Eye State Detection Using Image Processing Technique

Estimation of driver fatigue is a significant factor in driver assistance system. Recent statistics shows that annually 1,550 deaths and 71,000 injuries are attributed to fatigue related accidents. Because of the hazard that drowsiness present on the road, methods need to be developed for counteracting its affects. The focus may be placed on designing a system that will accurately monitor the open or closed state of the driver's eyes. In this paper, an algorithm is proposed for determining the state of an eye, based on the mean and standard deviation of eye image. In the proposed algorithm, Skin segmentation and Lab transform is used to detect face and Eye. To know the state of eye, mean and standard deviation of eye area is determined. It is found from a result that if mean is >0.2 and standard deviation is <0.02 then the state of the eye is open otherwise closed. This method is tested on face database from M/s. Audio Visual Technologies Group (GTAV) and also a new database is created in-house for the testing purpose. The overall success rate of the algorithm is 89.5%.