EUVIMEDEUVIMED entdecken
Crossref

EfficientNetB0-Based Masked Face Recognition: A Robust Approach for Real-World Occlusion Scenarios

Girish Katkar, Lekha Prajapati, Ajay Ramteke

International Journal of Innovative Science and Research Technology · 25.04.2026 · 1805

DOI: 10.38124/ijisrt/26apr835 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 25.04.2026. Verfasst von Girish Katkar und 2 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread use of face masks during and after the COVID-19 pandemic has posed significant challenges to traditional face recognition systems that rely on complete facial features. This paper presents an efficient and robust masked face recognition approach based solely on the EfficientNetB0 architecture, achieving an accuracy of 97% on the MFR2 dataset. The proposed method leverages transfer learning to utilize pre-trained ImageNet features, enabling effective extraction of discriminative information from the visible upper facial regions while maintaining computational efficiency. The model is trained and evaluated on the MFR2 benchmark, which contains real-world masked and unmasked face images across multiple identities. Experimental results demonstrate that EfficientNetB0 can deliver high recognition performance with a relatively small number of parameters, making it suitable for resource-constrained environments. The approach effectively addresses key challenges such as facial occlusion, loss of identity-specific features, and the need for robust maskinvariant representations. This work contributes to the development of practical and scalable masked face recognition systems for real-world applications, including security, surveillance, and access control.

Zitieren

APA

Katkar, G., Prajapati, L., & Ramteke, A. (2026). EfficientNetB0-Based Masked Face Recognition: A Robust Approach for Real-World Occlusion Scenarios. International Journal of Innovative Science and Research Technology, 1805. https://doi.org/10.38124/ijisrt/26apr835

Vancouver

Katkar G, Prajapati L, Ramteke A. EfficientNetB0-Based Masked Face Recognition: A Robust Approach for Real-World Occlusion Scenarios. International Journal of Innovative Science and Research Technology. 2026:1805. doi:10.38124/ijisrt/26apr835

BibTeX
@article{Katkar2026,
  author = {Katkar, Girish and Prajapati, Lekha and Ramteke, Ajay},
  title = {EfficientNetB0-Based Masked Face Recognition: A Robust Approach for Real-World Occlusion Scenarios},
  journal = {International Journal of Innovative Science and Research Technology},
  year = {2026},
  pages = {1805},
  doi = {10.38124/ijisrt/26apr835}
}
Kostenlos starten →