With the growing demand for modern transportation, there has been a significant increase in the number of vehicles on the road. As automobiles become an essential mode of transportation globally, driver drowsiness has emerged as a major contributor to accidents and fatalities. While numerous complex systems have been developed to detect drowsiness, they often require sophisticated hardware or high computational resources, making them less accessible for widespread use. This study proposes a novel, simplified yet highly efficient driver drowsiness detection system, designed to balance accuracy with computational efficiency. Utilizing Python and the Dlib model, the system detects drowsiness by analyzing the aspect ratios of the eyes and mouth based on facial landmark points. The system’s effectiveness will be validated through both pre-recorded videos from a recognized public dataset and real-time videos collected in a controlled environment. Preliminary tests suggest that the proposed approach offers comparable detection accuracy with significantly reduced computational complexity, making it well-suited for real-time applications in low-cost environments.