Hybrid Domain Consistency Constraints-Based Deep Neural Network for Facial Expression Recognition
Sensors · 30.05.2023 · 23 (11) · 5201
DOI: 10.3390/s23115201 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 30.05.2023. Verfasst von Xiaoliang Zhu und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan 430079, China. Hauptthemen laut MEDLINE: Facial Recognition. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Social Science Foundation of China for Education Project, National Social Science Foundation of China for Education Project.
Abstract (Originalsprache)
Facial expression recognition (FER) has received increasing attention. However, multiple factors (e.g., uneven illumination, facial deflection, occlusion, and subjectivity of annotations in image datasets) probably reduce the performance of traditional FER methods. Thus, we propose a novel Hybrid Domain Consistency Network (HDCNet) based on a feature constraint method that combines both spatial domain consistency and channel domain consistency. Specifically, first, the proposed HDCNet mines the potential attention consistency feature expression (different from manual features, e.g., HOG and SIFT) as effective supervision information by comparing the original sample image with the augmented facial expression image. Second, HDCNet extracts facial expression-related features in the spatial and channel domains, and then it constrains the consistent expression of features through the mixed domain consistency loss function. In addition, the loss function based on the attention-consistency constraints does not require additional labels. Third, the network weights are learned to optimize the classification network through the loss function of the mixed domain consistency constraints. Finally, experiments conducted on the public RAF-DB and AffectNet benchmark datasets verify that the proposed HDCNet improved classification accuracy by 0.3–3.84% compared to the existing methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- National Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan 430079, China.
ORCID-Profile: Xiaoliang Zhu, Zhicheng Dai
Förderung
- the National Social Science Foundation of China for Education Project
- National Social Science Foundation of China for Education Project
Zitieren
APA
Zhu, X., Sun, J., Liu, G., Shen, C., Dai, Z., & Zhao, L. (2023). Hybrid Domain Consistency Constraints-Based Deep Neural Network for Facial Expression Recognition. Sensors, 23(11), 5201. https://doi.org/10.3390/s23115201
Vancouver
Zhu X, Sun J, Liu G, Shen C, Dai Z, Zhao L. Hybrid Domain Consistency Constraints-Based Deep Neural Network for Facial Expression Recognition. Sensors. 2023;23(11):5201. doi:10.3390/s23115201
BibTeX
@article{Zhu2023,
author = {Zhu, Xiaoliang and Sun, Junyi and Liu, Gendong and Shen, Chen and Dai, Zhicheng and Zhao, Liang},
title = {Hybrid Domain Consistency Constraints-Based Deep Neural Network for Facial Expression Recognition},
journal = {Sensors},
year = {2023},
volume = {23},
number = {11},
pages = {5201},
doi = {10.3390/s23115201}
}
EUVIMED