Classification of Personal Protective Equipment with Quantum Transfer Learning in Industrial Training

Sulla Valdivia A.L.; Castillo Caceres C.P.; Sulla Torres J.A. · ICCMB 2026 - Proceedings of 2026 the 9th International Conference on Computers in Management and Business (2026) · DOI: 10.1145/3802463.3802473

Resumen

Compliance with Personal Protective Equipment (PPE) in mechanical training workshops is essential but complex to monitor consistently. This work presents a Quantum Transfer Learning (QTL) pipeline that couples a pre-trained classical feature extractor with a variational quantum classifier to recognize helmet-use conditions in industrial training footage. We target a three-class setting - correct helmet use, incorrect helmet use, and no helmet - using transfer features from a lightweight convolutional backbone and a Basic-Entangler-type parameterized quantum circuit optimized with the Adam optimizer. The dataset comprises images collected in a controlled mechanical-training environment, with standard splits and class imbalance typical of educational settings. A proof-of-concept evaluation on the QTL-Helmet subset reports a test accuracy of 71.45% after 50 epochs. Furthermore, a significant reduction in training time was observed when using GPUs compared to CPUs, demonstrating the efficiency of accelerated computing. The model shows the viability of the quantum-classical approach for classification tasks with moderate computational resources. While preliminary and below operational thresholds, the study surfaces concrete levers for improvement within the QTL paradigm: stronger data curation and augmentation tailored to PPE attributes, better class rebalancing, deeper classical backbones for richer embeddings, circuit-depth/ansatz search with regularization, and hybrid ensembling of multiple shallow quantum heads. We also outline deployment considerations for near-term quantum hardware via simulator-to-hardware transfer and batching strategies. These results establish a reproducible baseline for quantum-enhanced PPE recognition in industrial and educational contexts and delineate a roadmap to close the performance gap through data, architecture, and training refinements, bringing QTL closer to practical safety monitoring in Industry 4.0.

Instituciones: Universidad Católica de Santa María