用户微表情信息表征研究综述
|
刘洋,讲师,博士,E-mail: yang.liu27@whu.edu.cn |
|
吴佩,本科生 |
|
万芷涵,本科生 |
|
石佳玉,本科生 |
|
朱立芳,讲师,博士 |
Copy editor: 刘远颖
收稿日期: 2023-01-28
网络出版日期: 2025-04-28
基金资助
国家自然科学基金青年项目“突发公共卫生事件公众心理应激信息表征及干预机制研究”(72204190)
教育部人文社科项目青年项目“基于社交机器人的突发公共卫生事件公众心理应激干预研究”(22YJCZH114)
中国博士后面上基金“突发公共卫生事件公众心理应激信息表征及干预机制研究”(2022M722476)
A Review of Information Representation of User's Micro-Expressions
Received date: 2023-01-28
Online published: 2025-04-28
刘洋 , 吴佩 , 万芷涵 , 石佳玉 , 朱立芳 . 用户微表情信息表征研究综述[J]. 知识管理论坛, 2023 , 8(3) : 215 -227 . DOI: 10.13266/j.issn.2095-5472.2023.019
[Purpose/Significance] To analyze the current status and trends of research in the field of micro-expression recognition at home and abroad, and to provide a reference for the research on micro-expression information representation of users in the field of library and intelligence. [Method/Process] The bibliometric-based research method revealed the research dynamics in the field of micro-expression recognition in the last decade, and analyzed the convergence trends, technical basis and difficult challenges of micro-expression recognition and information representation. [Result/Conclusion] Micro-expression datasets and micro-expression recognition technologies are current research hotspots; technical approaches, security ethics and database volume are major challenges for today's development; information transmission and information feedback are emerging research areas that can be developed in libraries and intelligence in the future, and areas such as meta-universe, privacy issues and technology-driven are future trends in the application of micro-expression recognition technologies.
表1 常用数据集对比 |
| 分类 | 数据集 | 年份 | 样本数 /个 | 受试人员 /人 | 种族 /个 | 微表情种类/种 | 帧率 | |
| 非自发微表情数据集 | USF-HD | 2011 | 100 | N/A | 1 | 6 | 30 | |
| Polikovsky’s | 2013 | 42 | 10 | 1 | 6 | 200 | ||
| 自发微表情数据集 | SMIC 2 | 2013 | HS | 164 | 20 | 3 | 3 | 100 |
| VIS | 71 | 10 | 25 | |||||
| NIR | 71 | 10 | 25 | |||||
| CASME | 2013 | 195 | 35 | 1 | 8 | 60 | ||
| CASMEⅡ | 2014 | 247 | 35 | 1 | 5 | 200 | ||
| SAMM | 2016 | 159 | 32 | 13 | 7 | 200 | ||
| CAS(ME)2 | 2018 | 57 | 22 | 1 | 4 | 30 | ||
| SAMM long | 2020 | 159 | 29 | 1 | 7 | 200 | ||
| MMEW | 2021 | 300 | 36 | 1 | 7 | 200 | ||
| CASMEⅢ | 2022 | 1109 | 216 | 1 | 7 | 30 | ||
表2 传统表情特征提取方法 |
| 分类 | 主要方法 | 方法描述 |
| 基于纹理特征的算法 | 局部二值模式(local binary patterns, LBP)方法[32] | 定义在像素3×3的领域内,以领域中心像素为阈值,比较周围8个像素点与其之间的关系,得到该领域中心像素点的LBP值,并用这个值反映该区域的纹理信息 |
