An eye state analysis (i.e., open or closed) is an important step in the detection of fatigue driving. In this paper, a weighted color difference matrix algorithm is proposed for analyzing a driver’s eye state. First, an image of the driver’s eye is obtained from a face detection database. Two feature images are then constructed for the eye image, which are each gray-scale normalized. The feature image is then projected into a block feature matrix, and the feature value is calculated to construct a feature vector. Finally, a support vector machine is used to train and classify the extracted eigenvectors, and the state of the driver’s eye is judged to further analyze the driver’s state of fatigue. To evaluate the performance of the proposed algorithm, experiments are conducted with several publicly available databases, showing that our algorithm is efficient and reasonable.
|