An Improved Real Time Eye State Identification System in Driver Drowsiness Detection

Real time eye state detection is a key problem in driver drowsiness detection. This paper proposes an real-time eye state detection system to identify driver´s drowsy state. The system optimize several image processing techniques to get better performance to reach the criteria of the drowsiness detection methods. Firstly, face region is detected using the optimized Haar-like feature detection scheme; secondly, we apply horizontal projection of the detected face and geometrical position of the eye on the face to get the eye region; finally, a new complexity function with dynamic threshold to identify the eye state. The method in our paper makes better balance between accuracy and efficiency than lots of other methods. The system is optimized with Intel IPP (Integrated Performance Primitives) and experiment results show that it can meet the acquisition of real time.