Mask Detection Using the YOLO (You Only Look Once) Method

The COVID-19 pandemic has emphasized the importance of wearing masks as a preventive measure. To facilitate mask detection and ensure compliance, computer vision techniques have been widely utilized. This research aims to develop a mask detection system using the YOLO (You Only Look Once) method. YOLO is a real-time object detection method that provides accurate and efficient results. The proposed system utilizes a pre-trained YOLO model trained on a dataset comprising images of individuals with and without masks. The YOLO model can detect and locate faces, as well as differentiate between individuals wearing masks and those who are not. The method works by dividing the image into a grid and predicting bounding boxes and class probabilities for each grid cell. This approach enables real-time mask detection with minimal computational overhead. Experimental evaluations were conducted using various relevant benchmark datasets. The evaluation results demonstrate that the mask detection system using the YOLO method achieves high detection rates and fast response times. This research is expected to contribute to the effort of monitoring mask usage to control the spread of COVID-19.