北京航空航天大学学报 ›› 2020, Vol. 46 ›› Issue (9): 1797-1806.doi: 10.13700/j.bh.1001-5965.2020.0073

• 论文 • 上一篇    下一篇

基于联合正则化策略的人脸表情识别方法

兰凌强, 李欣, 刘淇缘, 卢树华   

  1. 中国人民公安大学 警务信息工程与网络安全学院, 北京 102600
  • 收稿日期:2020-03-02 发布日期:2020-09-22
  • 通讯作者: 卢树华 E-mail:lushuhua@ppsuc.edu.cn
  • 作者简介:兰凌强 男,硕士研究生。主要研究方向:计算机视觉;李欣 男,博士,副教授,硕士生导师。主要研究方向:信息技术;刘淇缘 女,硕士研究生。主要研究方向:计算机视觉;卢树华 男,博士,副教授,硕士生导师。主要研究方向:安全防范技术。
  • 基金资助:
    国家重点研发计划(2016YFC0801005);中央高校基本科研业务费专项资金(2019JKF225)

Facial expression recognition method based on a joint normalization strategy

LAN Lingqiang, LI Xin, LIU Qiyuan, LU Shuhua   

  1. College of Police Information Technology and Cyber Security, People's Public Security University of China, Beijing 102600, China
  • Received:2020-03-02 Published:2020-09-22
  • Supported by:
    National Key R & D Program of China (2016YFC0801005); the Fundamental Funds for the Central Universities (2019JKF225)

摘要: 针对目前人脸表情识别大多采用基于深度学习的端到端特征提取及分类方法的现象,提出了一种新的深度模型优化方法。基于ResNet18残差网络架构和正则化思想,提出了联合正则化策略,即将过滤器响应正则化和批量正则化、实例正则化和组正则化、组正则化和批量正则化分别嵌入网络之中,平衡和改善特征数据分布,弥补单一正则化的缺点,提升模型性能。在2个公开数据集FER2013和CK+进行了验证和测试,最高准确率分别达到了73.558%和94.9%,实验结果表明,联合正则化策略提高了基础网络的性能,其表现优于诸多当前较新的人脸表情识别方法。

关键词: 表情识别, 联合正则化策略, 过滤器响应正则化, 批量正则化, 组正则化

Abstract: As for that end-to-end feature extraction and classification based on deep learning often used in facial expression recognition, a new method of depth model optimization has been proposed. This paper proposes the joint optimization strategies learned from ResNet18 residual network and normalization ideas, that is, filter response normalization and batch normalization, instance normalization and group normalization, as well as group normalization and batch normalization were embedded in the network, respectively, to balance and improve the distribution of feature data, make up for the shortcomings of single regularization, and improve model performance. The validation and test were carried out on the two public datasets FER2013 and CK+, and the highest accuracy rates are 73.558% and 94.9%, respectively. The experimental results indicate that the joint optimization strategy enhances the performance of the basic network, which is better than most of the latest facial expression recognition methods.

Key words: expression recognition, joint strategy, filter response normalization, batch normalization, group normalization

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发