| 3个正交平面—局部二值模式(local binary pattern histograms from three orthogonal planes)方法[33] | 在LBP基础上,引入时间维度建立3个正交平面对图片序列的特征进行表达 | |
| 方向梯度直方图(histogram of oriented gradient, HOG)方法[34] | 将图像进行多层分块处理,计算每个子块的梯度直方图作为特征向量,最后逐层拼接作为每个图像的特征向量 | |
| 基于几何变换的算法 | 光流法(optical flow)[35] | 将运动图像函数f(x,y,t)作为基本函数,根据图像强度守恒原理建立光流约束方程,通过求解约束方程,得到微表情各序列帧之间的关系 |
| 定向光流直方图(histogram of oriented optical flow, HOOF)法[36] | 在光流法基础上对光流直方图进行改进,对光流值归一化处理,最后得到以光流为主要导向的光流直方图 | |
| 主方向平均光流(main directional mean optical flow feature, MDMO)法[37] | 根据人脸标志点将人脸划分为36个区域,计算得到每个区域的向量,选取这些区域的最大光流极坐标向量,并用其平均值来代表该区域特征向量 | |
| 三角化时域模型(delaunay-based temporal coding model, DTCM)法[38] | 使用主观模型对人脸序列进行分割,并通过相同位置的三角区域对比和其特征计算来表示微表情的动态变化的过程 |
表3 深度学习特征提取方法 |
| 分类 | 主要方法 | 方法描述 | 优点 |
| 基于关联学习的方法 | 基于卷积神经网络(CNN)[41] | CNN通过多层的卷积、池化、全连接,降低图片维度,将图片的特征转换为一维向量,从而得到更为全面的信息 | 识别效果比传统方法更好,通常情况下网络越深,提取的特征越抽象,也越具有代表性 |
| 基于卷积神经网络和长短期记忆网 络(long short-term memory, LSTM)网络架构[42] | 使用 CNN 提取二维平面上的特征,将其输入于LSTM结构中,通过LSTM结构的记忆单元,同时由3个门来控制结构的变化,从有效学习到长期依赖信息 | 卷积和LSTM组合提取微表情序列中的时空特征能够更加有效地描绘微表情特征 | |
| 三维卷积神经网络(3DCNN)[43] | 在二维卷积神经网络基础上,提取时间特质,考虑时间维度的帧间运动信息,主要运用于视频分类、动作识别等领域 | 准确率高,三维卷积能够充分提取微表情时间、空间上的特征 | |
| 基于卷积神经网络和注意力机制架构[44] | 提取微表情片段中的光流与光学应变,将其输入到浅层3DCNN中,提取光流特征向量。在迁移模型的基础上,加入卷积注意力模块以提取人脸特征向量。最后将两个特征向量拼接起来进行分类 | 注意力机制通过分配不同系数或者权重来突出重要信息和抑制不相关信息,并且随着网络的加深,能够捕捉到更多维度的特征 | |
| 基于区域学习的方法 | 多通道级联[45] | 使用3个并行的多通道卷积网络从不同的面部区域学习融合全局和局部特征,利用联合嵌入特征学习来探索基于融合区域的特征在嵌入空间中的身份不变和姿态感知的表达表示 | 性能和鲁棒性优于现有的先进方法 |
| 基于迁移学习的方法 | 基于迁移学习的跨域人脸表情识别[46] | 利用迁移学习将基于深度卷积神经网络的人脸识别模型VGGFace,从人脸识别领域迁移到面部表情识别领域,并引入聚焦损失函数作为目标函数来降低数据不均衡的影响 | 采用端到端的深度学习方法自动提取特征的效果更好,微表情识别的准确率更高 |
刘洋:进行研究设计,开展实验,撰写论文;
吴佩:开展实验,撰写论文;
万芷涵:开展实验,撰写论文;
石佳玉:开展实验,撰写论文;
朱立芳:进行研究设计,修改论文。
| [1] |
吴奇,申寻兵,傅小兰.微表情研究及其应用[J].心理科学进展,2010,18(9):1359-1368.
|
| [2] |
Ekman P, Friesen W V. Detecting deception from the body or face[J]. Journal of personality and social psychology, 1974, 29(3):288-298.
|
| [3] |
HOUSE C, MEYER R. Preprocessing and descriptor features for facial micro-expression recognition [EB/OL].[2022-07-30].https://web.stanford.edu/classlee368/Project_Spring_1415/Reports/House_Meyer.pdf.
|
| [4] |
陈子健,朱晓亮.基于面部表情的学习者情绪自动识别研究——适切性、现状、现存问题和提升路径[J].远程教育杂志,2019,37(4):64-72.
|
| [5] |
Zeng Z h, Pantic M, Roisman G I, et al. A survey of affect recognition methods: audio, visual, and spontaneous expression[J].IEEE trans on pattern analysis and machine intelligence,2009,31(1):39-58.
