融合LBP与并行注意力机制的微表情识别方法  

A micro expression recognition method integrating LBP and parallel attention mechanism

作　　者：李帅超 李明泽 孙嘉傲 卢树华[1,2] LI Shuaichao;LI Mingze;SUN Jiaao;LU Shuhua(College of Information and Cyber Security,People’s Public Security University of China,Beijing 102600,China;Key Laboratory of Security Technology and Risk Assessment Ministry of Public Security,Beijing 102600,China)

机构地区：[1]中国人民公安大学信息网络安全学院,北京102600 [2]公安部安全防范技术与风险评估重点实验室,北京102600

出　　处：《北京航空航天大学学报》2025年第4期1404-1414,共11页Journal of Beijing University of Aeronautics and Astronautics

基　　金：中国人民公安大学安全防范工程双一流创新研究专项(2023SYL08)。

摘　　要：针对面部微表情变化强度弱、背景噪声干扰及特征区分度较小等问题,提出了一种融合LBP与并行注意力机制的微表情识别网络。该网络将RGB图像输入密集连接改进的Shuffle Stage分支提取面部全局特征,增强上下文语义信息关联;将LBP图像输入多尺度分层卷积神经网络构成的局部纹理特征分支,提取细节信息;双分支特征提取后,在网络后端引入并行注意力机制提高特征融合能力,抑制背景干扰,专注微表情特征兴趣区域;所提方法在CASME、CASME II和SMIC等3个公开数据集上进行了测试,识别准确率分别达到了85.18%、74.53%和81.19%;实验结果表明,所提方法有效提高了微表情识别准确率,优于当前诸多先进方法。This research proposes a micro expression recognition network that incorporates LBP and parallel attention method to address the issues of small feature discrimination,background noise interference,and weak intensity of facial micro-expression changes.The network inputs the RGB image into the densely connected improved Shuffle Stage branch to extract the global features of the face and enhance the association of contextual semantic information.The LBP image is input into the local texture feature branch composed of a multi-scale layered convolutional neural network to extract detailed information.Following extraction of the dual-branch feature,the network backend implements a parallel attention technique to enhance feature fusion capabilities,reduce background noise,and concentrate on the micro-expression feature's interest region.The proposed method is tested on three public data sets including CASME,CASME II and SMIC,and the recognition is accurate The rates reached 85.18%,74.53%and 81.19%respectively.The experimental results show that the proposed method effectively improves the accuracy of micro expression recognition,which is better than many current advanced methods.

关 键 词：微表情识别 密集连接 Shuffle Stage分支 多尺度分层卷积 并行注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]