充体质人类学的相关研究工作.
    1)  本文责任编委 杨健
  • 图  1  人脸识别过程中的属性识别顺序[6]

    Fig.  1  The cognitive order of face recognition[6]

    图  2  人脸年龄和表情属性的流形语义分布

    Fig.  2  Semantic distribution of age and facial expression attributes

    图  3  人类学采用的人脸长度特征

    Fig.  3  Facial length attribute in anthropology

    图  4  壮族(浅色)、维吾尔族(中浅色)、朝鲜族(深色)男女流形结构

    Fig.  4  Male and female manifold structure of three ethnies (Zhuang, Uygur, Korean)

    图  5  人脸数据采集环境

    Fig.  5  The environment and setup for facial image collection

    图  6  三个民族正面人脸数据集

    Fig.  6  The samples of facial images from three ethnics

    图  7  本文采用人脸特征点及定位

    Fig.  7  Facial landmark detection in this paper

    图  8  人脸特征维度示意图

    Fig.  8  Feature dimension compansion of common facial attributes

    图  9  高维人脸长度特征流形分布

    Fig.  9  Facial face length feature manifold distribution

    图  10  多民族人脸流形分析流程

    Fig.  10  The schema of multi-ethnic facial manifold analysis

    图  11  不同权重的人脸长度几何特征

    Fig.  11  The demonstration of 4 types of distance-based features

    图  12  筛选长度特征数据集的流形结构

    Fig.  12  The illustration of ethnic manifold structure based on selected features

    图  13  不同权重的人脸角度几何特征

    Fig.  13  The demonstration of 4 types of angular features

    图  14  角度主分量的数据流形分布

    Fig.  14  The principal component distribution of angular features

    图  15  壮族(浅色)、维吾尔族(中浅色)、朝鲜族(深色)男女流形结构

    Fig.  15  The male and female manifold structure of the Zhuang (light), Uygur (middle light) and Korean (dark)

    图  16  不同权重的人脸比例特征

    Fig.  16  The demonstration of types of ratio-features

    图  17  比例特征在低维空间分布图

    Fig.  17  The distribution of ratio-features in low dimensional space

    图  18  指标中特征点在面部分布比例图

    Fig.  18  The distribution of landmarks from different facial area

    图  19  比例特征在低维空间分布图

    Fig.  19  The distribution of ratio-features in low dimensional space

    图  20  不同指标下的民族判别决策树

    Fig.  20  Ethnic classification decision trees with different indicators

    图  21  不同类型特征增量下的准确率变化曲线

    Fig.  21  The recongnition rates comparison based on different types of features

    表  1  3个民族人口数量和比例[53]

    Table  1  The demographical comparison of the three ethnic groups[53]

    民族 人口数量 人口比例(%) 地理位置
    壮族 16 926 381 1.27 广西
    维吾尔族 10 069 346 0.76 新疆
    朝鲜族 1 830 929 0.14 吉林
    下载: 导出CSV

    表  2  筛选的几何特征

    Table  2  The selected geometric features

    长度几何特征 角度几何特征 比例几何特征
    特征维度 2 926 219 450 4 279 275
    筛选后特征维度 195 250 500
    下载: 导出CSV

    表  3  mRMR筛选的4个权重范围的长度特征

    Table  3  The selected distance-based features by mRMR

    权重权重区域特点
    1眼裂宽度、眉眼距离、眉与鼻翼距离、鼻翼长度特征
    2眉毛各长度特征、额头宽度、鼻翼与眼内角距离、下唇厚度
    3更为精细的鼻部和嘴部几何长度特征
    4嘴部与眉尖距离, 嘴部与下颚距离, 眉与耳朵距离
    人类学常用指标体系头长、头宽、面宽、鼻宽、鼻高、唇厚、口裂宽、内眼角宽、外眼角间距、内眼角间距、颧间宽、下颌长度、下颌角间距
    下载: 导出CSV

    表  4  mRMR筛选的4个权重范围的角度特征

    Table  4  The selected angle features by mRMR

    权重角点权重区域特点
    1眉尖点眉毛与内眼角点和鼻根部形成的角度关系
    2鼻根点, 眉尖点, 形成鼻翼与鼻眼角度关系热区,
    耳位置点通过角度度量眉眼距离关系
    3眉、眼角点眼裂角度, 眉眼之间角度关系, 鼻翼角度关系
    4眉和嘴部更为精细的眼鼻嘴之间定位关系
    下载: 导出CSV

