Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (9): 245-254.DOI: 10.3778/j.issn.1002-8331.2202-0120

• Graphics and Image Processing • Previous Articles     Next Articles

Multi-Branch Network Facial Expression Recognition Based on Gender Constraint

ZENG Xi, XIN Yuelan, XIE Qiqi   

  1. College of Physics and Electronic Information Engineering, Qinghai Normal University, Xining 810000, China
  • Online:2023-05-01 Published:2023-05-01



  1. 青海师范大学 物理与电子信息工程学院,西宁 810000

Abstract: Aiming at the large intra-class variation and small inter-class differences of facial expressions under different genders, the thesis proposes a multi-branch network facial expression recognition based on gender constraints. Firstly, through the method of clustering algorithm K-means and convolutional neural network, the relationship between facial expression classes under gender constraints is obtained. Then, according to the obtained inter-class relationships, a backbone network and a branch network with a channel attention mechanism are constructed to further distinguish between strongly similar inter-class relationships and highlight intra-class changes in facial expressions of different genders. Finally, experiments and analysis are performed on CK+, FER2013 and RAF-DB datasets. Experiments show that the average recognition rate of the proposed network structure on the CK+, FER2013 and RAF-DB datasets is superior to other advanced methods, reaching 97.60%, 73.58% and 87.98%.

Key words: facial expression recognition, gender constraint, multi-branch network, attention mechanism

摘要: 针对不同性别下人脸表情类内变化大、类间差异小的问题,提出一种基于性别约束的多分支网络人脸表情识别方法。通过聚类算法K-means与卷积神经网络相结合的方法,得到性别约束下人脸表情类间关系。根据类间关系,构建主干网络和具有通道注意力机制的分支网络,进一步区分强相似的类间关系和突出不同性别人脸表情的类内变化。最后在CK+、FER2013和RAF-DB数据集上进行实验并分析。实验表明,提出的网络结构在CK+、FER2013和RAF-DB数据集上的平均识别率均优于其他先进方法,分别达到了97.60%、73.58%和87.98%。

关键词: 人脸表情识别, 性别约束, 多分支网络, 注意力机制