基于关键点的眼睛定位和状态估计  

EYE LOCATION AND STATE ESTIMATION BASED ON LANDMARKS

作　　者：何勇 孙哲南[2] 王财勇 王云龙 朱宇豪 He Yong;Sun Zhenan;Wang Caiyong;Wang Yunlong;Zhu Yuhao(School of Computer Science,Hunan University of Technology,Zhuzhou 412007,Hunan,China;Institute of Automation,China Academy of Sciences,Beijing 100190,China)

机构地区：[1]湖南工业大学计算机学院,湖南株洲412007 [2]中国科学院自动化研究所,北京100190

出　　处：《计算机应用与软件》2022年第4期185-192,共8页Computer Applications and Software

基　　金：国家自然科学基金项目(61427811,U1836217)。

摘　　要：眼睛定位和状态估计是虹膜、巩膜、眼周等生物特征识别中重要的预处理过程。非合作环境下捕获的眼睛图像经常面临严重的遮挡和复杂的背景。为此提出一种鲁棒而准确的基于眼睛关键点的单阶段方法去定位眼睛的位置并估计眼睛的左右和开闭状态。为了训练和评估提出的模型,手工标注一个新的数据集OCE-1000,每幅图像标注左右两只眼睛共8个关键点,以及左右眼的开闭状态。实验结果表明,提出的模型在OCE-1000数据集上达到了98%的关键点定位准确率,眼睛状态估计的准确率为97%。Eye location and state estimation are key steps in the preprocessing of biometrics recognition such as iris, sclera and periocular. Eye images captured in the non-cooperative environments often suffer from serious occlusions and complex backgrounds. To solve this problem, this paper proposes a robust and accurate single-stage framework based on eye landmarks to detect eye key points and estimate the left, right and open and closed states of eyes. In order to train and evaluate the proposed model, a new OCE-1000 dataset was created and manually labeled with eight key points, open and close state for left and right eyes of each image. Experimental results show that the proposed model achieves 98% accuracy of landmark location and 97% accuracy of eye state estimation on OCE-1000 dataset.

关 键 词：生物特征识别 眼睛关键点定位 眼睛状态估计 残差网络 堆叠沙漏网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]