基于加权多头并行注意力的局部遮挡面部表情识别  

Facial Expression Recognition with Local Occlusion Based on Weighted Multi-head Parallel Attention

作　　者：郭胜 蔡姗 邹雪 周珍胜 王林 GUO Sheng;CAI Shan;ZOU Xue;ZHOU Zhen-Sheng;WANG Lin(School of Data Science and Information Engineering,Guizhou Minzu University,Guiyang 550025,China;Guizhou Province Key Laboratory of Pattern Recognition and Intelligent Systems,Guizhou Minzu University,Guiyang 550025,China)

机构地区：[1]贵州民族大学数据科学与信息工程学院,贵阳550025 [2]贵州民族大学贵州省模式识别与智能系统重点实验室,贵阳550025

出　　处：《计算机系统应用》2024年第1期254-262,共9页Computer Systems & Applications

摘　　要：面部表情识别在诸多领域具有广泛的应用价值,但在识别过程中局部遮挡会导致面部难以提取有效的表情识别特征,而局部遮挡的面部表情识别可能需要多个区域的表情特征,单一的注意力机制无法同时关注面部多个区域特征.针对这一问题,本文提出了一种基于加权多头并行注意力的局部遮挡面部表情识别模型,该模型通过并行多个通道-空间注意力提取局部未被遮挡的多个面部区域表情特征,有效缓解了遮挡对表情识别的干扰,大量的实验结果表明,本文的方法相比于很多先进的方法取得了最优的性能,在RAF-DB和FERPlus上的准确率分别为89.54%、89.13%,在真实遮挡的数据集Occlusion-RAF-DB和Occlusion-FERPlus的准确率分别为87.47%、86.28%.因此,本文的方法具有很强的鲁棒性.Facial expression recognition(FER)has widespread application significance in many fields,but it is difficult to extract effective FER features due to local occlusion during the recognition.FER with local occlusion may require expression features of multiple regions,and a single attention mechanism cannot focus on the features of multiple facial regions simultaneously.To this end,this study proposes a local occlusion FER model based on weighted multi-head parallel attention.The model extracts the expression features of multiple facial regions that are not occluded by multiple channels in parallel-spatial attention,alleviating the occlusion interference on expression recognition.A large number of experiments show that the proposed method yields the best performance compared with many advanced methods,and the accuracy on RAF-DB and FERPlus is 89.54% and 89.13%,respectively.On the occluded datasets Occlusion-RAF-DB and Occlusion-FERPlus,the accuracy is 87.47% and 86.28%,respectively.Therefore,this method has strong robustness.

关 键 词：面部表情识别 局部遮挡 表情特征识别 注意力机制 加权多头并行注意力 神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]