Study On The Recognition Of Eye States In The Driver Drowsiness Detection System

Driver fatigue is one of the important causes of serious accidents. It results in a lot of people's deaths or injuries and directly or indirectly tremendous economic loss. Therefore, many countries make great efforts on how to detect drowsiness during driving. Based on the detection of driver's eye states, this paper tries to set up a driver drowsiness detection system that can issue prompt warnings when necessary.This paper mainly covers the following works:1．The method of face detection, eye location, eye states recognition and some techniques of digital image treatment are studied. Based on the current algorithms, the algorithm adapted to the system is presented.2．A new method using the geometrical characteristics of human face and the center of gravity of image is presented for the eye location. The experiments have proved that it is a very effective method and it is also applicable for the eye-closed images.3．A method using the gray-level projection and Hough transform is presented for the eye states detection.4．The algorithm of face location, eye location, eye tracking and eye states recognition are integrated in order to determine drowsiness. Several videos are treated in the simulation system.