Driver Drowsiness Detection Using Machine Learning

• Author(s):

  G. Bala Murugan | S. Harish Babu

• Keywords:

  Driver Drowsiness Detection, Convolutional Neural Network, Facial Feature Extraction, Eye Blink Detection, Real-Time Monitoring, Deep Learning, Road Safety, OpenCV.

• Abstract:

  Driver Drowsiness Is One Of The Leading Causes Of Road Accidents Worldwide, Posing A Significant Threat To Human Life And Road Safety. This Paper Presents A Real-time Driver Drowsiness Detection System Employing Convolutional Neural Networks (CNNs) To Analyze Facial Cues Captured Via An In-vehicle Camera. The System Monitors Critical Fatigue Indicators Including Eye Closure Rate, Blink Frequency, Mouth State (yawning), And Head Orientation. A Modular Pipeline — Encompassing Image Acquisition, Face Detection Using Haar Cascades/SSD, Facial Landmark Extraction With OpenCV/Dlib, And CNN-based Drowsiness Classification — Enables Robust Real-time Inference. Upon Detecting Drowsiness, The System Triggers Multi-modal Alerts To Prompt Corrective Driver Action. Experimental Results Demonstrate High Detection Accuracy Across Varied Lighting And Environmental Conditions, Making The Proposed System A Viable Enhancement For Modern Vehicle Safety Systems.

---

Other Details

• Paper id:

  IJSARTV12I4105087

• Published in:

  Volume: 12 Issue: 4 April 2026

• Publication Date:

  2026-04-20

Download Article