Fatigued driving stands as a critical factor contributing to road accidents and fatalities. Detecting driver drowsiness is a significant area of research, with existing methods falling into three categories: vehicle-based, behavior-based, or physiological-based. Many of these methods are intrusive, distracting to drivers, or require costly sensors and complex data handling. The planned system is a cost-effective drowsiness detection and alerting system for drivers, utilizing visual cues from the driver to achieve better accuracy. Our approach relies on monitoring a driver's visual behavior using a webcam and employing a Support Vector Machine (SVM) algorithm. This application utilizes an integrated webcam to capture frames (images) of the driver. By leveraging the OpenCV SVM algorithm, we detect features from the face using these images and check whether the driver exhibits signs of drowsiness, such as consecutive eye blinking or yawning. When drowsiness is detected, the application issues timely alerts to the driver. The system utilizes an SVM for drowsiness detection and employs the Euclidean distance function to continuously evaluate the proximity of eye and mouth movements to drowsiness thresholds, promptly notifying the driver when these thresholds are breached.