    表  5  体质人类学定义的15个正脸指数

    Table  5  The 15 Physical anthropological definition of 15 frontal face index

    序号指数特征名称
    1 头宽高指数
    2 额顶宽指数
    3 头面宽指数
    4 形态面指数
    5 形态上面指数
    6 容貌面指数
    7 颧下颌宽度指数
    8 颧额宽指数
    9 容貌上面指数
    10 额面指数
    11 容貌上面高
    12 头面高指数
    13 鼻指数
    14 鼻宽深指数
    15 唇指数
    下载: 导出CSV

    表  6  不同权重的比例特征

    Table  6  The index features with different weight

    序号权重区域特点权重值
    (眼裂高度) / (眉眼距离)0.329
    1(眼裂高度) / (鼻翼与眉毛距离)0.362
    (鼻翼与眉毛距离)/ (嘴部与眉尖)0.312
    (鼻翼与眼内角点距离) / (额头高度)0.35
    (眼裂高度) / (鼻翼与眉毛距离)0.302
    2(鼻翼长度) / (眉眼距离)0.302
    (眉眼距离) / (眉毛与鼻翼距离)0.301
    (鼻翼长度) / (眉毛与嘴部距离)0.302
    (眼裂高度) / (鼻翼与眉毛距离)0.30
    3(鼻翼与眼内角点距离) / (额头高度)0.294
    (鼻翼距离) / (嘴巴与眼外角点距离)0.297
    (眉间距) / (鼻翼与眼内角距离)0.297
    (眼裂高度) / (鼻翼与眼内角点距离)0.274
    4(眉毛与上唇距离) / (眉毛与下唇距离)0.283
    (鼻翼长度) / (眼睛与下颌距离)0.281
    下载: 导出CSV

    表  7  长度、角度筛选出的51个人脸几何特征

    Table  7  The selected 51 geometric features from distance-based and angular attributes

    ID类型详细权重ID类型详细权重
    1I(49, 57)/(22, 7)0.66927I(39, 43)/(7, 22)0.299
    2I(35, 47)/(23, 51)0.36228I(49, 69)/(34, 72)0.296
    3I(37, 51)/(16, 24)0.3529I(22, 73)/(21, 64)0.298
    4I(39, 43)/(22, 36)0.32930I(49, 52)/(15, 7)0.296
    5I(50, 71)/(33, 60)0.3331I(35, 47)/(28, 51)0.298
    6I(49, 52)/(5, 17)0.31232I(25, 50)/(21, 27)0.292
    7I(22, 76)/(21, 54)0.31233I(37, 51)/(14, 19)0.294
    8I(51, 59)/(22, 45)0.30234A∠(21, 55, 26)0.289
    9I(31, 35)/(37, 51)0.30535I(39, 43)/(28, 51)0.287
    10A∠(51, 59, 27)0.31136I(49, 52)/(22, 38)0.289
    11I(39, 43)/(20, 58)0.30237I(49, 76)/(35, 72)0.289
    12I(37, 59)/(14, 22)0.30238I(50, 52)/(22, 60)0.286
    13I(17, 36)/(23, 50)0.30239I(35, 47)/(23, 50)0.287
    14I∠(31, 22, 33)0.29740I(49, 52)/(7, 35)0.287
    15I(49, 52)/(60, 74)0.30441I(22, 53)/(21, 50)0.284
    16I(50, 55)/(17, 55)0.30142I(50, 70)/(33, 60)0.285
    17I(18, 21)/(33, 49)0.30243A∠(17, 49, 21)0.285
    18I(35, 60)/(21, 54)0.30544I(37, 51)/(16, 24)0.285
    19I(39, 43)/(23, 51)0.30345I(37, 51)/(16, 24)0.282
    20I(37, 51)/(18, 25)0.30146A∠(51, 25, 59)0.283
    21I(22, 73)/(21, 76)0.34747A∠(35, 29, 49)0.284
    22I(49, 52)/(24, 66)0.30348I(49, 57)/(22, 43)0.282
    23I(49, 57)/(14, 22)0.30249I(39, 43)/(19, 49)0.282
    24I(50, 57)/(29, 61)0.29650A∠(21, 49, 25)0.281
    25A∠(21, 36, 22)0.29951I(31, 35)/(24, 51)0.279
    26A∠(22, 60, 50)0.298
      注: I代表长度, A代表角度
    下载: 导出CSV

