Please wait a minute...
FITEE
Front. Inform. Technol. Electron. Eng.  2015, Vol. 16 Issue (4): 272-282    DOI: 10.1631/FITEE.1400209
    
基于Kinect的实时面部情感识别
Qi-rong Mao, Xin-yu Pan, Yong-zhao Zhan, Xiang-jun Shen
Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China
Using Kinect for real-time emotion recognition via facial expressions
Qi-rong Mao, Xin-yu Pan, Yong-zhao Zhan, Xiang-jun Shen
Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China
 全文: PDF 
摘要： 目的：基于Kinect提取面部表情特征，实现对视频中面部情感实时识别。
创新点：基于Kinect提出一种新颖的面部情感识别方法，充分发挥出Kinect高速易用的优势，可实时对视频序列最新连续帧中表现出的情感进行综合判定。识别方法涉及两种不同形式的表情特征，对此我们也针对性地提出基于最大置信的融合算法。
方法：首先，运用Kinect中Face Tracking SDK从实时视频数据中追踪人脸、提取面部运动单元信息和特征点坐标（图3、4）。然后，将这两类特征信息并行处理，在它们各自特征通道中，特征数据经7元1-vs-1分类器组进行预识别，将得到的预识别结果存入缓存用于情感置信统计，置信度最高的即为此通道中的情感识别结果（图2）。最后，融合这两个特征通道的结果即可得到最终情感识别结果（图1）。
结论：基于Kinect提取到的两种面部表情特征（面部运动单元信息和特征点坐标），提出一种新颖高效的面部情感识别方法，实现对视频中面部情感实时识别。
关键词： Kinect;  情感识别;  面部表情;  实时分类;  融合算法;  支持向量机    
Abstract: Emotion recognition via facial expressions (ERFE) has attracted a great deal of interest with recent advances in artificial intelligence and pattern recognition. Most studies are based on 2D images, and their performance is usually computationally expensive. In this paper, we propose a real-time emotion recognition approach based on both 2D and 3D facial expression features captured by Kinect sensors. To capture the deformation of the 3D mesh during facial expression, we combine the features of animation units (AUs) and feature point positions (FPPs) tracked by Kinect. A fusion algorithm based on improved emotional profiles (IEPs) and maximum confidence is proposed to recognize emotions with these real-time facial expression features. Experiments on both an emotion dataset and a real-time video show the superior performance of our method.
Key words: Kinect    Emotion recognition    Facial expression    Real-time classification    Fusion algorithm    Support vector machine (SVM)
收稿日期: 2014-06-12 出版日期: 2015-04-03
CLC:  TP391.4  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Qi-rong Mao
Xin-yu Pan
Yong-zhao Zhan
Xiang-jun Shen

引用本文:

Qi-rong Mao, Xin-yu Pan, Yong-zhao Zhan, Xiang-jun Shen. Using Kinect for real-time emotion recognition via facial expressions. Front. Inform. Technol. Electron. Eng., 2015, 16(4): 272-282.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/FITEE.1400209    或    http://www.zjujournals.com/xueshu/fitee/CN/Y2015/V16/I4/272

[1] Jun-hong Zhang, Yu Liu. 应用完备集合固有时间尺度分解和混合差分进化和粒子群算法优化的最小二乘支持向量机对柴油机进行故障诊断[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(2): 272-286.
[2] Miguel Oliver, Francisco Montero, José Pascual Molina, Pascual González, Antonio Fernández-Caballero. 应用于康复治疗的多摄像系统：微软Kinect传感器的精度研究[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(4): 348-364.
[3] Mohammad Mosleh, Hadi Latifpour, Mohammad Kheyrandish, Mahdi Mosleh, Najmeh Hosseinpour. 运用支持向量机的稳健智能音频水印设计[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(12): 1320-1330.
[4] G. R. Brindha, P. Swaminathan, B. Santhi. 一种观点挖掘新词语权重过程性能分析[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(11): 1186-1198.
[5] Gurmanik Kaur, Ajat Shatru Arora, Vijender Kumar Jain. 基于体位特征使用混杂模型预测血压对于无支撑后背的反应[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(6): 474-485.
[6] Zheng-wei Huang, Wen-tao Xue, Qi-rong Mao. 基于无监督特征学习的语音情感识别方法[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(5): 358-366.
[7] Ya-tao Zhang, Cheng-yu Liu, Shou-shui Wei, Chang-zhi Wei, Fei-fei Liu. 基于非线性支持向量机和遗传算法的移动ECG质量评估[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(7): 564-573.
[8] Kai-sheng Luo, Zheng Shi, Xiao-lang Yan, Zhen Geng. 基于支持向量机的反向光刻版图重定向算法[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(5): 390-400.
[9] Li Chen, Ying-chun Yang, Zhao-hui Wu. 用于情感说话人识别的精细失真特征检测与修正[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(10): 903-916.