[1]陈 斌,樊飞燕,张 睿.年龄算子深度稀疏融合扩展表情识别[J].南京师范大学学报(工程技术版),2023,23(03):043-52.[doi:10.3969/j.issn.1672-1292.2023.03.006]
　Chen Bin,Fan Feiyan,Zhang Rui.Age Operator Deep Sparse Fusion Extension of the Expression Recognition[J].Journal of Nanjing Normal University(Engineering and Technology),2023,23(03):043-52.[doi:10.3969/j.issn.1672-1292.2023.03.006]
点击复制

年龄算子深度稀疏融合扩展表情识别
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
23卷
期数:
2023年03期
页码:
043-52
栏目:
计算机科学与技术
出版日期:
2023-09-15

文章信息/Info

Title:
Age Operator Deep Sparse Fusion Extension of the Expression Recognition
文章编号:
1672-1292(2023)03-0043-10
作者:
陈 斌; 樊飞燕; 张 睿
(南京师范大学信息化建设管理处,江苏 南京 210023)
Author(s):
Chen Bin; Fan Feiyan; Zhang Rui
(Informatization Office, Nanjing Normal University, Nanjing 210023, China)
关键词:
表情识别; 深度稀疏; 融合扩展; 年龄算子; 机器学习; 卷积神经网络
Keywords:
expression recognition;  deep sparse;  fusion extension;  age operator;  machine learning;  convolutional neural network
分类号:
TP39
DOI:
10.3969/j.issn.1672-1292.2023.03.006
文献标志码:
A
摘要:
为解决不同年龄段的人群在表情特征上的特质差异,提出了年龄算子深度稀疏融合扩展表情识别模型. 该模型利用高层级形式的线性字典序列作为稀疏表示的输入信号,将输入对象以线性组合的方式构造训练集,并在所有求解中以稀疏级别为指标选择最优解,进一步通过卷积神经网络的卷积、池化和全连接处理,通过融合扩展策略解决数据集相似度高、数量不足及分布不均的问题. 在此基础上结合了年龄算子作为特征元素与表情特征一并提取并作为分类决策依据. 通过深度稀疏融合扩展,并利用年龄算子的人体测量模型、内部角度构算和皮肤皱纹检测作为表情特征提取附加因子,经过多数据集实验结果比对,证明了本算法跨数据集的有效性和稳定性,并通过代表性跨年龄表情分类算法横向比对,证明了本算法的优势. 该方法对跨年龄表情识别准确度和鲁棒性有较好效果,有一定研究价值和参考意义.
Abstract:
In order to solve the trait differences in expression characteristics of people at different ages, the age operator deep sparse fusion extended expression recognition model is proposed. The model uses the form of linear dictionary sequence as sparse input signal, the input object with linear combination of training set, and select the optimal solution, further by convolutional neural network convolution, pooling and full connection processing, through fusion extension strategy to solve the problem of data set similarity, insufficient quantity and uneven distribution, and on the basis of combining age operator as characteristic elements and expression features extraction and as the basis of classification decision. Through deep sparse fusion extension, the age operator anthropometric model, internal angle structure and skin wrinkles detection as expression feature extraction additional factors. The multiple data set experiment results prove the effectiveness and stability of the algorithm across data sets, and the representative across age expression classification algorithm transverse comparison proves the advantages of the algorithm. This method has good effects on the accuracy and robustness of cross-age expression recognition, and has certain research value and reference significance.

参考文献/References:

