Driving fatigue and drowsiness are major contributors to road accidents, endangering both drivers and other road users. This paper introduces a real-time driver drowsiness detection system that leverages computer vision and machine learning techniques to enhance road safety. The system utilizes a webcam to continuously capture images of the driver, analyzing eye states to detect signs of drowsiness and fatigue. By employing algorithms that monitor eye aspect ratios and yawning patterns, the system provides immediate visual and auditory alerts to prevent accidents caused by drowsy driving. The integration of machine learning algorithms and computer vision ensures high accuracy and efficient model training, making the system scalable for broader deployment. This approach aims to reduce accident rates due to driver fatigue and contribute to overall transportation safety.

Machine Learning, Driver Drowsiness Detection, Behavioral Analysis, OpenCV, CNN