首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于深度学习的面部表情识别方法综述
引用本文:党宏社,王淼,张选德.基于深度学习的面部表情识别方法综述[J].科学技术与工程,2020,20(24):9724-9732.
作者姓名:党宏社  王淼  张选德
作者单位:陕西科技大学大学电气与控制工程学院,西安710021;陕西科技大学大学电气与控制工程学院,西安710021;陕西科技大学大学电气与控制工程学院,西安710021
基金项目:国家自然科学基金(61871260)
摘    要:人脸表情识别就是让计算机按照人类的思维理解表情,是人机交互的重要组成,然而随着深度学习的迅速发展,深度学习技术在人脸表情领域的研究也成为研究热点,所以对深度学习技术在表情识别中的应用及取得的成果进行分析。首先总结了几种常用表情数据集;然后从特征提取和特征分类两方面对基于深度学习的表情识别方法进行了分类,并从网络改进方面分析了基于深度学习的表情识别中的几种网络改进方法;最后阐述了表情识别这一领域中面临的挑战和未来发展。

关 键 词:深度学习  表情识别  特征提取  表情分类
收稿时间:2020/1/19 0:00:00
修稿时间:2020/6/14 0:00:00

A Survey of Facial Expression Recognition Methods Based on Deep Learning
DANG Hong-she,WANG Miao,ZHANG Xuan-de.A Survey of Facial Expression Recognition Methods Based on Deep Learning[J].Science Technology and Engineering,2020,20(24):9724-9732.
Authors:DANG Hong-she  WANG Miao  ZHANG Xuan-de
Institution:College of electrical and control engineering, Shaanxi University of science and technology
Abstract:Facial expression recognition is to make computer understand facial expression according to human thinking, which is an important part of human-computer interaction. However, with the rapid development of deep learning, the research of deep learning technology in facial expression field has become a research hotspot, so the application and achievements of deep learning technology in facial expression recognition were analyzed. Firstly, several common expression data sets were summarized; then, the expression recognition methods based on deep learning were classified from two aspects of feature extraction and feature classification, and several network improvement methods in expression recognition based on deep learning were analyzed from the aspect of network improvement; finally, the challenges and future development in the field of expression recognition were described.
Keywords:deep learning      expression recognition      feature extraction      expression classification
本文献已被 万方数据 等数据库收录!
点击此处可从《科学技术与工程》浏览原始摘要信息
点击此处可从《科学技术与工程》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号