• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 图形与图像 • 上一篇    下一篇

基于VGG-NET的特征融合面部表情识别

李校林1,2,3,钮海涛1,2   

  1. (1.重庆邮电大学通信与信息工程学院,重庆400065;2.重庆邮电大学通信新技术应用研究中心,重庆400065;
    3.重庆信科设计有限公司,重庆 401121)
  • 收稿日期:2019-07-18 修回日期:2019-10-15 出版日期:2020-03-25 发布日期:2020-03-25

Facial expression recognition using
feature fusion based on VGG-NET

LI Xiao-lin1,2,3,NIU Hai-tao1,2   

  1. (1.School of Communication and Information Engineering,
    Chongqing University of Posts and Telecommunications,Chongqing 400065;
    2.Research Center of New Telecommunication Technology Applications,
    Chongqing University of Posts and Telecommunications,Chongqing 400065;
    3.Chongqing Information Technology Designing Co.,Ltd.,Chongqing 401121,China)
  • Received:2019-07-18 Revised:2019-10-15 Online:2020-03-25 Published:2020-03-25

摘要:

为了解决在面部表情特征提取过程中卷积神经网络CNN和局部二值模式LBP只能提取面部表情图像的单一特征,难以提取与面部变化高度相关的精确特征的问题,提出了一种基于深度学习的特征融合的表情识别方法。该方法将LBP特征和CNN卷积层提取的特征通过加权的方式结合在改进的VGG-16网络连接层中,最后将融合特征送入Softmax分类器获取各类特征的概率,完成基本的6种表情分类。实验结果表明,所提方法在CK+和JAFFE数据集上的平均识别准确率分别达到了97.5%和97.62%,利用融合特征得到的识别结果明显优于利用单一特征识别的效果。与其他方法相比较,该方法能有效提高表情识别准确率,对光照变化更加鲁棒。
 
 

关键词: 面部表情识别, 特征融合, VGG-NET网络, Softmax分类

Abstract:

Convolutional Neural Networks (CNN) and Local Binary Patterns (LBP) can only extract single features of facial expression images during facial expression feature extraction, so it is difficult to extract the precise features related to facial changes. In order to solve this problem, this paper proposes a facial expression recognition method using feature fusion based on deep learning. The method combines the LBP feature and the features extracted by the CNN convolutional layer into the improved VGG-16 network connection layer by weighting. Finally, the fusion features are sent to the Softmax classifier to obtain the probability of various features, and complete the basic six expression classifications. The experimental results show that the average recognition accuracy of the proposed method on the CK+ and JAFFE datasets is 97.5% and 97.62%, respectively. The recognition results obtained by the fusion features are significantly superior to that of single feature recognition. Compared with other methods, this method can effectively improve the accuracy of expression recognition and is more robust to illumination changes.

 

 

 

Key words: facial expression recognition, feature fusion, VGG-NET network, Softmax classification