DRIVER DROWSINESS DETECTION VIA EYE BLINK RATE

Abstract

Driver drowsiness is one of the major causes of road accidents worldwide, leading to reduced alertness, slower reaction time, and impaired decision-making ability while driving. To address this critical issue, this project proposes a Driver Drowsiness Detection System based on eye blink rate analysis using computer vision and machine learning techniques. The system continuously monitors the driver through a camera and analyzes facial landmarks to detect eye movements in real time. By calculating the Eye Aspect Ratio (EAR), the system determines whether the driver’s eyes are open or closed and identifies signs of fatigue when the eyes remain closed beyond a predefined threshold. The proposed model uses computer vision algorithms such as Histogram of Oriented Gradients (HOG) for face detection and machine learning techniques including Support Vector Machine (SVM) and Convolutional Neural Networks (CNN) to improve classification accuracy between alert and drowsy states. Image preprocessing techniques such as grayscale conversion, noise reduction, and facial landmark extraction are applied to enhance detection reliability under different lighting and environmental conditions. The system evaluates performance using metrics such as accuracy, precision, recall, and F1-score to ensure reliable predictions. Once drowsiness is detected, an alert mechanism such as a warning message or alarm is triggered to notify the driver immediately, helping prevent potential accidents. This approach provides a non-intrusive, cost-effective, and real-time monitoring solution without requiring wearable sensors. The proposed system contributes to intelligent transportation systems by improving road safety and reducing fatigue-related accidents, making it a practical and scalable solution for modern vehicles and driver safety applications.