结合人脸图像和脑电的情绪识别技术  

Fusion of Facial Expressions and EEG for Emotion Recognition

作　　者：黄泳锐 杨健豪 廖鹏凯 潘家辉 

机构地区：[1]华南师范大学软件学院,佛山528225

出　　处：《计算机系统应用》2018年第2期9-15,共7页Computer Systems & Applications

基　　金：国家自然科学基金青年科学基金(61503143);广东省自然科学基金博士科研启动项目(2014A030310244);广州市科技计划项目珠江科技新星专题项目(201710010038)

摘　　要：本文通过人脸图像和脑电两个输入信号对情绪识别技术展开研究.采用对应不同情绪的电影片段对被实验者进行情绪刺激的方法采集输入信号.通过表情识别出八种基本表情的分类,通过脑电识别出情绪的三种强弱波动.通过决策层面的信息融合,进行情绪分类.最终的识别准确率达到89.5%,高于采用单模态进行识别的准确率,分别为:表情识别:81.35%,脑电识别:71.53%.This study focuses on emotion recognition technology. The input signals are EEG and facial expression. The stimuli are based on a subset of movie clips that correspond to four specific areas of valance-arousal emotional space. In facial expression detection, one of the four basic emotional states is determined. In EEG detection, one of the three emotional intensities is determined. Emotion recognition is based on a decision-level fusion of both EEG and facial expression detection. The results show that the accuracy of information fusion detection is 89.5%, which is higher than that of facial expression（81.35%） or EEG detection（71.53%）.

关 键 词：情绪识别 计算机视觉 脑机接口 机器学习 决策层信息融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]