    表  8  混合指标中的特征边与点的频繁项集

    Table  8  The frequent itemsets of the characteristic edge and point in the mixed attributes

    ID支持度说明ID支持度部位
    139 ~ 436眼裂12216
    249 ~ 526鼻翼长度24916
    337 ~ 514鼻眼距离35114
    435 ~ 473眼裂42111
    549 ~ 573鼻翼宽度55010
    622 ~ 732眉嘴距离6359
    731 ~ 352眼裂7377
    814 ~ 222额头高度18437
    916 ~ 242额头高度29527
    1021 ~ 542眉鼻距离110396
    1123 ~ 502眉鼻距离211245
    1223 ~ 512眉鼻距离312574
    13234
    14313
    15463
    16143额头
    17163额头
    18732
    19542
    下载: 导出CSV

    表  9  J48交叉验证学习后结果指标

    Table  9  J48 cross validation results after feature learning

    DataSetSexTP RateFP RatePrecisionRecallF-MeasureAUC
    AM0.7530.1230.7530.7530.7530.814
    BM0.8330.0830.8340.8330.8330.879
    CM0.920.040.9210.9210.9210.935
    DM0.900.050.9020.90.900.935
    EM0.960.020.960.960.960.975
    AF0.7270.1370.7250.7270.7240.775
    BF0.7730.1130.7760.7730.7730.863
    CF0.8130.0930.8140.8130.8120.853
    DF0.7670.1170.7650.7670.7640.844
    EF0.8130.0930.8180.8130.8140.888
    下载: 导出CSV

    表  10  Naive Bayes实验结果

    Table  10  Naive Bayes experimental results

    DataSetSexTP RateFP RatePrecisionRecallF-MeasureAUC
    AM0.820.090.8210.820.820.927
    BM0.900.050.9030.900.9010.96
    CM0.960.020.960.960.960.993
    DM0.9670.0170.9680.9670.9670.992
    EM0.9730.0130.9740.9730.9730.999
    AF0.7730.1130.7790.7730.7720.882
    BF0.7530.1230.7550.7530.7500.902
    CF0.8930.0530.8940.8930.8930.947
    DF0.8870.0570.8890.8870.8870.956
    EF0.920.040.9210.920.920.979
    下载: 导出CSV

    表  11  Bayes network实验结果

    Table  11  Bayes network experimental results

    DataSetSexTP RateFP RatePrecisionRecallF-MeasureAUC
    AM0.7930.1030.7930.7930.7930.923
    BM0.8930.0530.8970.8930.8940.962
    CM0.9670.0170.9670.9670.9670.995
    DM0.9670.0170.9670.9670.9670.992
    EM0.9670.0170.9670.9870.9871.0
    AF0.7330.1330.7350.7330.7340.883
    BF0.7670.1170.7660.7670.7660.898
    CF0.8870.0570.8880.8870.8870.951
    DF0.9000.050.9010.90.90.964
    EF0.9130.0430.9140.9130.9130.983
    下载: 导出CSV

    表  12  RBF network实验结果

    Table  12  RBF network experimental results

    DataSetSexTP RateFP RatePrecisionRecallF-MeasureAUC
    AM0.7730.1130.7750.7730.7730.871
    BM0.9130.0430.9150.9130.9140.947
    CM0.9670.0170.9670.9670.9670.978
    DM0.9730.0130.9740.9730.9730.976
    EM0.9930.0030.9930.9930.9930.994
    AF0.7530.1230.7530.7530.7530.866
    BF0.8070.0970.8050.8070.8050.904
    CF0.9000.0500.9000.9000.9000.937
    DF0.8930.0530.8930.8930.8930.943
    EF0.9070.0470.9090.9070.9070.94
    下载: 导出CSV

