基于兴趣区域深度神经网络的静态面部表情识别

doi:10.3969/j.issn.0372-2112.2017.05.023

电子学报

基于兴趣区域深度神经网络的静态面部表情识别

孙晓, 潘汀

合肥工业大学计算机与信息学院, 安徽合肥 230009

收稿日期:2016-02-16 修回日期:2016-06-14 出版日期:2017-05-25
- 作者简介:
- 孙晓男,1980年出生,山东龙口人,博士,副教授,硕士生导师.研究方向为人机交互系统、情感计算与机器学习.E-mail:sunx@hfut.edu.cn;潘汀男,1995年出生,江苏连云港人,本科生.研究方向为深度学习,贝叶斯学习理论及其在计算机视觉与自然语言处理方面的应用.E-mail:neopenx@mail.hfut.edu.cn
- 基金资助:
- 安徽省自然科学基金 (No.1508085QF119）; 国家自然科学基金重点项目 (No.61432004）; 模式识别国家重点实验室开放课题 (No.NLPR201407345）; 中国博士后科学基金 (No.2015M580532）

Static Facial Expression Recognition System Using ROI Deep Neural Networks

SUN Xiao, PAN Ting

School of Computer and Information, Hefei University of Technology. Hefei, Anhui 230009, China

Received:2016-02-16 Revised:2016-06-14 Online:2017-05-25 Published:2017-05-25

摘要/Abstract

摘要：

通过在面部表情数据集上训练深度卷积神经网络、深度稀疏校正神经网络两种模型，对两种深度神经网络在静态面部表情识别方面的应用作了对比和分析.基于面部表情的结构先验知识，提出一种面向面部表情识别的改良方法——K兴趣区域方法，该方法在构建的开放实验数据集上，降低了由于训练数据过少而导致深度神经网络模型泛化能力不佳的问题，使得混合模型普遍且显著地降低了测试错误率.进而，结合实验结果进行了深入分析，并对深度神经网络在任意图像数据集上的可能有效性进行了深入剖析和分析.

关键词: K兴趣区域, 深度神经网络, 深度学习, 面部表情识别

Abstract:

By building two models including Deep Convolutional Neural Networks and Deep Sparse Rectifier Neural Networks on facial expression dataset,we made contrastive evaluations in facial expression recognition system with deep neural networks.Based on prior structure knowledge of facial expression,we proposed a fast and simple improved method called K Region Of Interest——‘K-ROI’,which relieved the poor generalization of deep neural networks on experimental dataset due to insufficient data and decreased the testing error rate apparently and generally.Finally,we infer the experimental results and analyze comprehensively for the possible validity with deep neural networks on arbitrary image dataset.

Key words: K-ROI, deep neural networks, deep learning, facial expression recognition

中图分类号:

TP391

孙晓, 潘汀. 基于兴趣区域深度神经网络的静态面部表情识别[J]. 电子学报, DOI: 10.3969/j.issn.0372-2112.2017.05.023.

SUN Xiao, PAN Ting. Static Facial Expression Recognition System Using ROI Deep Neural Networks[J]. Acta Electronica Sinica, DOI: 10.3969/j.issn.0372-2112.2017.05.023.

