Chirra, V., ReddyUyyala, S. and KishoreKolli, V. (2019) Deep CNN: A Machine Learning Approach for Driver Drowsiness Detection Based on Eye State. Revue d’Intelligence Artificielle, 33, 461-466.
https://doi.org/10.18280/ria.330609

has been cited by the following article:

• TITLE: Driver Drowsiness Detection Based on Eye Blinking Using Convolutional Neural Network Approach

  AUTHORS: Mithun Kumar, Mahmudur Rahman, Jakir Khan, Abu Sale Mohammad Mostafizur Rahman

  KEYWORDS: Artificial Intelligence, Driver Drowsiness Detection System, Deep Learning, Haar Cascade Algorithm, Machine Learning

  JOURNAL NAME: Journal of Computer and Communications, Vol.13 No.9, September 26, 2025

  ABSTRACT: This research presents a Driver Drowsiness Detection System (DDDS) that uses a Convolutional Neural Network (CNN) to improve road safety. The system uses a vast dataset of 97,860 images from the internet and 55,900 images created, achieving a combined accuracy of 99.66%. The individual datasets show exceptional performance, with the internet source dataset achieving 99.71% accuracy and the created dataset achieving 99.94%. The methodology prioritizes safety and reliability, resulting in a stable driver frame that meets functional requirements. The research approach uses advanced computer vision techniques, including edge detection, grayscale conversion, and dilation, to preprocess images from the MRL eye dataset. The methodology employs an OpenCV program for the precise detection of critical areas, specifically eyes and faces, using the Haar Cascade program. This work introduces a state-of-the-art solution to driver sleepiness detection and emphasizes the importance of a diverse and comprehensive dataset for robust model training.