Abstract These The COVID-19 pandemic has emphasized the importance of wearing face masks as an effective measure to reduce the spreading of the virus. With the increasing demand for automated systems capable of detecting and classifying face mask wearing conditions, deep learning models have emerged as a powerful tool in this domain. In this research paper, we investigate the performance of the YOLOv8 (You Only Look Once) object detection algorithm for the classification of face mask wearing conditions. YOLOv8 is a state-of-the-art deep learning model known for its real-time object detection capabilities. The model is trained with Face Mask Detector(FMD) dataset to provide ground truth labels for training and evaluation purposes. We fine-tune the YOLOv8 model using transfer learning techniques on this dataset, enabling it to classify face mask wearing conditions accurately. The experiments performed demonstrate that the YOLOv8 model achieves excellent performance in face mask wearing condition classification. We evaluate the model on various metrics, including precision, recall, mAP, to assess its accuracy, sensitivity, and overall performance. The results show that the model successfully distinguishes between individuals wearing face masks, not wearing face masks, or wearing face masks incorrectly, with high precision and recall rates.The YOLOv5 model was also trained using the same dataset for comparative analysis.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|