DriDrowsy: An enhanced framework for drowsiness detection
DOI:
https://doi.org/10.31181/jdaic10026122025dKeywords:
Eye Aspect Ratio (EAR), facial features, image pre-processing, haar cascade, object detection, image segmentation, Mouth Opening Ratio (MOR)Abstract
Road accidents remain one of the leading causes of non-natural deaths worldwide, and driver distraction is a major contributor. Among the various forms of distraction, drowsiness is particularly dangerous as it greatly increases the likelihood of traffic collisions. Detecting drowsiness early and issuing timely alerts can help prevent such incidents by encouraging drivers to take necessary breaks. This paper presents an image-based drowsiness detection method that utilizes the Eye Aspect Ratio (EAR) and Mouth Opening Ratio (MOR) in combination with a modified Haar Cascade model. The system detects facial indicators of drowsiness that include yawning, closed eyelids, and partially closed eyes through thresholding and expression analysis. Experimental results show that the method achieves an accuracy of over 96.75% in identifying drowsy states. This proposed method is experimentally tested on three different benchmarked data sets. By consistently monitoring driver alertness, this approach offers a promising solution for reducing fatigue-related road accidents and enhancing overall driving safety.
Downloads
References
ANSI/ASHRAE Standard 55 (2023). Thermal Environmental Conditions for Human Occupancy. https://www.ashrae.org/technical-resources/bookstore/standard-55-thermal-environmental-conditions-for-human-occupancy, Accessed 14 August 2025.
Arunpandian, J., & Gunasekaran, V. (2024). Enhanced Road Safety Through Intelligent Lane Detection and Driver Drowsiness Monitoring. 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT) (pp. 1-7). Kamand: IEEE.
Bakheet, S., & Al-Hamadi, A. (2021). A Framework for Instantaneous Driver Drowsiness Detection Based on Improved HOG Features and Naïve Bayesian Classification. Brain Sciences, 11(2), 240.
Biswas, S., Saha, T., Banerjee, P., & Datta, S. (2023). A novel facial emotion recognition technique using convolution neural network. In Singh, P., Singhal, P., Mishra, P. K., & Vatsa, A. K., Heterogeneous Computational Intelligence in Internet of Things (pp. 175–195). Boca Raton: CRC Press.
Chen, S., Wang, Z., & Chen, W. (2021). Driver Drowsiness Estimation Based on Factorized Bilinear Feature Fusion and a Long-Short-Term Recurrent Convolutional Network. Information, 12(1), 3.
Choudhury, P., Thakur, K., & Datta, S. (2023). An application of convolutional neural networks in recognition of handwritten digits. In Singh, P., Singhal, P., Mishra, P. K., & Vatsa, A. K., Heterogeneous Computational Intelligence in Internet of Things (pp. 261–276). Boca Raton: CRC Press.
Datta, S., & Chaki, N. (2015). Detection of dental caries lesion at early stage based on image analysis technique. 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS) (pp. 89-93). Bhubaneswar: IEEE.
Datta, S., Chaki, N., & Modak, B. (2019). A Novel Technique to Detect Caries Lesion Using Isophote Concepts. IRBM, 40(3), 174–182.
Datta, S., Chaki, N., & Modak, B. (2023). A novel technique for dental radiographic image segmentation based on neutrosophic logic. Decision Analytics Journal, 7, 100223.
Dua, H. K., Goel, S., & Sharma, V. (2018). Drowsiness detection and alert system. 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN) (pp. 621-624). Greater Noida: IEEE.
Ed-Doughmi, Y., Idrissi, N., Hbali, Y. (2020). Real-Time System for Driver Fatigue Detection Based on a Recurrent Neuronal Network. Journal of Imaging, 6(3), 8.
Fahmy, H. (2023). Drowsiness detection dataset: UnityEyes - Openned/Closed Eyes - Sleepy Driver Detection. https://www.kaggle.com/datasets/hazemfahmy/openned-closed-eyes, Accessed 3 November 2025.
Global status report on road safety 2018. (2018). Geneva: World Health Organization. file:///C:/Users/p-c/Downloads/9789241565684-eng.pdf, Accessed 18 August 2025.
Horne, J., & Reyner, L. (1999). Vehicle accidents related to sleep: A review. Occupational and Environmental Medicine, 56(5), 289–294.
Jebraeily, Y. (2023). Drowsy Detection Dataset: Stay Awake, Stay Safe: A Dataset for Drowsiness Detection on Kaggle. https://www.kaggle.com/dsv/8311245, Accessed 17 August 2025.
Kawashima, H. (2021). Active appearance models. In Ikeuchi, K. (Ed.), Computer Vision: A Reference Guide (pp. 11-15). Cham: Springer.
Kolus, A. (2024). A Systematic Review on Driver Drowsiness Detection Using Eye Activity Measures. IEEE Access, 12, 97969-97993.
Kolus, A., Wells, R. P., & Neumann, W. P. (2023). Examining the relationship between human factors related quality risk factors and work related musculoskeletal disorder risk factors in manufacturing. Ergonomics, 66(7), 954-975.
Lenin, N. C., Padmanaban, S., Bhaskar, M. S., Mitolo, M., & Hossain, E. (2021). Ceiling Fan Drives–Past, Present and Future. IEEE Access, 9, 44888-44904.
Luo, Y, WU, C-m, & Zhang, Y. (2013). Facial expression feature extraction using hybrid PCA and LBP. The Journal of China Universities of Posts and Telecommunications, 20(2), 120-124.
Magán, E., Sesmero, M. P., Alonso-Weber, J. M., & Sanchis, A. (2022). Driver Drowsiness Detection by Applying Deep Learning Techniques to Sequences of Images. Applied Sciences, 12(3), 1145.
Mohana, B., & Sheela Rani, C. M. (2019). Drowsiness Detection Based on Eye Closure and Yawning Detection. International Journal of Recent Technology and Engineering, 8(4), 8941–8944.
Moujahid, A., Dornaika, F., Arganda-Carreras, I., & Reta, J. (2021). Efficient and compact face descriptor for driver drowsiness detection. Expert Systems with Applications, 168, 114334.
Patil, P. V. (2020). Drowsiness detection dataset: Classify based on whether eyes are closed or open. https://www.kaggle.com/datasets/prasadvpatil/mrl-dataset, Accessed 29 December 2024.
Rastogi, A., & Ryuh, B. S. (2019). Teat detection algorithm: Yolo vs. Haar-cascade. Journal of Mechanical Science and Technology, 33(4) 1869–1874.
Saeed, K., Datta, S., & Chaki, N. (2020). A Granular Level Feature Extraction Approach to Construct HR Image for Forensic Biometrics Using Small Training DataSet. IEEE Access, 8, 123556-123570.
Singh, J., Kanojia, R., Singh, R., Bansal, R., & Bansal, S. (2023). Driver drowsiness detection system: An approach by machine learning application. arXiv preprint: https://doi.org/10.48550/arXiv.2303.06310.
Zhang, W., Cheng, B., & Lin, Y. (2012). Driver drowsiness recognition based on computer vision technology. Tsinghua Science and Technology, 17(3), 354-362.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Journal of Decision Analytics and Intelligent Computing
This work is licensed under a Creative Commons Attribution 4.0 International License.
All site content, except where otherwise noted, is licensed under the 