Driver eye feature extraction based on infrared illuminator

Driver fatigue and decentralization of spirit at night is a major factor causing the night-time traffic accident. Eye location is the precondition to monitor driver´s fatigue state with image processing technique. Based on Otsu threshold segmentation algorithm, with the help of horizontal projection and vertical projection in binary image, the paper locates the driver face region accurately, and establishes eye location based on the region labeling algorithm. The paper also locates driver pupils efficiently and accurately by using the method of Harris corner detection. Experiments have proved good reliability and validity of the algorithms.