Driving fatigue and drowsiness significantly contribute to road accidents, posing a threat to both drivers and other road users. This paper presents a driver drowsiness detection system that utilizes computer vision and machine learning techniques to enhance transportation safety. By continuously capturing real-time images of the driver using a webcam, the system analyzes the state of the driver's eyes and detects signs of drowsiness and fatigue using specific algorithms. The proposed system focuses on minimizing accidents caused by drowsy drivers by providing immediate alerts through visual and auditory alarms. The system incorporates machine learning algorithms, leveraging the eye aspect ratio and eyepoints to accurately detect eye closure and yawning. The scalability and efficiency of the proposed system architecture make it suitable for larger-scale deployment. By employing computer vision algorithms, the system achieves improved accuracy and faster model training. Through the integration of intelligent vehicle systems, this driver drowsiness detection system aims to reduce the frequency of accidents caused by driver fatigue and contribute to overall transportation safety