Fatigue detection system with haar cascade classifier

Drowsy driving is one of the major contributing factors to Malaysia's rising accident statistics. Drowsiness may be caused by a few reasons including fatique. Therefore, this study proposes a design for image processing to detect fatique during driving using the Raspberry Pi 3 board. The Haar Cascade Classifier technique is used to recognize eyes and faces, while the Eye Aspect Ratio (EAR) algorithm is used to detect eyes blink (open and close) to fulfil the research's goal. The system's average EAR value ranged from 0.125 while the eyes were closed to 0.299 when the eyes were opened. This project is an upgraded version of a previous project that includes an LCD display with a touch panel and interaction between driver and system. For future improvement, a GPS can be implemented into the system so it can inform the driver the nearest Rest & Relaxation so they can go take a rest after receiving several warnings