In order to improve the real-time localization accuracy and anti-jamming capability of the pupil center, an eye-tracking method was used based on the pupil-cornea tracking principle and image processing. As a result, accurate measurements of the centers of the pupil and corneal reflection were obtained. First, under the infrared light, an eye image was captured by a camera. In order to reduce the processing time, the image processing area was acquired by applying an adaptive binarization threshold. Second, the center of the corneal reflection was extracted by using a high threshold value and a low threshold value. Then, the optimum adaptive threshold value was calculated to get the location and size of the pupil. Finally, the feature points of the pupil edge were obtained by applying the gradient method, and the center of the pupil was located by a fitting ellipse. The results show that this algorithm can not only guarantee the accuracy and stability of obtaining the center of the pupil and the center of corneal reflection, but also meet the demands of real-time processing.%为了提高瞳孔中心的实时提取精度和抗干扰能力,利用基于瞳孔-角膜跟踪法原理和图像处理的眼动跟踪技术,实现瞳孔和角膜反射中心的精确提取.首先在红外光源条件下,用摄像机捕获人眼图像,通过图像自适应二值化阈值确定图像处理区域,以减小处理时间；其次,利用高低2次二值化阈值提取角膜反射中心；然后求取自适应最佳阈值确定瞳孔位置和大小；最后用梯度法提取瞳孔轮廓特征点,并用椭圆拟合瞳孔的方法确定瞳孔中心.实验结果表明,该算法在保证瞳孔和角膜反射中心提取的准确性和稳定性的同时,能满足实时处理要求.
展开▼
