Drowsiness Detection System Based on Machine Learning Using Eye State

Drowsiness is one of the major causes driver-induced traffic accidents. The interactive systems developed to reduce road accidents by alerting drivers called as Advanced Driver Assistance Systems (ADAS). most important ADAS are Lane Departure Warning System, Front Collision System and Systems. In this study, an system based on eye state detection presented detect driver drowsiness. First, Viola-Jones algorithm approach used face areas in proposed method. detected region classified closed or open making use a machine learning Finally, conditions analyzed at time domain with PERcentage eyelid CLOsure (PERCLOS) metric drowsiness determined Support Vector Machine (SVM), kNN decision tree classifiers. methods tested 7 real people states 99.77%, 94.35%, 96.62% accuracy, respectively.