    表  13  SVM中LibSVM实验结果

    Table  13  SVM in LibSVM experimental results

    DataSetSexTP RateFP RatePrecisionRecallF-MeasureAUC
    AM0.7730.1130.7750.7730.7720.83
    BM0.820.090.8230.820.8230.865
    CM0.860.070.8580.860.8570.895
    DM0.9330.0330.9340.9330.9330.95
    EM0.9530.0230.9530.9530.9530.965
    AF0.7330.1330.7520.7330.7340.8
    BF0.7200.140.7580.720.7130.79
    CF0.6670.1670.7150.6670.6080.75
    DF0.8600.070.8620.860.8590.895
    EF0.920.040.9220.920.920.94
    下载: 导出CSV

    表  14  SVM中SMO实验结果

    Table  14  SVM in SMO experimental results

    DataSetSexTP RateFP RatePrecisionRecallF-MeasureAUC
    AM0.8930.0530.8950.8930.8930.944
    BM0.9670.0170.9670.9670.9670.982
    CM0.9670.0170.9670.9670.9670.983
    DM0.9730.0130.9740.9730.9730.985
    EM0.9730.0130.9730.9730.9730.985
    AF0.8670.0670.8680.8670.8670.922
    BF0.9070.0470.9070.9070.9070.947
    CF0.9070.0470.9070.9070.9070.943
    DF0.9330.0330.9340.9330.9340.965
    EF0.9530.0230.9540.9530.9530.97
    下载: 导出CSV

    表  15  SVM中SMO实验结果

    Table  15  SVM in SMO experimental results

    性别J48Naive BayesBayesNet
    M(20长度特征)80.00±1.8389.33±1.0479.30±1.62
    M(195长度特征)83.33±2.2190.00±1.0689.33±0.69
    M(250角度特征)92.00±1.0596.00±0.5596.70±0.85
    M(400角度特征)90.00±1.1196.70±0.4796.70±0.28
    M(51混合特征)96.00±0.5597.33±0.2198.67±0.53
    F(20长度特征)72.67±2.3177.33±1.4473.33±1.94
    F(195长度特征)77.33±1.5175.33±1.2176.67±1.20
    F(250角度特征)81.33±2.7889.33±0.9588.67±0.47
    F(400角度特征)76.67±2.5188.67±0.5590.00±0.38
    F(51混合特征)81.33±2.1092.00±0.3591.33±0.32
    M(20长度特征)77.33±2.1789.33±1.6577.33±1.03
    M(195长度特征)91.33±0.9596.67±0.5482.00±0.99
    M(250角度特征)96.70±0.8596.70±0.5686.00±0.32
    M(400角度特征)97.30±0.3597.30±0.6193.30±0.52
    M(51混合特征)99.33±1.2597.33±0.4995.33±0.49
    F(20长度特征)75.33±2.8786.67±1.1973.33±1.67
    F(195长度特征)80.67±1.1490.67±1.2972.00±1.43
    F(250角度特征)90.00±1.1090.67±0.8866.67±1.08
    F(400角度特征)89.33±0.8593.33±1.3086.00±0.73
    F(51混合特征)90.67±0.9495.33±0.7692.00±0.89
    下载: 导出CSV
  • [1] Calder A J, Rhodes G, Johnson M, Haxby J. The Oxford Handbook of Face Perception. Oxford:Oxford University Press, 2011.
    [2] Bruce V, Young A. Understanding face recognition. British Journal of Psychology, 1986, 77(3):305-327 doi: 10.1111/bjop.1986.77.issue-3
    [3] 苏连成, 朱枫.一种新的全向立体视觉系统的设计.自动化学报, 2006, 32(1):67-72 http://www.aas.net.cn/CN/abstract/abstract15769.shtml

