FEDA: Fine-grained emotion difference analysis for facial expression recognition. (January 2023)

• Record Type: Journal Article
• Authors: Liu, Hanwei; Cai, Huiling; Lin, Qincheng; Zhang, Xiwen; Li, Xuefeng; Xiao, Hui
• Is Part Of: Biomedical signal processing and control. Volume 79(2023)Part 2
• Publication Date: 2023-01
• Subjects: Facial expression recognition -- Cluster analysis -- Correlation analysis -- Fine-grained emotion; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104209
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The complexity and confusion of emotions and the subjectivity of observers. Correlation analysis of fine-grained emotional representation. Variable fine-grained emotion representations based on clustering algorithm. Emotion correlation analysis based on recognition and facial action units. Emotion representation model with high-efficiency facial expression recognition. Abstract: Facial expression recognition (FER) has an important role in intelligent human–computer interaction. The complexity and confusion of target emotions and the subjectivity of observers make the definition of emotion categories controversial, and low accuracy has become a bottleneck in facial expression recognition analysis. To establish an emotion representation model with efficient facial expression recognition, this study presents FEDA, a fine-grained emotion difference analysis based on correlation, and explores the issue of emotion categories with appropriate intraclass correlation and interclass differences. First, a clustering algorithm is employed to obtain variable fine-grained emotion representations. Second, the correlation is objectively analysed through recognition and facial action units. Last, an emotion representation model that supports high-efficiency FER is obtained. Through a test with the FERPlus public dataset, the recognition accuracy rate reached 91.5% for the first time, verifying the rationality of our emotion representation model. Our experimental results can also support the effective establishment of emotion representation models based on facial expression recognition and have a role in promoting the diagnosis and treatment of mental illness, as well as technological development in the fields of human–computer interaction, security, and robotics services. The codes and training logs are publicly available at https://github.com/liuhw01/FEDA .