Eye center localization is considered a crucial step for many human–computer interaction (HCI) real-time applications. Detecting the center of eye (COE), accurately and in real time, is very challenging due to the wide variation of poses, eye appearance and specular reflection, especially in low-resolution images. In this paper, an accurate real-time detection algorithm of the COE is proposed. The proposed approach depends on the image gradient to detect the COE. The computational complexity is minimized and the accuracy is improved by down sampling the face resolution and applying a rough-to-fine algorithms, to reduce the search area, in accordance with the Eye Region Of Interest (EROI) and the number of COE candidates, tested by the proposed algorithm. Also, the detection algorithm is applied on a limited number of pixels that represent the iris boundary of the COE candidates. The Look Up Tables (LUTs) are implemented to, initially, store the invariant elements of the proposed image gradient-based algorithm, to reduce the detection time. Before applying the proposed COE detection approach, a modified specular reflection method is used to improve the detection accuracy. The performance of the proposed algorithm has been evaluated by applying it to three benchmark databases: the BIOID, GI4E and Talking Face video datasets, at different face resolutions. Experimental results revealed that the accuracy of the proposed algorithm is up to 91.68% and 96.7% for BIOID and GI4E datasets, respectively, while the minimum achieved average detection time is 2.7 ms. The promising results highlight the potential of the proposed algorithm to be used in some eye gaze-based real-time applications. Comparing the proposed method with the most state-of-the-art approaches showed that the system outperforms most of them and has a comparable performance with the others, in terms of the COE localization accuracy and detection speed.

眼中心定位被认为是许多人机交互（HCI）实时应用程序的关键步骤。由于姿势，眼睛外观和镜面反射的变化很大，尤其是在低分辨率图像中，准确且实时地检测眼中心（COE）极具挑战性。本文提出了一种精确的实时检测COE的算法。所提出的方法取决于图像梯度来检测COE。根据感兴趣的眼睛区域（EROI）和COE候选者的数量，通过对人脸分辨率进行下采样并应用从粗到细的算法来减少搜索区域，可以最大程度地减少计算复杂度并提高准确性。通过提出的算法进行测试。也，检测算法应用于代表COE候选对象的虹膜边界的有限像素。查找表（LUT）最初用于存储所提出的基于图像梯度的算法的不变元素，以减少检测时间。在应用提出的COE检测方法之前，先使用一种改进的镜面反射方法来提高检测精度。通过将其应用到三个基准数据库（不同的面部分辨率下的BIOID，GI4E和Talking Face视频数据集），已评估了该算法的性能。实验结果表明，该算法对BIOID和GI4E数据集的准确性分别达到91.68％和96.7％，而平均检测时间最短为2.7 ms。令人鼓舞的结果凸显了该算法在某些基于眼睛注视的实时应用中的潜力。将建议的方法与最先进的方法进行比较表明，该系统的性能优于大多数方法，并且在COE定位精度和检测速度方面具有与其他方法相当的性能。