Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186023,
        author = {Mounika Paluri and Rama Krishna and Md ishaq and Jagadheesh B and Deepak and Mohiddin Sk and Mrs Balaji Rohitha},
        title = {Real-Time Driver Drowsiness and Yawning Detection System Using Vision-Based Facial Landmark Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {4217-4224},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186023},
        abstract = {Driver fatigue represents a major causative factor in traffic accidents globally, contributing to significant mortality and economic burden. This investigation proposes a resilient, eco- nomical, and rapid-response methodology for identifying driver drowsiness and yawning episodes through computer vision-based facial feature examination. Our methodology employs the Medi- aPipe platform for accurate facial landmark identification and OpenCV for live video analysis to determine Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR). A Python-developed soft- ware component handles incoming visual data from conventional webcams. When persistent irregular EAR or MAR readings suggestive of fatigue are recognized, it interfaces with an Arduino Uno microcontroller through serial communication to initiate audible alarms. This manuscript comprehensively outlines the system architecture, mathematical principles underlying fatigue assessment, detailed implementation procedures, experimental arrangements, and validation criteria. Rigorous testing across varied illumination circumstances, head positions, and diverse subjects reveals sustained detection precision surpassing 90% with complete system delay under 100 ms. These outcomes verify the approach’s viability, performance, and suitability for extensive automotive integration in private and commercial transport applications.},
        keywords = {Driver Fatigue Detection, Computer Vision, OpenCV, MediaPipe, Eye Aspect Ratio, Mouth Aspect Ratio, Arduino, Real-Time Systems, Embedded Systems, ADAS},
        month = {November},
        }