    Su Lian-Cheng, Zhu Feng. Design of a novel omnidirectional stereo vision system. Acta Automatica Sinica, 2006, 32(1):67-72 http://www.aas.net.cn/CN/abstract/abstract15769.shtml
    [4] O'Toole A J, Roark D A, Abdi H. Recognizing moving faces:a psychological and neural synthesis. Trends in Cognitive Sciences, 2002, 6(6):261-266 doi: 10.1016/S1364-6613(02)01908-3
    [5] Eberhardt J L, Dasgupta N, Banaszynski T L. Believing is seeing:the effects of racial labels and implicit beliefs on face perception. Personality and Social Psychology Bulletin, 2003, 29(3):360-370 doi: 10.1177/0146167202250215
    [6] Kumar N, Berg A, Belhumeur P N, Nayar S. Describable visual attributes for face verification and image search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(10):1962-1977 doi: 10.1109/TPAMI.2011.48
    [7] Demirkus M, Garg K, Guler S. Automated person categorization for video surveillance using soft biometrics. In: Proceedings of the 2010 SPIE 7667, biometric technology for human identification Ⅶ. Orlando, Florida, USA: SPIE, 2010. Article No. 76670P doi: 10.1117/12.851424
    [8] Senior A, Pankanti S, Hampapur A, Brown L, Tian Y L, Ekin A, Connell J, Shu C F, Lu M. Enabling video privacy through computer vision. IEEE Security and Privacy, 2005, 3(3):50-57 doi: 10.1109/MSP.2005.65
    [9] Ito T A, Bartholow B D. The neural correlates of race. Trends in Cognitive Sciences, 2009, 13(12):524-531 doi: 10.1016/j.tics.2009.10.002
    [10] 张继宗.中国体质人类学研究.北京:科学出版社, 2010.

    Zhang Ji-Zong. The Research of Chinese Physical Anthropology. Beijing:Science Press, 2010.
    [11] 席焕久.体质人类学.北京:知识产权出版社, 2012.

    Xi Huan-Jiu. Physical Anthropology. Beijing:Intellectual Property Publish House, 2012.
    [12] Bledsoe W W. Man-Machine Facial Recognition. Panoramic Research Inc. Palo Alto, CA, Report PRI: 22, 1966.
    [13] Kanade T. Picture Processing System by Computer Complex and Recognition of Human Faces[Ph. D. dissertation]. Kyoto University, Japan, 1973 http://www.researchgate.net/publication/239021259_Picture_Processing_by_Computer_Complex_and_Recognition_of_Human_Faces
    [14] Brunelli R, Poggio T. Face recognition:features versus templates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(10):1042-1052 doi: 10.1109/34.254061
    [15] Malpass R S, Kravitz J. Recognition for faces of own and other race. Journal of Personality and Social Psychology, 1969, 13(4):330-334 doi: 10.1037/h0028434
    [16] Lindsay D S, Jack P C, Christian M A. Other-race face perception. Journal of Applied Psychology, 1991, 76(4):587-589 doi: 10.1037/0021-9010.76.4.587
    [17] Li Z, Duan X, Zhang Q, Wang C R, Wang Y G, Liu W Q. Multi-ethnic facial features extraction based on axiomatic fuzzy set theory. Neurocomputing, 2017, 242:161-177 doi: 10.1016/j.neucom.2017.02.070
    [18] Hadid A, Pietikäinen M. Demographic classification from face videos using manifold learning. Neurocomputing, 2013, 100:197-205 doi: 10.1016/j.neucom.2011.10.040
    [19] Seung H S, Lee D D. The manifold ways of perception. Science, 2000, 290(5500):2268-2269 doi: 10.1126/science.290.5500.2268
    [20] Fu S Y, He H B, Hou Z G. Learning race from face:a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(12):2483-2509 doi: 10.1109/TPAMI.2014.2321570
    [21] Duan X D, Wang C R, Liu X D, Li Z J, Wu J, Zhang H L. Ethnic features extraction and recognition of human faces. In: Proceedings of the 2nd International Conference on Advanced Computer Control (ICACC). Shenyang, China: IEEE, 2010. 125-130
    [22] 段晓东, 王存睿, 刘向东, 刘慧.人脸的民族特征抽取及其识别.计算机科学, 2010, 37(8):276-279, 301 http://www.docin.com/p-1301615906.html

    Duan Xiao-Dong, Wang Cun-Rui, Liu Xiang-Dong, Liu Hui. Minorities features extraction and recognition of human faces. Computer Science, 2010, 37(8):276-279, 301 http://www.docin.com/p-1301615906.html
    [23] Li Z D, Duan X D, Zhang Q L. A novel survey based on multiethnic facial semantic web. TELKOMNIKA, 2013, 11(9):5076-5083 https://www.researchgate.net/profile/Qingling_Zhang4/publication/275415292_A_Novel_Survey_Based_on_Multiethnic_Facial_Semantic_Web/links/5675798408aebcdda0e46b5e.pdf?inViewer=0&pdfJsDownload=0&origin=publication_detail
    [24] 段晓东, 李泽东, 王存睿, 张庆灵, 刘晓东.基于AFS的多民族人脸语义描述与挖掘方法研究.计算机学报, 2016, 39(7):1435-1449 doi: 10.11897/SP.J.1016.2016.01435

