Driver drowsiness is a critical factor contributing to road accidents worldwide. This research introduces a driver drowsiness detection system (DDDS) that employs computer vision techniques for real-time monitoring and alerting of driver drowsiness. The DDDS utilises OpenCV, Dlib, and Python to analyse facial landmarks and eye aspect ratio (EAR) from a webcam feed, enabling the identification of drowsiness signs. The DDDS continuously captures and processes video frames to detect specific facial landmarks, primarily focusing on eye and mouth regions. By calculating EAR and evaluating yawning patterns, the system assesses the driver’s level of alertness. When drowsiness is detected based on predefined thresholds, visual and audible alerts are triggered to notify the driver. This research project emphasises the integration of computer vision technology to address the pressing issue of drowsy driving. The DDDS provides a cost-effective and non-intrusive solution for enhancing driver safety by monitoring alertness in real time and issuing timely warnings. Its potential to reduce road accidents associated with drowsiness makes it a valuable tool for improving road safety. The DDDS serves as a significant step towards mitigating drowsy driving incidents, contributing to the overall goal of safer roadways.