Facial expression distribution prediction based on surface electromyography
Facial expression distribution prediction based on surface electromyography
复制标题
基于表面肌电的面部表情分布预测
DOI：
10.1016/j.eswa.2020.113683
复制
发表时间：
2020-12
影响因子：
8.5
通讯作者：
Zhizeng Luo
中科院分区：
文献类型：
--
作者：
Xugang Xi;Yan Zhang;Xian Hua;Seyed M. Miran;Yun-Bo Zhao;Zhizeng Luo
人脸表情识别在人机交互研究中起着重要的作用。常见的面部表情是六种基本情绪的混合：愤怒、厌恶、恐惧、快乐、悲伤和惊讶。然而，目前的研究集中在基于生理信号的单一基本情绪上。提出了基于表面肌电信号的情绪分布学习方法(EDL)来预测基本情绪的强度。我们记录了降眉上肌、颧大肌、额内侧肌和口降肌的表面肌电信号。在频域、时域、时频域和熵域提取了6个特征。使用主成分分析(PCA)选择最具代表性的特征进行预测。EDL的核心思想是学习一个将PCA选择的特征映射到面部表情分布的函数，从而使EDL能够学习到对一种情绪的所有基本情绪的特殊描述程度。同时，杰弗里的分歧考虑了不同基本情绪之间的关系。与基于主元分析选择特征的多标签学习的性能进行了比较。用6个指标衡量预测结果，这些指标可以反映分布之间的距离或相似程度。我们对六种不同的情绪分布进行了实验。实验结果表明，与其他方法相比，该方法能更准确地预测人脸表情分布。
Facial expression recognition plays an important role in research on human–computer interaction. The common facial expressions are mixtures of six basic emotions: anger, disgust, fear, happiness, sadness, and surprise. The current study, however, focused on a single basic emotion on the basis of physiological signals. We proposed emotion distribution learning (EDL) based on surface electromyography (sEMG) for predicting the intensities of basic emotions. We recorded the sEMG signals from the depressor supercilii, zygomaticus major, frontalis medial, and depressor anguli oris muscles. Six features were extracted in the frequency, time, time–frequency, and entropy domains. Principal component analysis (PCA) was used to select the most representative features for prediction. The key idea of EDL is to learn a function that maps the PCA-selected features to the facial expression distributions such that the special description degrees of all basic emotions for an emotion can be learned by EDL. Simultaneously, Jeffrey's divergence considered the relationship between different basic emotions. The performance of EDL was compared with that of multilabel learning based on PCA-selected features. Predicted results were measured by six indices, which could reflect the distance or similarity degree between distributions. We conducted an experiment on six different emotion distributions. Experimental results show that the EDL can predict the facial expression distribution more accurately than the other methods.
登录
查看更多内容
DOI：
10.3390/s18020614
发表时间：
2018-02-17
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Xi X;Tang M;Luo Z
通讯作者：
Luo Z
DOI：
10.3390/s130912431
发表时间：
2013-09-17
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Chowdhury RH;Reaz MB;Ali MA;Bakar AA;Chellappan K;Chang TG
通讯作者：
Chang TG
影响因子：
3.9
作者：
Santamaria-Granados, Luz;Munoz-Organero, Mario;Arunkumar, N.
通讯作者：
Arunkumar, N.
DOI：
10.1016/j.patrec.2018.04.006
发表时间：
2019-04
期刊：
Pattern Recognit. Lett.
影响因子：
--
作者：
Claudio Loconsole;Giacomo Donato Cascarano;Antonio Brunetti;Gianpaolo Francesco Trotta;Giacomo Losavio;Vitoantonio Bevilacqua;E. Sciascio
通讯作者：
Claudio Loconsole;Giacomo Donato Cascarano;Antonio Brunetti;Gianpaolo Francesco Trotta;Giacomo Losavio;Vitoantonio Bevilacqua;E. Sciascio
利用表面肌电信号识别眉毛情绪表情
影响因子：
6
作者：
Chen, Yumiao;Yang, Zhongliang;Wang, Jiangping
通讯作者：
Wang, Jiangping