基于AU-GCN与注意力机制的微表情识别  

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

作　　者：赵婧华 杨秋翔[1] ZHAO Jing-hua;YANG Qiu-xiang(School of Software,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学软件学院,山西太原030051

出　　处：《计算机与现代化》2023年第3期48-53,共6页Computer and Modernization

基　　金：武器装备预研基金资助项目(9140A17020113BQ04)。

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%。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 aggre⁃gates 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%.

关 键 词：微表情 面部运动单元 图卷积网络 注意力机制 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]