眼睛状态检测的组合方法

Combined Method of Eye States Detection

眼睛状态的检测具有广泛的应用.详细介绍了5种检测眼睛状态的方法,即灰度模板方法、Fisher方法、投影的方法、找眼睛上眼睑的方法、用Hough变换找眼珠的方法.通过对这5种方法进行组合,提高了眼睛状态检测的准确率.通过对396个眼睛进行检测,准确率达到了95.2％.实验结果表明了这5种算法组合算法的有效性,抗光照能力强;同时适中的复杂性也说明了该组合算法的可行性.

There are many applications of the robust eye states detection. In this paper, five methods are applied to detect the eye states in color eye images. They are gray model method, fisher method, projection method, detect-upper-eyelid method and detect-eyeball method. Each of the five methods has its advantage as well as its disadvantage. To increase the accuracy of detection, a combined method is proposed, which combines the above five methods so that it can take good advantage of them all. Experiments are done with 396 different human eyes, 264 of which are closed ones, and 377 of these experiments turned out satisfactory results. The accuracy reaches 95. 2 %. The inspiring outcome shows that the combined method is effective even if the illumination is nonlinear. At the same time, the combined method is practical because it is moderate in both time and space consuming. This paper introduces in details the idea of the five methods, the design of the combined algorithm, the experiments and their relevant results.