Drowsy driving poses a significant risk to road safety, leading to accidents with potentially severe consequences. To address this issue, we propose a driver drowsiness detection system utilizing yawning as a prominent indicator of driver fatigue. Yawning is a physiological response closely associated with drowsiness and can serve as a reliable marker for assessing driver alertness levels. Our system employs facial recognition and machine learning algorithms to detect and analyze yawning instances captured by vehicle-mounted cameras. Features such as yawning duration, frequency, and intensity are extracted and fed into a classification model trained to distinguish between normal behavior and signs of drowsiness. The detection of yawning is efficient and works under different situations. This project describes on how to detect the mouth in a video recorded from the. Within the video, the member will drive the driving reenactment framework and a camera will be setup in front of the driver. The video will be recorded using the webcam to record the moves of the driver. The image-processing model will detect the are of mouth and then capture the yawning from the frames generated from the video. The facial analysis is popular research areas these days, which is used for face recognition, tracking human for security, etc. This project is focused on the localization of mouth, which involves looking at the entire image of the face, and determining the position of mouth, by applying the existing methods in image- processing algorithm. Once the position of the mouth is located, the system is designed to determine whether the mouth is opened or closed, and detect fatigue and drowsiness.