Action unit classification for facial expression recognition using active learning and SVM

Author:

Yao Li,Wan YanORCID,Ni Hongjie,Xu Bugao

Abstract

AbstractAutomatic facial expression analysis remains challenging due to its low recognition accuracy and poor robustness. In this study, we utilized active learning and support vector machine (SVM) algorithms to classify facial action units (AU) for human facial expression recognition. Active learning was used to detect the targeted facial expression AUs, while an SVM was utilized to classify different AUs and ultimately map them to their corresponding facial expressions. Active learning reduces the number of non-support vectors in the training sample set and shortens the labeling and training times without affecting the performance of the classifier, thereby reducing the cost of labeling samples and improving the training speed. Experimental results show that the proposed algorithm can effectively suppress correlated noise and achieve higher recognition rates than principal component analysis and a human observer on seven different facial expressions.

Publisher

Springer Science and Business Media LLC

Subject

Computer Networks and Communications,Hardware and Architecture,Media Technology,Software

Reference28 articles.

1. Abdul-Majjed IO (2017) Emotion recognition system based on facial expressions using svm. Recent Developments in Intelligent Computing, Communication and Devices. pp. 31–35.

2. AU R-CNN (2019) Encoding expert prior knowledge into R-CNN for action unit detection. Ma C., Chen L., Yong J. H. Neurocomputing

3. Benitez-Quiroz CF, Srinivasan R, Martinez AM (2016) EmotioNet: an accurate, real-time algorithm for the automatic annotation of a million facial expressions in the wild [C]// the IEEE conference on computer vision and pattern recognition (CVPR). IEEE:5562–5570

4. Chen L (2014) A fair comparison should be based on the same protocol--comments on "trainable convolution filters and their application to face recognition"[J]. IEEE Trans Pattern Anal Mach Intell 36(3):622–623

5. Cheng ZY, Shen JL (2016) On effective location-aware music recommendation[J]. ACM Trans Inf Syst 34(2):1–13

Cited by 42 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Sentiment and emotion analysis using pretrained deep learning models;Journal of Data, Information and Management;2024-07-31

2. FORMICARY SWARM OPTIMIZED DEEP CNN FOR FACIAL EMOTION RECOGNITION FROM HUMAN FACIAL EXPRESSIONS;Biomedical Engineering: Applications, Basis and Communications;2024-07-17

3. Automated photo filtering for tourism domain using deep and active learning: the case of Israeli and worldwide cities on instagram;Information Technology & Tourism;2024-07-02

4. Time to retire F1-binary score for action unit detection;Pattern Recognition Letters;2024-06

5. Scalable Real-time Emotion Recognition using EfficientNetV2 and Resolution Scaling;2024 10th International Conference on Web Research (ICWR);2024-04-24

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3