基于域适应卷积神经网络的人脸表情识别

doi:10.19678/j.issn.1000-3428.0054950

摘要/Abstract

摘要： 在利用卷积神经网络进行人脸表情识别时，可借助其他数据集进行辅助训练以应对缺少标记数据的情况，但源域数据库和目标域数据库之间的数据分布差异会影响分类正确率。为此，以AlexNet网络为原型构建基于域适应的卷积神经网络结构。通过引入包含注意力机制的SE模块进行特征重标定，同时利用域适应方法减小领域差异性。在人脸识别公开数据集上的实验结果表明，与AlexNet和GoingDeep等网络相比，该网络能够以较少的参数量获得较高的识别正确率。

关键词: 卷积神经网络, 人脸表情识别, 数据分布, 域适应, 迁移学习

Abstract: In facial expression recognition using Convolutional Neural Network(CNN),other data sets can assist in training to deal with the lack of tag data.However,the classification accuracy will be affected by the data distribution differences between the source domain database and the target domain database.To address the problem,this paper constructs a domain adaptation-based convolutional neural network structure modeled after AlexNet.The network introduces a SE module including the attention mechanism for feature re-location,and uses the domain adaption method to reduce the differences between domains.Experimental results on the public data sets of facial expression recognition show that the proposed network can achieve a higher recognition accuracy rate than AlexNet and GoingDeep with fewer parameters.

Key words: Convolutional Neural Network(CNN), facial expression recognition, data distribution, domain adaptation, transfer learning

中图分类号:

TP391

亢洁, 李佳伟, 杨思力. 基于域适应卷积神经网络的人脸表情识别[J]. 计算机工程, 2019, 45(12): 201-206.

KANG Jie, LI Jiawei, YANG Sili. Facial Expression Recognition Based on Convolutional Neural Network with Domain Adaption[J]. Computer Engineering, 2019, 45(12): 201-206.