|
| [6] |
ZHANG J, DONALD A N. Representations in distributed cognitive tasks[J]. Cognitive science,1994,18(1):87-122.
|
| [7] |
阳长征.危机事件中网络信息表征对用户持续分享意愿影响研究[J].图书情报工作,2019,63(21):105-116.
|
| [8] |
石程旭.监狱民警应用微表情分析的思考[J].法制博览,2022(5):27-29.
|
| [9] |
崔小洛.基于微表情追踪的课堂教学效果即时反馈系统设计[J].无线互联科技,2022,19(4):52-54.
|
| [10] |
李婧婷,东子朝,刘烨,等.基于人类注意机制的微表情检测方法[J].心理科学进展,2022,30(10):2143-2153.
|
| [11] |
Frank M G, Herbasz M, Sinuk K, et al. I see how you feel: training laypeople and professionals to recognize fleeting emotion[C]// The annual meeting of the International Communication Association. New York: International Communication Association, 2009: 1-35.
|
| [12] |
Pfister T, Li X, Zhao G, et al. Recognising spontaneous facial micro-expressions[C]//2011 international conference on computer vision. Piscataway: IEEE, 2011: 1449-1456.
|
| [13] |
徐峰,张军平.人脸微表情识别综述[J].自动化学报,2017,43(3):333-348.
|
| [14] |
Pfister T, Li X B, Zhao G Y, et al. Recognising spontaneous facial micro-expressions[C]//Proceedings of the 2011 IEEE international conference on computer vision. Piscataway: IEEE,2011:1449-1456.
|
| [15] |
Li X B, Pfister T, Huang X H, et al. Aspontaneous micro-expression database: inducement, collection and baseline[C]//Proceedings of the 10th IEEE international conference and workshops on automatic face and gesture recognition. Piscataway: IEEE,2013:1-6.
|
| [16] |
Yan w J, Wu Q, Liu Y J, et al. CASME database: a dataset of spontaneous micro-expressions collected from neutralized faces[C]//Proceedings of the 10th IEEE international conference and workshops on automatic face and gesture recognition. Piscataway: IEEE, 2013:1-7.
|
| [17] |
Yan W J, Li X, Wang S J, et al. CASME II: an improved spontaneous micro-expression database and the baseline evaluation[J]. PloS one, 2014, 9(1): e86041.
|
| [18] |
Qu F, Wang S J, Yan W J, et al. CAS (ME)^2: a database for spontaneous macro-expression and micro-expression spotting and recognition[J]. IEEE transactions on affective computing, 2017, 9(4): 424-436.
|
| [19] |
Li J, Dong Z, Lu S, et al. CAS (ME)3: a third generation facial spontaneous micro-expression database with depth information and high ecological validity[J]. IEEE transactions on pattern analysis and machine intelligence, 2022,45(3): 2782-2800.
|
| [20] |
Yap C H, Kendrick C, Yap M H. SAMM long videos: a spontaneous facial micro-and macro-expressions dataset[C]//2020 15th IEEE international conference on automatic face and gesture recognition. Piscataway: IEEE, 2020: 771-776.
|
| [21] |
Ben X,Ren Y, Zhang J, et al. Video-based facial micro-expression analysis: a survey of datasets, features and algorithms[J]. IEEE transactions on pattern analysis and machine intelligence, 2021,44(9): 5826-5846.
|
| [22] |
Pfister T, Li X, Zhao G, et al. Recognising spontaneous facial micro-expressions[C]//2011 international conference on computer vision. Piscataway: IEEE, 2011: 1449-1456.
|
| [23] |
Polikovsky S, Kameda Y, Ohta Y. Facial micro-expression detection in hi-speed video based on facial action coding system (FACS)[J]. IEICE transactions on information and systems, 2013, 96(1): 81-92.
|
| [24] |
Rowley H A, Baluja S, Kanade T. Neural network-based face detection[J] IEEE transactions on pattern analysis and machine intelligence, 1998, 20(1): 23-38.
|
| [25] |
Schapire E, Singer Y. Improved boosting algorithms using confidence-rated predictions[J].Machine learning,1999,37(3):297-336.
