• Gayatri Baragi
• K R Sumana

Road safety remains a critical concern worldwide, with driver fatigue being a significant contributing factor to traffic accidents. This project aims to develop an advanced driver drowsiness detection system using deep learning techniques. Leveraging datasets of open and closed eye images, and implementing algorithms such as Inception v3 and Convolutional Neural Networks (CNN), the system achieves high accuracy in identifying signs of drowsiness. Integration of dlib for facial landmark detection enhances the system's capability to monitor critical features like eye closure, yawning, and head tilting. Deployed in a real-time monitoring application using Flask, the Inception v3 model achieved an accuracy of 98%, while the CNN model reached 96%. This robust system offers a potent solution to detect drowsiness, potentially reducing the risk of accidents caused by driver fatigue.

Image Processing, Facial Landmarks Detection, Deep Learning Algorithms, Drowsiness Detection.

"OPTIMIZING ROAD SAFETY: ADVANCED SOLUTIONS FOR DETECTING AND MITIGATING DRIVER DROWSINESS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.h350-h353, July-2024, Available :http://www.jetir.org/papers/JETIR2407745.pdf

"OPTIMIZING ROAD SAFETY: ADVANCED SOLUTIONS FOR DETECTING AND MITIGATING DRIVER DROWSINESS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. pph350-h353, July-2024, Available at : http://www.jetir.org/papers/JETIR2407745.pdf