Driver Drowsiness Detection System Using Machine Learning

Driver drowsiness is a significant factor in road accidents, leading to substantial fatalities and injuries.Various systems have been developed to monitor driver alertness to mitigate this risk.This paper explores a driver drowsiness and yawning detection system using the dlib library, which provides machine learning algorithms and tools for facial recognition and landmark detection.The proposed system leverages Dlib's capabilities to monitor eye and mouth movements, thereby detecting early signs of drowsiness and yawning.A key aspect of the system is the use of the Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) to measure eye closure duration and yawning detection, a critical indicator of drowsiness.This method does not require any special hardware installations, making it highly accessible and easy to implement using standard cameras.This paper details the design, implementation, and testing of the system, highlighting its effectiveness and potential for real-world application.By identifying early signs of driver fatigue, the system