Detection of Drowsy Driver's through Eye State Analysis

the increasing number of traffic accidents due to a drivers diminished vigilance level has become a serious problem for society. Some of these accidents are the result of the drivers medical condition. However, a majority of these accidents are related to driver fatigue, drowsiness of drivers. Car accidents associated with driver fatigue are more likely to be serious, leading to serious injuries and deaths. In this paper, an algorithm for drivers drowsiness detection based on eye states tracking is presented. I use a database which contains 150 images captured from different people in various conditions for better results. These images are captured using a camera located in a car in front of the driver. These images are used for tracking as input of the proposed method. In first step I use color space for drivers face detection and crop the face from background. In the next step, I estimate the area of the eyes and crop image from this region. Then top and bottom coordinates of the eyes are located using retrench the face pixels from this area and canny operator for edge detection. In the last step I count the number of white and black pixels and compare the distance between these coordinates for recognition of the drivers fatigue.