重庆大学学报2025，Vol.48Issue(6)：98-111,14.DOI:10.11835/j.issn.1000-582X.2025.06.009
基于非线性深度子空间学习的微表情识别方法研究
Micro-expression recognition based on nonlinear deep subspace learning
摘要
Abstract
To address the issues of poor robustness and weak generalisation in deep subspace network-based micro-expression recognition,this paper proposes a novel method that integrates nonlinear deep subspace learning with optical flow computation.The method employs kernel transformation to comprehensively extract emotional features from micro-expressions while simultaneously utilizing optical flow characteristcs to capture subtle motion dynamics,thereby enhancing recognition robustness.Experimental validation is performed on 4 widely adopted spontaneous micro-expression datasets(SMIC,SAMM,CASME and CASME Ⅱ)as well as a composite dataset 3DB-combined samples.Results demonstrate that the proposed method outperforms existing deep learning algorithms,including MACNN and Micro-Attention,achieving a recognition accuracy of 0.834 6 on the composite dataset.Furthermore,after adding 10%,20%,30%,and 40%random noise blocks to the SMIC dataset,the method consistently maintains superior unweighted F1 scores compared to other algorithms.These findings substantiate its effectiveness and robustness in real-world micro-expression recognition scenarios.关键词
深度子空间/微表情识别/光流特征/主成分分析Key words
deep subspace/micro-expression recognition/optical flow features/principal component analysis分类
计算机与自动化引用本文复制引用
冉光伟,何祺,王楠,冯为嘉,姜立标..基于非线性深度子空间学习的微表情识别方法研究[J].重庆大学学报,2025,48(6):98-111,14.基金项目
国家自然科学基金资助项目(61602345,62002263).Supported by National Natural Science Foundation of China(61602345,62002263). （61602345,62002263）
