? 使用一种基于Depth-Patch的深度神经网络的非正面人脸表情识别
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2017, Vol. 32 Issue (6) :1172-1185    DOI: 10.1007/s11390-017-1792-1
Special Section of CAD/Graphics 2017 << Previous Articles | Next Articles >>
使用一种基于Depth-Patch的深度神经网络的非正面人脸表情识别
Nai-Ming Yao1,2, Hui Chen1,2,*, Member, CCF, Qing-Pei Guo1,2, Hong-An Wang1,2,3, Member, CCF, IEEE
1 Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences Beijing 100190, China;
2 University of Chinese Academy of Sciences, Beijing 100049, China;
3 State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China
Non-Frontal Facial Expression Recognition Using a Depth-Patch Based Deep Neural Network
Nai-Ming Yao1,2, Hui Chen1,2,*, Member, CCF, Qing-Pei Guo1,2, Hong-An Wang1,2,3, Member, CCF, IEEE
1 Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences Beijing 100190, China;
2 University of Chinese Academy of Sciences, Beijing 100049, China;
3 State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China

摘要
参考文献
相关文章
Download: [PDF 1698KB]  
摘要 在自然交流中,非正面头部姿态导致人脸表情识别的准确性和鲁棒性大幅下降。本文中,我们尝试从二维视频中识别具有较大头部旋转角度的人脸表情。为此,我们提出了一种基于depth patch的四维表情表示模型。该模型通过二维动态图像重建,用于表示非正面表情的连续空间变化和时序上下文。更进一步,我们提出了一种有效的深度神经网络分类器,它能够准确地从depth patch中捕获不同姿态下的表情特征并识别非正面表情。在BU-4DFE表情数据库上识别52度头部旋转范围内的非正面人脸表情的实验结果表明本文提出的方法取得了高达86.87%的识别准确率,超过了已有的方法。在BU-4DFE和Multi-PIE数据库上,我们对取得识别性能提升的关键因素进行了实验量化分析。
关键词人脸表情识别   非正面头部姿态   深度信息   时空结合   卷积神经网络     
Abstract: The challenge of coping with non-frontal head poses during facial expression recognition results in considerable reduction of accuracy and robustness when capturing expressions that occur during natural communications. In this paper, we attempt to recognize facial expressions under poses with large rotation angles from 2D videos. A depth-patch based 4D expression representation model is proposed. It was reconstructed from 2D dynamic images for delineating continuous spatial changes and temporal context under non-frontal cases. Furthermore, we present an effective deep neural network classifier, which can accurately capture pose-variant expression features from the depth patches and recognize non-frontal expressions. Experimental results on the BU-4DFE database show that the proposed method achieves a high recognition accuracy of 86.87% for non-frontal facial expressions within a range of head rotation angle of up to 52°, outperforming existing methods. We also present a quantitative analysis of the components contributing to the performance gain through tests on the BU-4DFE and Multi-PIE datasets.
Keywordsfacial expression recognition   non-frontal head pose   depth   spatial-temporal   convolutional neural network     
Received 2017-06-20;
本文基金:

This work was supported by the National Key Research and Development Program of China under Grant No. 2016YFB1001405, and the National Natural Science Foundation of China under Grant Nos. 61232013, 61422212, and 61661146002.

通讯作者: Hui Chen     Email: chenhui@iscas.ac.cn
About author: Nai-Ming Yao is a Ph.D.candidate at Institute of Software,Chinese Academy of Sciences,Beijing,and University of Chinese Academy of Sciences,Beijing.His research interests include human-computer interaction,affective computing,machine learning,and computer vision.
引用本文:   
Nai-Ming Yao, Hui Chen, Qing-Pei Guo, Hong-An Wang.使用一种基于Depth-Patch的深度神经网络的非正面人脸表情识别[J]  Journal of Computer Science and Technology , 2017,V32(6): 1172-1185
Nai-Ming Yao, Hui Chen, Qing-Pei Guo, Hong-An Wang.Non-Frontal Facial Expression Recognition Using a Depth-Patch Based Deep Neural Network[J]  Journal of Computer Science and Technology, 2017,V32(6): 1172-1185
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1792-1
Copyright 2010 by Journal of Computer Science and Technology