Drowsy driving is a significant contributor to road accidents and fatalities, prompting active research in the detection of driver fatigue. While conventional methods exist, they can be either intrusive or require expensive sensors and data handling. In response, this study develops a low-cost, real- time driver's drowsiness detection system using a webcam to record video and image processing techniques to detect the driver's face and compute facial landmarks. By analyzing the eye aspect ratio, mouth opening ratio, and nose length ratio, the system can detect drowsiness based on an adaptive thresholding algorithm. Additionally, offline machine learning algorithms can alert drivers when drowsiness is detected. This system aims to reduce accidents caused by driver fatigue by detecting special body and facial gestures, such as yawning and eye movements, and proposing a new method for detecting yawning based on changes in mouth geometricfeatures.