Construction and optimization of an intelligent mask wearing detection system under YOLOv5 framework

In order to reduce the risk of epidemic transmission caused by public health incidents and remind citizens to raise self-protection awareness, this article introduces the design and implementation method of a mask wearing detection system. This method relies on high pixel cameras to capture and detect faces, which can effectively identify whether people are wearing masks to remind them to wear masks and improve the efficiency of epidemic prevention and control. Use 2000 annotated and processed images as the dataset for training the model, and train the model using the YOLOv5 algorithm to generate model and recognition accuracy data. The detection system utilizes the pyqt5 development library to build a complete human-computer interaction interface, realizing image upload function, video upload function, and interactive operations such as detection, basically realizing the functions of the mask wearing detection system. After system testing, it has been verified that the system can improve the detection efficiency of wearing masks, reduce the labor cost of detection, and make epidemic detection more convenient and efficient.