https://www.ecice06.com/CN/Y2019/V45/I12/201

图/表 11

20191214133435

20191214133438

20191214133441

20191214133443

20191214133446

20191214133448

20191214133451

20191214133454

20191214133457

20191214133459

20191214133502

参考文献

[1] MEHRABIAN A,RUSSELL J A.An approach to environ-mental psychology[M].Cambridge,USA:MIT Press,1974.
[2] ZHANG Yanliang,LU Bing.Micro-expression recognition method based on information gain feature selection[J].Computer Engineering,2019,45(5):261-266.(in Chinese)张延良,卢冰.基于信息增量特征选择的微表情识别方法[J].计算机工程,2019,45(5):261-266.
[3] ZHAO Guoying,PIETIKÃINEN M.Dynamic texture recognition using local binary patterns with an application to facial expressions[J].Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):915-928.
[4] DAHMANE M,MEUNIER J.Emotion recognition using dynamic grid-based HoG features[C]//Proceedings of International Conference on Automatic Face and Gesture Recognition.Washington D.C.,USA:IEEE Press,2011:884-888.
[5] BARTLETT M S,LITTLEWORT G,FRANK M,et al.Recognizing facial expression:machine learning and application to spontaneous behavior[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2005:568-573.
[6] CORTES C,VAPNIK V N.Support vector networks[J].Machine Learning,1995,20(3):273-297.
[7] HUANG Zhong,HU Min,LIU Juan.Facial expression recognition method based on multi-feature decision-level fusion[J].Computer Engineering,2015,41(10):171-176.(in Chinese)黄忠,胡敏,刘娟.基于多特征决策级融合的表情识别方法[J].计算机工程,2015,41(10):171-176.
[8] PAN Wusheng,HUANG Yushui.A facial expression recognition method based on gaussian process latent variable method[J].Computer Simulation,2018,35(3):341-344.(in Chinese)潘武生,黄玉水.一种基于高斯过程隐变量模型的表情识别方法[J].计算机仿真,2018,35(3):341-344.
[9] HE Zhichao,ZHAO Longzhang,CHEN Chuang.Convolution neural network with multi-resolution feature fusion for facial expression recognition[J].Laser & Optoelectronics Progress,2018,55(7):370-375.(in Chinese)何志超,赵龙章,陈闯.用于人脸表情识别的多分辨率特征融合卷积神经网络[J].激光与光电子学进展,2018,55(7):370-375.
[10] CAI Jie,MENG Zibo,KHAN A S,et al.Island loss for learning discriminative features in facial expression recognition[C]//Proceedings of the 13th IEEE Inter-national Conference on Automatic Face and Gesture Recognition.Washington D.C.,USA:IEEE Press,2018:302-309.
[11] DAI Wenyuan,YANG Qiang,XUE Guirong,et al.Boosting for transfer learning[C]//Proceedings of the 24th International Conference on Machine Learning.New York,USA:ACM Press,2007:193-200.
[12] SHEN Junge,ZHENG Enrang,CHENG Zhiyong,et al.Assisting attraction classification by harvesting Web data[J].IEEE Access,2017,10(5):1600-1608.
[13] ZHAO Zhongtang,CHEN Yiqiang,LIU Junfa,et al.Cross-mobile ELM based activity recognition[J].International Journal of Engineering and Industries,2010,1(1):30-38.
[14] YAN Keyu,ZHENG Wenming,CUI Zhen,et al.Cross-database facial expression recognition via unsupervised domain adaptive dictionary learning[C]//Proceedings of International Conference on Neural Information Processing.Berlin,Germany:Springer,2016:427-434.
[15] SUN Baochen,SAENKO K.Deep coral:correlation alignment for deep domain adaptation[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2016:443-450.
[16] MIAO Yunqian,ARAUJO R,KAMEL M S.Cross-domain facial expression recognition using supervised kernel mean matching[C]//Proceedings of the 11th International Conference on Machine Learning and Applications.Washington D.C.,USA:IEEE Press,2012:326-332.
[17] HU Jie,SHEN Li,ALBANIE S,et al.Squeeze-and-excitation networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:7132-7141.
[18] GRETTON A,SEJDINOVIC D,STRATHMANN H,et al.Optimal kernel choice for large-scale two-sample tests[M]//PEREIRA F,BURGES C J C,BOTTOU L,et al.Advances in neural information processing systems.Cambridge,USA:MIT Press,2012:1205-1213.
[19] IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of International Conference on Machine Learning.New York,USA:ACM Press,2015:448-456.
[20] KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNet classification with deep convolutional neural networks[J].Advances in Neural Information Processing Systems,2012,25(2):1097-1105.
[21] SEJDINOVIC D,SRIPERUMBUDUR B,GRETTON A,et al.Equivalence of distance-based and RKHS-based statistics in hypothesis testing[J].The Annals of Statistics,2013,41(5):2263-2291.
[22] GRETTON A.A kernel two-sample test[J].Journal of Machine Learning Research,2012,13(1):723-773.
[23] LYONS M J,AKAMATSU S,KAMACHI M,et al.Coding facial expressions with Gabor wavelets[C]//Proceedings of the 3rd IEEE International Conference on Automatic Face and Gesture Recognition.Washington D.C.,USA:IEEE Press,1998:200-205.
[24] LI Shan,DENG Weihong,DU Junping.Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2584-2593.
[25] 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]//Proceedings of Computer Vision and Pattern Recognition Workshops.Washington D.C.,USA:IEEE Press,2010:94-101.
[26] MOLLAHOSSEINI A,CHAN D,MAHOOR M H.Going deeper in facial expression recognition using deep neural networks[C]//Proceedings of 2016 IEEE Winter Conference on Applications of Computer Vision.Washington D.C.,USA:IEEE Press,2016:1-10.

选择文件类型/文献管理软件名称

选择包含的内容