The COVID-19 pandemic has significantly impacted global public health, prompting the adoption of preventive measures, including mask-wearing in public spaces. This approach has proven effective in reducing the transmission of infectious diseases. With the rapid advancement of deep learning and computer vision technologies, object detection has seen remarkable progress, opening new possibilities for real-time applications, such as detecting mask usage. This research leverages the YOLO11 object detection algorithm to detect and classify the use of face masks accurately. By merging the Face Mask Dataset (FMD) and the Medical Mask Dataset (MMD), we create a unified dataset that facilitates comprehensive training and evaluation of the model’s performance. Our experiments show that the YOLO11m model achieves an average accuracy of 93.8% and a mean average precision (mAP) of 98.4% for the “good” classification, outperforming previous models applied to the FMD and MMD datasets. These results highlight the effectiveness of YOLO11m in detecting medical face masks, providing a promising solution to enhance public health safety.