|
| [26] |
COOTES T F, TAYLOR C J, EDWARDS G J. Active appearance models[C]//European conference on computer vision. Berlin: Springer,1998:484-498.
|
| [27] |
Wadhwa N, Rubinstein M, Durand F, et al. Phase-based video motion processing[J]. ACM transactions on graphics, 2013, 32(4):1-10.
|
| [28] |
姚海燕,李健,邓小昭.网络用户信息行为研究中的隐私问题探讨[J].情报探索,2010(7):14-16.
|
| [29] |
周霞,王萍,王美月,等.政府开放数据用户认知影响因素研究——先验图式调节效应[J].情报科学,2022,40(9):159-166.
|
| [30] |
蒋福明,曾慧平.人脸识别技术应用中的隐私伦理问题及其消解路径[J].山西高等学校社会科学学报,2020,32(9):19-24.
|
| [31] |
李思宁. 基于深度学习的面部微表情识别方法研究[D]. 徐州:中国矿业大学, 2020.
|
| [32] |
Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE transactions on pattern analysis machine intelligence, 2002,24(7): 971-987.
|
| [33] |
Zhao G, Pietikainen M. Dynamic texture recognition using local binary patterns with an application to facial expressions[J]. IEEE transactions on pattern analysis and machine intelligence, 2007, 29(6): 915-928.
|
| [34] |
Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//IEEE computer society conference on computer vision & pattern recognition. Piscataway: IEEE, 2005: 886-893.
|
| [35] |
Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[C]//Proceedings of the 7th international joint conference on artificial intelligence. San Francisco: Morgan Kaufmann Publishers, 1997, 2: 674-679.
|
| [36] |
Chaudhry R, Ravichandran A, Hager G, et al. Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions[C]//Proceedings of 2009 IEEE conference on computer vision and pattern recognition. Miami: IEEE, 2009: 1932-1939.
|
| [37] |
Liu Y J, Zhang J K, Yan W J, et al. A main directional mean optical flow feature for spontaneous micro-expression recognition[J]. IEEE transactions on affective computing, 2015, 7(4): 299-310.
|
| [38] |
Lu Z, Luo Z, Zheng H, et al. A delaunay-based temporal coding model for micro-expression recognition [C]//Asian conference on computer vision. Singapore: Springer, 2014: 698-711.
|
| [39] |
Takalkar M A, Xu M. Image based facial micro-expression recognition using deep learning on small datasets[C]//2017 international conference on digital image computing: techniques and applications. Piscataway: IEEE, 2017: 1-7.
|
| [40] |
钱付兰,李建红,赵姝,等.基于深度混合模型评分推荐[J].南京航空航天大学学报,2019,51(5):592-598.
|
| [41] |
刘德志, 梁正友, 孙宇. 结合空间注意力机制与光流特征的微表情识别方法 [J]. 计算机辅助设计与图形学学报, 2021,33(10):1541-1552.
|
| [42] |
Khor H Q, See J, Phan R, et al. Enriched long-term recurrent convolutional network for facial micro-expression recognition [C]// IEEE international conference on automatic face & gesture recognition. Piscataway: IEEE, 2018: 667-674.
|
| [43] |
YAO L, XIAO X, CAO R, et al. Three stream 3D CNN with SE block for micro-expression recognition[C]//2020 International conference on computer engineering and application. Piscataway: IEEE, 2020:439-443
|
| [44] |
李星燃,张立言,姚树婧.结合特征融合和注意力机制的微表情识别方法[J].计算机科学,2022,49(2):4-11.
|
| [45] |
LIU Y Y, DAI W, FANG F, et al. Dynamic multi- channel metric network for joint pose-aware and identity-invariant facial expression recognition[J]. Information sciences,2021(578):195-213.
|
| [46] |
孔慧芳,钱世超,闫嘉鹏.基于不均衡数据与迁移学习的面部微表情识别[J].合肥工业大学学报(自然科学版),2020,43(7):895-900.
|
| [47] |
刘洋,马莉莉,张雯,等.基于跨模态深度学习的旅游评论反讽识别[J].数据分析与知识发现,2022,6(12):23-31.
