Driver Drowsiness Prediction Based on Multiple Aspects Using Image Processing Techniques

The majority of the accidents were happening perpetually due to driver drowsiness over decades. Automation has been playing key role in many fields provide conformity and improve quality life users. Though various detection systems have developed during last decade based on factors, still demanding an improvement terms efficiency, accuracy, cost, speed, availability, etc. In this paper, proposed integrated approach depends Eye mouth closure status (PERCLOS) along with calculation new vector FAR (Facial Aspect Ratio) similarly EAR MAR. This helps find closed eyes or opened like yawning, any frame finds that hand gestures nodding covering as innate nature humans when trying control sleepiness. system also methods textural-based gradient patterns driver’s face directions identify sunglasses scenarios hands-on while yawning recognized addressed. work tested datasets such NTHU-DDD, YawDD, a dataset EMOCDS (Eye Mouth Open Close Data Set) proved better accuracy provides results general by considering circumstances.