EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Dynamic Multi-Scale Convolution Model for Face Recognition Using Event-Related Potentials

Shengkai Li iD, Tonglin Zhang, Fangmei Yang, Xian Li, Ziyang Wang, Dongjie Zhao

Sensors · 2024

DOI: 10.3390/s24134368 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Shengkai Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Qingdao University, Qingdao 266071, China. Hauptthemen laut MEDLINE: Evoked Potentials, Facial Recognition. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the development of data mining technology, the analysis of event-related potential (ERP) data has evolved from statistical analysis of time-domain features to data-driven techniques based on supervised and unsupervised learning. However, there are still many challenges in understanding the relationship between ERP components and the representation of familiar and unfamiliar faces. To address this, this paper proposes a model based on Dynamic Multi-Scale Convolution for group recognition of familiar and unfamiliar faces. This approach uses generated weight masks for cross-subject familiar/unfamiliar face recognition using a multi-scale model. The model employs a variable-length filter generator to dynamically determine the optimal filter length for time-series samples, thereby capturing features at different time scales. Comparative experiments are conducted to evaluate the model’s performance against SOTA models. The results demonstrate that our model achieves impressive outcomes, with a balanced accuracy rate of 93.20% and an F1 score of 88.54%, outperforming the methods used for comparison. The ERP data extracted from different time regions in the model can also provide data-driven technical support for research based on the representation of different ERP components.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Evoked PotentialsFacial RecognitionHumansElectroencephalographyAlgorithmsFace

Stichwörter der Autor:innen

familiar and unfamiliar face recognitionmaskmulti-scale

Autor:innen und Institutionen

  • School of Automation, Qingdao University, Qingdao 266071, China.
  • State Key Laboratory of Multimodal Artifcial Intelligence Systems, The Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
  • School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100190, China.
  • Shandong Key Laboratory of Industrial Control Technology, Qingdao University, Qingdao 266071, China.

ORCID-Profile: Shengkai Li

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, S., Zhang, T., Yang, F., Li, X., Wang, Z., & Zhao, D. (2024). A Dynamic Multi-Scale Convolution Model for Face Recognition Using Event-Related Potentials. Sensors. https://doi.org/10.3390/s24134368

Vancouver

Li S, Zhang T, Yang F, Li X, Wang Z, Zhao D. A Dynamic Multi-Scale Convolution Model for Face Recognition Using Event-Related Potentials. Sensors. 2024. doi:10.3390/s24134368

BibTeX
@article{Li2024,
  author = {Li, Shengkai and Zhang, Tonglin and Yang, Fangmei and Li, Xian and Wang, Ziyang and Zhao, Dongjie},
  title = {A Dynamic Multi-Scale Convolution Model for Face Recognition Using Event-Related Potentials},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24134368}
}
Kostenlos starten →