|
| [48] |
阳长征.危机事件中网络信息表征对用户持续分享意愿影响研究[J].图书情报工作,2019,63(21):105-116.
|
| [49] |
韩丽,李洋,周子佳,等.课堂环境中基于面部表情的教学效果分析[J].现代远程教育研究,2017(4):97-103,112.
|
| [50] |
夏乾馨,付强.应用微表情识别技术实现公安预警模式的探讨[J].中国防伪报道,2021(2):82-85.
|
| [51] |
康桐瑞.论微表情分析在我国侦查讯问中的应用[J].上海公安学院学报,2019,29(4):28-33.
|
| [52] |
Kang J, CHEN X Y, LIU Q Y, et al. Research on a micro-expression recognition technology based on multimodal fusion[J/OL]. Complexity, 2021[2023-03-02]. https://www.hindawi.com/journals/complexity/2021/5221950/.
|
| [53] |
Buhari A M, Ooi C P, Baskaran V M, et al. Invisible emotion magnification algorithm (IEMA) for real-time micro-expression recognition with graph-based features[J]. Multimedia tools and applications, 2022, 81(7): 9151-9176.
|
| [54] |
Liu J, Wang H, Feng Y. An end-to-end deep model with discriminative facial features for facial expression recognition[J]. IEEE access, 2021, 9: 12158-12166.
|
| [55] |
El Zarif N, Montazeri L, Leduc-Primeau F, et al. Mobile-optimized facial expression recognition techniques[J]. IEEE access, 2021, 9: 101172-101185.
|
| [56] |
Zhang G, Lv G, Binsawad M, et al. Dynamic nonlinear expression recognition technology using neural network and attention mechanism[J]. Fractals, 2022, 30(2): 2240097.
|
| [57] |
陈子健,朱晓亮.基于面部表情的学习者情绪自动识别研究——适切性、现状、现存问题和提升路径[J].远程教育杂志,2019,37(4):64-72.
|
| [58] |
彭小江,乔宇.面部表情分析进展和挑战[J].中国图象图形学报,2020,25(11):2337-2348.
|
| [59] |
马艳准. 多民族面部表情理解分析技术研究[D].沈阳: 东北大学,2012.
|
| [60] |
张旭东,刘洋.组态视角下元宇宙图书馆用户接受意愿影响因素研究[J].图书馆理论与实践,2023(3):73-85.
|
| [61] |
于明,钟元想,王岩.人脸微表情分析方法综述[J].计算机工程,2023,49(2):1-14.
|
| [62] |
殷明,张剑心,史爱芹,等.微表情的特征、识别、训练和影响因素[J].心理科学进展,2016,24(11):1723-1736.
|
| [63] |
樊振佳,宋正刚,刘鸿彬,等.贫困地区返乡创业人员信息获取不平等表征及其根源分析[J].情报科学,2019,37(10):81-86,113.
|
| [64] |
刘汝涵,徐丹.视频放大和深度学习在微表情识别任务上的应用[J].计算机辅助设计与图形学学报,2019,31(9):1535-1541.
|
| [65] |
姜婷婷,吴茜,徐亚苹,等.眼动追踪技术在国外信息行为研究中的应用[J].情报学报,2020,39(2):217-230.
|
| [66] |
吴冉,任衍具.微表情的启动效应研究[J].应用心理学,2011,17(3):241-248.
|
| [67] |
刘缘,庾永波.在安检中加强“微表情”识别的思考——基于入藏公路安检的考察[J].四川警察学院学报,2019,31(1):61-68.
|
| [68] |
Shen X, Wu Q, Fu X. Effects of the duration of expressions on the recognition of micro expressions[J]. Journal of Zhejiang University science B, 2012, 13(3): 221-230.
|
| [69] |
刘洋,马莉莉,张雯,等.基于跨模态深度学习的旅游评论反讽识别[J].数据分析与知识发现,2022,6(12):23-31.
|
| [70] |
谭春辉,陈晓琪,梁远亮,等.隐私泄露事件中社交媒体围观者情感分析[J].情报科学,2023,41(3):8-18.
|
/
| 〈 |
|
〉 |