计算机与现代化 ›› 2023, Vol. 0 ›› Issue (03): 48-53.

• 人工智能 • 上一篇    下一篇

基于AU-GCN与注意力机制的微表情识别

  

  1. (中北大学软件学院,山西 太原 030051)
  • 出版日期:2023-04-17 发布日期:2023-04-17
  • 作者简介:赵婧华(1997—),女,山西太原人,硕士研究生,研究方向:人工智能,图像分类,E-mail: 386751764@qq.com; 杨秋翔(1969—),男,教授,研究方向:移动云计算与大数据技术及应用,E-mail: yangqx@nuc.edu.cn。
  • 基金资助:
    武器装备预研基金资助项目(9140A17020113BQ04)

Micro-expression Recognition Based on AU-GCN and Attention Mechanism

  1. (School of Software, North University of China, Taiyuan 030051, China)
  • Online:2023-04-17 Published:2023-04-17

摘要: 微表情作为一种持续时间非常短的表情,能够隐晦地将人试图压抑与隐藏的真正情感表达出来,在国家安全、司法系统、医学范畴和政治选举等有着较好的应用。但由于微表情有着数据集较少、持续时间短暂、表情幅度低等特点,在识别微表情时存在数据样本量较少、计算量较大、缺失重点特征的关注、易过拟合等困难。因此本文将针对微表情只出现在面部部分区域的特点,借助面部动作单元(Action Units, AU),对其使用加权注意力机制凸显局部特征,并且应用图卷积神经网络找到AU各个节点间的依赖关系,聚合为全局特征,用于微表情识别。实验结果表明,相较于现有方法,本文提出的方法将准确率提高至79.3%。

关键词: 微表情, 面部运动单元, 图卷积网络, 注意力机制

Abstract: As a kind of expression with very short duration, micro-expression can implicitly express people ’s true feelings of trying to suppress and hide, which has a good application in national security, judicial system, medical category and political elections. However, since micro-expression has the characteristics of less data sets, short duration and low expression amplitude, there are many difficulties in identifying micro-expressions, such as less data samples, larger calculation, lack of attention to key features, and easy to over-fitting. Therefore, this paper uses facial action units ( AU ) to highlight local features by weighted attention mechanism, and applies graph convolution network to find the dependencies between AU nodes, and aggregates them into global features for micro-expression recognition. The experimental results show that compared with the existing methods, the proposed method improves the accuracy to 79.3 %.

Key words: micro-expression, facial action unit, graph convolution network, attention mechanism