    Duan Xiao-Dong, Li Ze-Dong, Wang Cun-Rui, Zhang Qing-Ling, Liu Xiao-Dong. Multi-ethnic face semantic description and mining method based on AFS. Chinese Journal of Computer, 2016, 39(7):1435-1449 doi: 10.11897/SP.J.1016.2016.01435
    [25] Turk M, Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 1991, 3(1):71-86 doi: 10.1162/jocn.1991.3.1.71
    [26] Belhumeur P N, Hespanha J P, Kriegman D J. Eigenfaces vs. fisherfaces:recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):711-720 doi: 10.1109/34.598228
    [27] Bartlett M S, Movellan J R, Sejnowski T J. Face recognition by independent component analysis. IEEE Transactions on Neural Networks, 2002, 13(6):1450-1464 doi: 10.1109/TNN.2002.804287
    [28] Yang J, Zhang D, Frangi A F, Yang J Y. Two-dimensional PCA:a new approach to appearance-based face representation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1):131-137 doi: 10.1109/TPAMI.2004.1261097
    [29] Li M, Yuan B Z. 2D-LDA:a statistical linear discriminant analysis for image matrix. Pattern Recognition Letters, 2005, 26(5):527-532 doi: 10.1016/j.patrec.2004.09.007
    [30] Tenenbaum J B, de Silva V, Langford J C. A global geometric framework for nonlinear dimensionality reduction. Science, 2000, 290(5500):2319-2323 doi: 10.1126/science.290.5500.2319
    [31] Belkin M, Niyogi P. Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation, 2003, 15(6):1373-1396 doi: 10.1162/089976603321780317
    [32] He X F, Niyogi X. Locality preserving projections. Neural Information Processing Systems, 2004, 16(4):153-160
    [33] He X F, Yan S C, Hu Y X, Niyogi P, Zhang H J. Face recognition using Laplacianfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3):328-340 doi: 10.1109/TPAMI.2005.55
    [34] He X F, Cai D, Yan S C, Zhang H J. Neighborhood preserving embedding. In: Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing, China: IEEE, 2005, 2: 1208-1213
    [35] 詹德川, 周志华.基于集成的流形学习可视化.计算机研究与发展, 2005, 42(9):1533-1537 http://www.cnki.com.cn/Article/CJFDTOTAL-WXJY201508008.htm

    Zhan De-Chuan, Zhou Zhi-Hua. Ensemble-based manifold learning for visualization. Journal of Computer Research and Development, 2005, 42(9):1533-1537 http://www.cnki.com.cn/Article/CJFDTOTAL-WXJY201508008.htm
    [36] 何力, 张军平, 周志华.基于放大因子和延伸方向研究流形学习算法.计算机学报, 2005, 28(12):2000-2009 doi: 10.3321/j.issn:0254-4164.2005.12.007

    He Li, Zhang Jun-Ping, Zhou Zhi-Hua. Investigating manifold learning algorithms based on magnification factors and principal spread directions. Chinese Journal of Computers, 2005, 28(12):2000-2009 doi: 10.3321/j.issn:0254-4164.2005.12.007
    [37] 曾宪华, 罗四维.动态增殖流形学习算法.计算机研究与发展, 2007, 44(9):1462-1468 https://www.wenkuxiazai.com/doc/d9249222a32d7375a417801c.html

    Zeng Xian-Hua, Luo Si-Wei. A dynamically incremental manifold learning algorithm. Journal of Computer Research and Development, 2007, 44(9):1462-1468 https://www.wenkuxiazai.com/doc/d9249222a32d7375a417801c.html
    [38] Chen S B, Zhao H F, Kong M, Luo B. 2D-LPP:a two-dimensional extension of locality preserving projections. Neurocomputing, 2007, 70(4-6):912-921 doi: 10.1016/j.neucom.2006.10.032
    [39] 张大明, 符茂胜, 罗斌.基于二维近邻保持嵌入的图像识别.模式识别与人工智能, 2011, 24(6):810-815 http://www.oalib.com/paper/4238112

