On Vision Transformer Explainability for Personal Protective Equipment Detection: A Qualitative and Quantitative Analysis
Journal of Imaging · 30.04.2026 · 12 (5) · 195
DOI: 10.3390/jimaging12050195 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 30.04.2026. Verfasst von Miriam Di Renzo und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, 86100 Campobasso, Italy. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Istituto Nazionale per l'Assicurazione Contro gli Infortuni sul Lavoro.
Abstract (Originalsprache)
The safety of workers in industrial settings is ensured through the correct use of Personal Protective Equipment (PPE). The use of such equipment can be monitored using Deep Learning (DL). Federated Machine Learning (FML) is a technique that can be used in this context to preserve the privacy of sensitive information and provide explainability for the models adopted. Explainability techniques are an essential resource for interpreting the classification performed by the model. In this regard, this study aims to evaluate, through the adoption of specific similarity indices, the robustness and consistency of the explainability algorithms adopted to identify the areas of the images that are decisive for PPE classification. The dataset consists of 1600 real images representing work environments, in which staff are portrayed both with and without Personal Protective Equipment; specifically, there are workers wearing helmets, workers wearing reflective vests, workers wearing both devices and, finally, workers without any PPE. SSIM, VIF and SCC are the most relevant indices involved in the study. In the experimental phase, their mean values stand at 0.99, 0.96 and 0.96 for the intra-client study, and 0.96, 0.91 and 0.71 in the inter-client analysis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, 86100 Campobasso, Italy.
- Istituto Nazionale per l'Assicurazione Contro gli Infortuni sul Lavoro, 00144 Roma, Italy.
- Institute for High Performance Computing and Networking, National Research Council of Italy (CNR), 87036 Rende, Italy.
- Department of Engineering, University of Sannio, 82100 Benevento, Italy.
ORCID-Profile: Patrizia Agnello, Francesco Mercaldo
Förderung
- Istituto Nazionale per l'Assicurazione Contro gli Infortuni sul Lavoro
Zitieren
APA
Di Renzo, M., Niro, F., Agnello, P., Petyx, M., Martinelli, F., Cesarelli, M., Santone, A., & Mercaldo, F. (2026). On Vision Transformer Explainability for Personal Protective Equipment Detection: A Qualitative and Quantitative Analysis. Journal of Imaging, 12(5), 195. https://doi.org/10.3390/jimaging12050195
Vancouver
Di Renzo M, Niro F, Agnello P, Petyx M, Martinelli F, Cesarelli M, et al. On Vision Transformer Explainability for Personal Protective Equipment Detection: A Qualitative and Quantitative Analysis. Journal of Imaging. 2026;12(5):195. doi:10.3390/jimaging12050195
BibTeX
@article{DiRenzo2026,
author = {Di Renzo, Miriam and Niro, Filomena and Agnello, Patrizia and Petyx, Marta and Martinelli, Fabio and Cesarelli, Mario and Santone, Antonella and Mercaldo, Francesco},
title = {On Vision Transformer Explainability for Personal Protective Equipment Detection: A Qualitative and Quantitative Analysis},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {5},
pages = {195},
doi = {10.3390/jimaging12050195}
}
EUVIMED