EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Domain Consistency Constraints-Based Deep Neural Network for Facial Expression Recognition

Xiaoliang Zhu iD, Junyi Sun, Gendong Liu, Chen Shen, Zhicheng Dai iD, Liang Zhao

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Facial RecognitionNeural Networks, ComputerMachine LearningLearningFacial Expression

Stichwörter der Autor:innen

JS divergenceattention consistencyattention mechanismfacial expression recognition

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}
}
Kostenlos starten →