    Zhang Da-Ming, Fu Mao-Sheng, Luo Bin. Image recognition with two-dimensional neighbourhood preserving embedding. Pattern Recognition and Artificial Intelligence, 2011, 24(6):810-815 http://www.oalib.com/paper/4238112
    [40] Li Z D, Zhang Q L, Duan X D, Wang C R, Shi Y. New semantic descriptor construction for facial expression recognition based on axiomatic fuzzy set. Multimedia Tools and Applications, 2017, 1:1-31 doi: 10.1007/s11042-017-4818-3
    [41] Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding. Science, 2000, 290(5500):2323-2326 doi: 10.1126/science.290.5500.2323
    [42] Li Z D, Zhang Q L, Duan X D, Wei W. Semantic knowledge based on fuzzy system for describing facial expression. In: Proceedings of the 2017 Chinese Control Conference. 2017: 9865-9870 http://www.researchgate.net/publication/320114803_Semantic_knowledge_based_on_fuzzy_system_for_describing_facial_expression
    [43] Guo G D, Fu Y, Dyer C R, Huang T S. Image-based human age estimation by manifold learning and locally adjusted robust regression. IEEE Transactions on Image Processing, 2008, 17(7):1178-1188 doi: 10.1109/TIP.2008.924280
    [44] Yan S C, Xu D, Zhang B Y, Zhang H J. Graph embedding: a general framework for dimensionality reduction. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE, 2005, 2: 830-837
    [45] 续爽, 贾云得.基于表情相似性的人脸表情流形.软件学报, 2009, 20(8):2191-2198 http://mall.cnki.net/magazine/Article/JSJF201702007.htm

    Xu Shuang, Jia Yun-De. Facial expression manifold based on expression similarity. Journal of Software, 2009, 20(8):2191-2198 http://mall.cnki.net/magazine/Article/JSJF201702007.htm
    [46] 李小林. 中国南方五个少数民族人群面部五官形态特征研究[硕士学位论文], 重庆医科大学, 中国, 2008 http://www.wanfangdata.com.cn/details/detail.do?_type=degree&id=Y1353533

    Li Xiao-Lin. Analysis of Morphous Characteristics of Facial Reconstruction and the Five Organs in Chinese South Five National Minorities Crowd[Master dissertation], Chongqing Medical University, China, 2008 http://www.wanfangdata.com.cn/details/detail.do?_type=degree&id=Y1353533
    [47] 赵明, 文建军, 赵霞, 孙嬿嬿.藏、蒙、土、回、汉五民族青年面部测量数据分析.青海医学院学报, 1995, 16(3):7-8 http://paper.usc.cuhk.edu.hk/Details.aspx?id=5247

    Zhao Ming, Wen Jian-Jun, Zhao Xia, Sun Yan-Yan. An analysis on measuring data of face in 169 young students of Tibetan, Mongolian, Tu, Huis, and Han nationality. Journal of Qinghai Medical College, 1995, 16(3):7-8 http://paper.usc.cuhk.edu.hk/Details.aspx?id=5247
    [48] 席焕久, 陈昭.人体测量方法.第2版.北京:科学出版社, 2010.

    Xi Huan-Jiu, Chen Zhao. Anthropometric Methods (Second edition). Beijing:Science Press, 2010.
    [49] Wang X, Liu X, Zhang L. A rapid fuzzy rule clustering method based on granular computing. Applied Soft Computing, 2014, 24(C):534-542 https://www.sciencedirect.com/science/article/pii/S156849461400369X
    [50] Heo J, Savvides M. Gender and ethnicity specific generic elastic models from a single 2D image for novel 2D pose face synthesis and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(12):2341-2350 doi: 10.1109/TPAMI.2011.275
    [51] Feng Ding-Cheng, Chen Feng, Xu Wen-Li. Detecting local manifold structure for unsupervised feature selection. Acta Automatica Sinica, 2014, 40(10):2253-2261 doi: 10.1016/S1874-1029(14)60362-1
    [52] 王朝云, 蒋刚毅, 郁梅, 陈芬.基于流形特征相似度的感知图像质量评价.自动化学报, 2016, 42(7):1113-1124 http://www.aas.net.cn/CN/Y2016/V42/I7/1113

