Many road accidents now happen because of drivers not paying enough attention or being vigilant. We call this driver sleepiness. This results in numerous unfavorable circumstances that negatively impact people’s life. The driver fatigue identification and appropriate handling of such information is the primary objective of this study. There are numerous techniques that rely on how the car moves or how the driver behaves. The physiological method is one of the techniques that helps keep the driver awake and distracted from his tiredness. A small number of techniques also deal with large amounts of data and costly sensors. As a result, this research creates a mechanism that can precisely and properly identify sleepiness in real time. This technology captures and records the driver's facial expressions using a while simultaneously keeping an eye on the driver's health. Each frame's movements are all recognized. The MOR and eye aspect ratio are calculated. The estimated values are contrasted with the basis given by the module, and the variation in value initiates the detection process. In order to increase efficiency, the vehicle speed will be lowered anytime drowsiness is detected. Additionally, offline machine-learning techniques are used.