参考文献

[1] Alex K,Ilya S,Geoffrey H.Imagenet classification with deep convolutional neural networks[A].Advances in Neural Information Processing Systems[C].Lake Tahoe:Bartlett P,et al,2012.1097-1105.
[2] Andre T L,Edilson D A,Thiago O S.A Facial expression recognition system using convolutional networks[A].28th SIBGRAPI Conference on Graphics,Patterns and Images[C].Bahia,Brazil:IEEE,2015.273-280.
[3] Lucey P,Cohn J,Kanade T,Saragih J,Ambadar Z,and Matthews I.The extended cohn-kanade dataset (CK+):A complete dataset for action unit and emotion-specified expression[A].Conference on Computer Vision and Pattern Recognition Workshops[C].San Francisco,US:IEEE,2010.94-101.
[4] Christopher M B.Pattern Recognition and Machine Learning[M].New York:Springer,2006.
[5] Bengio Y.Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-127.
[6] Max J,Karen S,Andrew Z,Koray K.Spatial transformer networks[A].Conference on Neural Information Processing Systems[C].Montréal,Quebec,Canada:Curran Associates Inc,2015.2017-2025.
[7] LeCun Y,Boser B,et al..Handwritten digit recognition with a back-propagation network[A].Conference on Neural Information Processing Systems[C].Morgan Kaufman,Denver:Morgan Kaufmann,1990.396-404.
[8] Fukushima K.Neocognitron:A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J].Biological Cybernetics,1980,36(4):193-202.
[9] Rumelhart D E,Hinton G E,,Williams R J.Learning representations by back-propagating errors[J].Nature,1986,323(9):533-536.
[10] LeCun Y,Bottou L,Bengio Y,Haffner P.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[11] Szegedy C,Liu W,Jia Y,et al.Going deeper with convolutions[DB].arXiv preprint arXiv:1409.4842,2014.
[12] Xavier G,Antoine B,Yoshua B.Deep sparse rectifier neural networks[J].JMLR W&CP,2011,15:315-323.
[13] Andrew R B.Universal approximation bounds for super positions of a sigmoidal function[J].IEEE Trans on Information Theory,1993,39(3):930-945.
[14] Hubel D H,Wiesel T N,LeVay S.Visual field representation in layer IVC of monkey striate cortex[A].Society for Neuroscience,4th Annual Meeting[C].St Louis,US,1974.264-265.
[15] Dayan P,Abott L.Theoretical Neuroscience[M].MA:MIT Press,2001.
[16] Attwell D,Laughlin S.An energy budget for signaling in the grey matter of the brain[J].Journal of Cerebral Blood Flow and Metabolism,2001,21(10):1133-1145.
[17] Hinton G E,Srivastava N,Krizhevsky A,Sutskever I,Salakhutdinov R R.Improving neural networks by preventing co-adaptation of feature detectors[DB].arXiv preprint arXiv:1207.0580,2012.
[18] Charles D.On the origin of species[R].UK:John Murray,1859.
[19] Glorot X,Bengio Y.Understanding the difficulty of training deep feedforward neural networks[A].International Conference on Artificial Intelligence and Statistics[C].Italy:Sardinia,2010.249-256.
[20] Sun Y,Wang X,Tang X.Deep learning face representation from predicting 10000 classes[A].Conference on Computer Vision and Pattern Recognition[C].Columbus,USA:IEEE,2014.1891-1898.
[21] Tarjan R E.Depth-first search and linear graph algorithms[J].SIAM Journal on Computing,1972,1(2):146-160.
[22] 潘泓,朱亚平,夏思宇,金立左.基于上下文信息和核熵成分分析的目标分类算法[J].电子学报,2016,44(3):580-586. PAN Hong,ZHU Ya-ping,XIA Si-yu,JIN Li-zuo.Object classification using context cue and kernel entropy component analysis[J].Acta Electronica Sinica,2016,44(3):580-586.(in Chinese)

基于兴趣区域深度神经网络的静态面部表情识别

Static Facial Expression Recognition System Using ROI Deep Neural Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[2]	李雪莹, 王田路, 梁鹏, 王翀. 基于系统模型的用户评论中非功能需求的自动分类[J]. 电子学报, 2022, 50(9): 2079-2089.
[3]	琚长瑞, 秦晓燕, 袁广林, 李豪, 朱虹. 尺度敏感损失与特征融合的快速小目标检测方法[J]. 电子学报, 2022, 50(9): 2119-2126.
[4]	张志昌, 于沛霖, 庞雅丽, 朱林, 曾扬扬. SMGN：用于对话状态跟踪的状态记忆图网络[J]. 电子学报, 2022, 50(8): 1851-1858.
[5]	张亚洲, 俞洋, 朱少林, 陈锐, 戎璐, 梁辉. 一种量子概率启发的对话讽刺识别网络模型[J]. 电子学报, 2022, 50(8): 1885-1893.
[6]	王飞扬, 冀鹏欣, 孙笠, 危倩, 李根, 张忠宝. 一种基于深度学习的动态社交网络用户对齐方法[J]. 电子学报, 2022, 50(8): 1925-1936.
[7]	徐兴荣, 刘聪, 李婷, 郭娜, 任崇广, 曾庆田. 基于双向准循环神经网络和注意力机制的业务流程剩余时间预测方法[J]. 电子学报, 2022, 50(8): 1975-1984.
[8]	裴炤, 邱文涛, 王淼, 马苗, 张艳宁. 基于Transformer动态场景信息生成对抗网络的行人轨迹预测方法[J]. 电子学报, 2022, 50(7): 1537-1547.
[9]	欧阳与点, 谢鲲, 谢高岗, 文吉刚. 面向大规模网络测量的数据恢复算法：基于关联学习的张量填充[J]. 电子学报, 2022, 50(7): 1653-1663.
[10]	李政伟, 李佳树, 尤著宏, 聂茹, 赵欢, 钟堂波. 基于异质图注意力网络的miRNA与疾病关联预测算法[J]. 电子学报, 2022, 50(6): 1428-1435.
[11]	彭闯, 王伦文, 胡炜林. 融合深度特征的电磁频谱异常检测算法[J]. 电子学报, 2022, 50(6): 1359-1369.
[12]	张波, 陆云杰, 秦东明, 邹国建. 一种卷积自编码深度学习的空气污染多站点联合预测模型[J]. 电子学报, 2022, 50(6): 1410-1427.
[13]	杨伟超, 杜宇, 文伟, 侯舒维, 徐常志, 张建华. 基于多重分形谱智能分析的卫星信号调制识别研究[J]. 电子学报, 2022, 50(6): 1336-1343.
[14]	冀振燕, 韩梦豪, 宋晓军, 冯其波. 面向激光光条图像修复的循环相似度映射网络[J]. 电子学报, 2022, 50(5): 1234-1242.
[15]	廖勇, 李玉杰. 一种轻量化低复杂度的FDD大规模MIMO系统CSI反馈方法[J]. 电子学报, 2022, 50(5): 1211-1217.