Drowsiness Detection by Exploring Facial Expression

Abstract

Exploration of facial expressions has been an interesting area of research for various applications. Drowsiness identification is one such application that can be explored from facial expression. The paper proposes a system that detects the drowsiness state of the driver by using a continuous face-tracking algorithm, without equipping the driver with any external bodily gadgets. The system independently tracks the eye and mouth regions using facial landmarks. The parameters extracted from the eye region are eye aspect ratio and blink rate while computation of mouth opening indicates yawning as a sign of fatigue of the driver. The experimentation involves investigating 30 participants (drivers) to evaluate the system's performance. The experimentation revealed that the system accurately determined the driver fatigue state, and the system was found to be independent of variations in the age group, gender, and eye capture status (with or without wearing eyeglasses). The thresholds set for eye aspect ratio and yawning have provided the best accuracy in detecting the drowsiness state for any unknown test driver with minimum response time. The proposed model is fast and reliable and the alert system helps to restore the driver's attention avoiding consequences due to fatigue of the driver.