• Aman Raj
• D N Sujatha
• S Uma
• V Padmapriya

Driver drowsiness is one of the main sources of car crashes. This calls for implementing a real-time monitoring system, which is the only way to improve road safety. The paper we are presenting here is a driver drowsiness detection system that includes the use of computer vision and deep learning techniques. The system utilizes Media Pipe Face Mesh for facial landmark detection to obtain Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) so that it can detect one even if the eye is closed for a long time, yawning, and the head is tilted accurately. A PyQt5-based GUI offers real-time monitoring with an on-screen display and status updates. An audio alert is sent out when a signal of fatigue or loss of the driver's attention is found, for example, no face for a certain period. Our system shows very high responsiveness and real-world applicability; thus, it intends to lower the cases of drowsiness that result in car crashes to the greatest extent possible.

Driver drowsiness detection, eye aspect ratio (EAR), mouth aspect ratio (MAR), Media Pipe Face Mesh, computer vision, deep learning, real-time monitoring, PyQt5 GUI, road safety, alert system.

"Driver Drowsiness Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 12, page no.b758-b764, December-2025, Available :http://www.jetir.org/papers/JETIR2512196.pdf

"Driver Drowsiness Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 12, page no. ppb758-b764, December-2025, Available at : http://www.jetir.org/papers/JETIR2512196.pdf