Heuristic objective for facial expression recognition

被引:10
作者
Li, Huihui [1 ]
Xiao, Xiangling [1 ]
Liu, Xiaoyong [1 ]
Guo, Jianhua [1 ]
Wen, Guihua [2 ]
Liang, Peng [1 ]
机构
[1] Guangdong Polytech Normal Univ, Sch Comp Sci, Guangzhou 510665, Peoples R China
[2] South China Univ Technol, Sch Comp Sci & Engn, Guangzhou 510064, Peoples R China
基金
中国国家自然科学基金;
关键词
Facial expression recognition; Domain knowledge; Objective function; Heuristics; FACE; NETWORK;
D O I
10.1007/s00371-022-02619-7
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Facial expression recognition has been widely used in lots of fields such as health care and intelligent robot systems. However, recognizing facial expression in the wild is still very challenging due to variations, light intensity, occlusions and the ambiguity of human emotion. When training samples cannot include all these environments, the classification can easily lead to errors. Therefore, this paper proposes a new heuristic objective function based on the domain knowledge so as to better optimize deep neural networks for facial expression recognition. Moreover, we take the specific relationship between the facial expression and facial action units as the domain knowledge. By analyzing the mixing relationship between different expression categories and then enlarging the distance of easily confused categories, we define a new heuristic objective function which can guide deep neural network to learn better features and then improve the accuracy of facial expression recognition. The experimental results verify the effectiveness, universality and the superior performance of our methods.
引用
收藏
页码:4709 / 4720
页数:12
相关论文
共 59 条
[1]   Emotion Recognition in Speech using Cross-Modal Transfer in the Wild [J].
Albanie, Samuel ;
Nagrani, Arsha ;
Vedaldi, Andrea ;
Zisserman, Andrew .
PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, :292-301
[2]  
Anderson JR., 1986, MACHINE LEARNING ART
[3]   Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution [J].
Barsoum, Emad ;
Zhang, Cha ;
Ferrer, Cristian Canton ;
Zhang, Zhengyou .
ICMI'16: PROCEEDINGS OF THE 18TH ACM INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 2016, :279-283
[4]   EmotioNet: An accurate, real-time algorithm for the automatic annotation of a million facial expressions in the wild [J].
Benitez-Quiroz, C. Fabian ;
Srinivasan, Ramprakash ;
Martinez, Aleix M. .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :5562-5570
[5]   Residual multi-task learning for facial landmark localization and expression recognition [J].
Chen, Boyu ;
Guan, Wenlong ;
Li, Peixia ;
Ikeda, Naoki ;
Hirasawa, Kosuke ;
Lu, Huchuan .
PATTERN RECOGNITION, 2021, 115
[6]   Toward Children's Empathy Ability Analysis: Joint Facial Expression Recognition and Intensity Estimation Using Label Distribution Learning [J].
Chen, Jingying ;
Guo, Chen ;
Xu, Ruyi ;
Zhang, Kun ;
Yang, Zongkai ;
Liu, Honghai .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (01) :16-25
[7]  
Chen SK, 2020, PROC CVPR IEEE, P13981, DOI 10.1109/CVPR42600.2020.01400
[8]   Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning [J].
Chen, Tianshui ;
Pu, Tao ;
Wu, Hefeng ;
Xie, Yuan ;
Liu, Lingbo ;
Lin, Liang .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (12) :9887-9903
[9]   Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition [J].
Chen, Tianshui ;
Lin, Liang ;
Chen, Riquan ;
Hui, Xiaolu ;
Wu, Hefeng .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (03) :1371-1384
[10]   Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition [J].
Chen, Tianshui ;
Xu, Muxin ;
Hui, Xiaolu ;
Wu, Hefeng ;
Lin, Liang .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :522-531