[1]ZHANG T,ZHENG W M,CUI Z,et al. A deep neural network-driven feature learning method for multi-view facial expression recognition[J]. IEEE Transactions on Multimedia,2016,18(12):2528-2536.
[2]YUAN X H,XIE L J,ABOUELENIEN M. A regularized ensemble framework of deep learning for cancer detection from multi-class,inbalanced training data[J]. Pattern Recognition,2018,77:160-172.
[3]FANG B F,ZHANG Q,WANG H,et al. Personality driven task allocation for emotional robot team[J]. International Journal of Machine Learning and Cybernetics,2018,9(12):1955-1962.
[4]MALATESTA C Z,IZARD C E,CULVER C,et al. Emotion communication skills in young,middle-aged,and older women[J]. Psychol Aging,1987,2:193-203.
[5]SULLIVAN S,RUFFMAN T. Emotion recognition deficits in the elderly[J]. International Journal of Neuroscience,2004,114,403-432.
[6]GONCALVES A R,FERNANDES C,PASION R,et al. Effects of age on the identification of emotions in facial expressions:A meta-analysis[J]. Peer J,2018,6:e5278.
[7]DANTCHEVA A,ELIA P,ROSS A. What else does your biometric datareveal?A survey on soft biometrics[J]. IEEE Transactions on Information Forensic Security,2016,11(3):441-467.
[8]MACEDO J,COSTA F,JEFERSSON A,et al. A benchmark methodology for child pornography detection[C]//2018 31st Conference on Graphics,Patterns and Images. Parana,Brazil,2018.
[9]KANADA T,COHN J F,TIAN Y L,et al. Comprehensive database for facial expression analysis[C]//Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition. Grenoble,France:IEEE,2000:46-53.
[10]LUCEY P,COHN J F,KANADE T,et al. The Extended Cohn-Kanade Dataset(CK+):A complete dataset for action unit and emotion-specified expression[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops. San Francisco,CA,USA:IEEE,2010:94-101.
[11]LYONS M,AKAMATSU S,KAMACHI M,et al. Coding facial expressions with Gabor wavelets[C]//Proceeding Third IEEE International Conference on Automatic Face and Gesture Recognition. Nara,Japan:IEEE,2018:200-205.
[12]PANTIC M,VALSTAR M,RADEMAKER R,et al. Web-based database for facial expression analysis[C]//2015 IEEE International Conference on Multimedia and Expo. Amsterdam,Netherlands:IEEE,2005.
[13]EKMAN P,ROLLS E T,PERRETT D I,et al. Facial expressions of emotion:An old controversy and new findings[J]. Philosophical Transactions:Biological Sciences,335(1273):69.
[14]GUO G D,GUO R,LI X. Facial expression recognition influenced by human aging[J]. IEEE Transactions on Affective Computing,2013,4(3):291-298.
[15]WANG S F,WU S,GAO Z,et al. Facial expression recognition through modeling age-related spatial patterns[J]. Multimedia Tools and Applications,2016,75(7):3937-3954.
[16]MALATESTA-MAGAI C,JONAS R,SHEPARD B,et al. Type A behavior pattern and emotion expression in younger and older adults[J]. Psychology and Aging,1992,7(4):551-561.
[17]YANG D,ZHOU Q,WEN J. Interactive two-stream graph neural network for skeleton-based action recognition[J]. Journal of Electronic Imaging,2021,30(3):033025.
[18]ZHU D H,DU B,ZHANG L P. Two-stream convolutional net-works for hyperspectral target detection[J]. IEEE Transactions on Geoscience and Remote Sensing,2021,59(8):6907-6921.
[19]TEJA R S P,TEJA K S,DUBEY S R,et al. Spontaneous facial micro-expression recognition using 3D spatiotemporal convolu-tional neural networks[C]//2019 International Joint Conference on Neural Networks. Budapest,Hungary,2019:1-8.
[20]ZACH C,POCK T,BISCHOF H. A duality based approach for realtime TV-L1 optical flow[C]//Joint Pattern Recognition Symposium. Berlin Heidelberg:Springer,2007:214-223.
[21]李勇,李小竹,蒋梦莹. 基于跨连接LeNet-5网络的面部表情识别[J]. 自动化学报,2018,44(1):176-182.
[22]GOYAL S J,UPADHYAY A K,JADON R S,et al. Reallife facical expression recognition systems:A review[J]. Smart Computing and Informatics,2018,77(1):311-331.
[23]WANG S F,LIU Z L,LÜ S L,et al. A natural visible and infrared facial expression database for expression recognition and emotion inference[J]. IEEE Transactions on Multimedia,2010,12(7):682-691.
[24]KELTNER D,EKMAN P. Facial Expression of Emotion[J]. Encyclopedia of Human Behavior,2012:173-183.
[25]孟昭兰. 情绪心理学[M]. 北京:北京大学出版社,2005.
[26]FU Y,LAM A,SATO I,et al. Adaptive spatial-spectral dictionary learning for hyperspectral image restoration[J]. Interna-tional Journal of Computer Vision,2017,122(2):228-245.
[27]陈斌,东一舟,朱晋宁. 非控场景下主成分稀疏表示与低秩分解的人脸识别[J]. 液晶与显示,2019,34(8):816-824.
[28]陈斌,朱晋宁,东一舟. 基于残差整流增强卷积神经网络的表情识别[J]. 液晶与显示,2020,35(12):1299-1308.
[29]SZEGEDY C,LIU W,JIA Y Q,et al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston,Massachusetts,2015:1-9.
[30]陈斌,朱晋宁. 双流增强融合网络微表情识别[J]. 智能系统学报,2013,18(2):360-371.
[31]SYEDA A R,YAZEED Y G,AHMAD J,et al. Automated facial expression recognition and age estimation using deep learning[J]. Computers Materials & Continua,2022,71(3):5235-5252.
[32]JO L,RACHEL A R,EMILIE M F R,et al. Caricaturing can improve facial expression recognition in low-resolution images and age-related macular degeneration[J]. Journal of Vision,2019,19(6):1-22.
[33]廖海斌,徐斌. 基于性别和年龄因子分析的鲁棒性人脸表情识别[J]. 计算机研究与发展,2021,58(3):528-538.
[34]FERNANDO A F,KEVIN H D,SILVIA R R,et al. Facial masks and soft-biometrics:Leveraging face recognition CNNs for age and gender prediction on mobile ocular images[J]. The Institution of Engineering and Technology,2021,10(5):562-580.

相似文献/References:

[1]谢 非,龚 俊,王元祥,等.基于肤色增强和分块PCA的人脸表情识别方法[J].南京师范大学学报(工程技术版),2017,17(02):049.[doi:10.3969/j.issn.1672-1292.2017.02.008]
　Xie Fei,Gong Jun,Wang Yuanxiang,et al.A Facial Expression Recognition Method Based onSkin Color Enhancement and Block PCA[J].Journal of Nanjing Normal University(Engineering and Technology),2017,17(03):049.[doi:10.3969/j.issn.1672-1292.2017.02.008]

备注/Memo

备注/Memo:
收稿日期:2023-06-25.
基金项目:江苏省现代教育技术研究智慧校园专项课题项目(2021-R-96609).
通讯作者:陈斌,博士,高级工程师,研究方向:模式识别、机器学习、大数据分析. E-mail:njnuchenbin@njnu.edu.cn
更新日期/Last Update: 2023-09-15