    Wang Chao-Yun, Jiang Gang-Yi, Yu Mei, Chen Fen. Manifold feature similarity based perceptual image quality assessment. Acta Automatica Sinica, 2016, 42(7):1113-1124 http://www.aas.net.cn/CN/Y2016/V42/I7/1113
    [53] Huang D, Shan C, Ardabilian M, Wang Y, Chen L. Local binary patterns and its application to facial image analysis:a survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews. 2011, 41:765-781 doi: 10.1109/TSMCC.2011.2118750
    [54] Wang Y G, Duan X D, Liu X D, Wang C R, Li Z D. Semantic description method for face features of larger Chinese ethnic groups based on improved WM method. Neurocomputing, 2016, 175:515-528 doi: 10.1016/j.neucom.2015.10.089
    [55] Milborrow S, Nicolls F. Active shape models with SIFT descriptors and MARS. In: Proceedings of the 2014 International Conference on Computer Vision Theory and Applications (VISAPP). Lisbon, Portugal: IEEE, 2014. 380-387
    [56] Ding C, Peng H C. Minimum redundancy feature selection from microarray gene expression data. Journal of Bioinformatics and Computational Biology, 2005, 3(2):185-205 doi: 10.1142/S0219720005001004
    [57] Peng H C, Long F H, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8):1226-1238 doi: 10.1109/TPAMI.2005.159
    [58] 洪泉, 陈松灿, 倪雪蕾.子模式典型相关分析及其在人脸识别中的应用.自动化学报, 2008, 34(1):21-30 http://www.aas.net.cn/CN/abstract/abstract16043.shtml

    Hong Quan, Chen Song-Can, Ni Xue-Lei. Sub-pattern canonical correlation analysis with application in face recognition. Acta Automatica Sinica, 2008, 34(1):21-30 http://www.aas.net.cn/CN/abstract/abstract16043.shtml
    [59] 高全学, 潘泉, 梁彦, 张洪才, 程咏梅.基于描述特征的人脸识别研究.自动化学报, 2006, 32(3):386-392 http://www.aas.net.cn/CN/abstract/abstract15824.shtml

    Gao Quan-Xue, Pan Quan, Liang Yan, Zhang Hong-Cai, Cheng Yong-Mei. Face recognition based on expressive features. Acta Automatica Sinica, 2006, 32(3):386-392 http://www.aas.net.cn/CN/abstract/abstract15824.shtml
    [60] Bouckaert R R, Frank E, Hall M A, Holmes G, Pfahringer B, Reutemann P, Witten I H. WEKA-experiences with a java open-source project. The Journal of Machine Learning Research, 2010, 11:2533-2541 https://researchcommons.waikato.ac.nz/handle/10289/4766
    [61] Han J W, Kamber M, Pei J. Data Mining: Concepts and Techniques (Third edition). Amsterdam: Elsevier, 2011.
    [62] Quinlan J R. C4. 5: Programs for Machine Learning. San Mateo, CA, USA: Morgan Kaufmann Publishers, 1993.
    [63] Zhang M L, Peña J M, Robles V. Feature selection for multi-label naive Bayes classification. Information Sciences, 2009, 179(19):3218-3229 doi: 10.1016/j.ins.2009.06.010
    [64] Gopnik A, Glymour C, Sobel D M, Schulz L E, Kushnir T, Danks D. A theory of causal learning in children:causal maps and Bayes nets. Psychological Review, 2004, 111(1):3-32 doi: 10.1037/0033-295X.111.1.3
    [65] Kokshenev I, Braga A P. A multi-objective approach to RBF network learning. Neurocomputing, 2008, 71(7-9):1203-1209 doi: 10.1016/j.neucom.2007.11.021
    [66] Joachims T. Making Large Scale SVM Learning Practical[Ph. D. dissertation]. Universität Dortmund, Germany, 1999 http://www.researchgate.net/publication/28355923_Making_Large-Scale_SVM_Learning_Practical
    [67] Keerthi S S, Shevade S K, Bhattacharyya C, Murthy K R K. Improvements to Platt's SMO algorithm for SVM classifier design. Neural Computation, 2001, 13(3):637-649 doi: 10.1162/089976601300014493
  • 加载中
图(21) / 表(15)
计量
  • 文章访问数:  2773
  • HTML全文浏览量:  459
  • PDF下载量:  611
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-08-23
  • 录用日期:  2017-05-06
  • 刊出日期:  2018-01-20

目录

    /

    返回文章
    返回