Facial Emotion Recognition Based on Biorthogonal Wavelet Entropy, Fuzzy Support Vector Machine, and Stratified Cross Validation
Facial Emotion Recognition Based on Biorthogonal Wavelet Entropy, Fuzzy Support Vector Machine, and Stratified Cross Validation
复制标题
DOI：
10.1109/access.2016.2628407
复制
发表时间：
2016-11
期刊：
影响因子：
3.9
通讯作者：
Yudong Zhang;Zhang Yang;Huimin Lu-;Xingxing Zhou;Preetha Phillips;Qing-Ming Liu;Shuihua Wang
中科院分区：
文献类型：
--
作者：
Yudong Zhang;Zhang Yang;Huimin Lu-;Xingxing Zhou;Preetha Phillips;Qing-Ming Liu;Shuihua Wang
情绪识别是指面部肌肉的位置和运动。它在许多领域作出了重大贡献。目前的方法并没有取得很好的效果。本文旨在提出一种新的基于面部表情图像的情感识别系统。我们招募了20名受试者，让每个受试者摆出七种不同的情绪：快乐、悲伤、惊讶、愤怒、厌恶、恐惧和中性。然后利用双正交小波熵提取多尺度特征，并利用模糊多类支持向量机作为分类器。采用分层交叉验证作为严格的验证模型。统计分析表明，该方法的总体准确率为96.77±0.10%。此外，我们的方法优于三种最先进的方法。总之，该方法是有效的。
Emotion recognition represents the position and motion of facial muscles. It contributes significantly in many fields. Current approaches have not obtained good results. This paper aimed to propose a new emotion recognition system based on facial expression images. We enrolled 20 subjects and let each subject pose seven different emotions: happy, sadness, surprise, anger, disgust, fear, and neutral. Afterward, we employed biorthogonal wavelet entropy to extract multiscale features, and used fuzzy multiclass support vector machine to be the classifier. The stratified cross validation was employed as a strict validation model. The statistical analysis showed our method achieved an overall accuracy of 96.77±0.10%. Besides, our method is superior to three state-of-the-art methods. In all, this proposed method is efficient.