一种基于Harris角点检测的快速瞳孔定位方法  

Fast Pupils Localization Method Based on Harris Corner Detection

作　　者：王力[1] 唐琎[1] 许海柱[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410075

出　　处：《液晶与显示》2008年第1期87-90,共4页Chinese Journal of Liquid Crystals and Displays

基　　金：教育部留学回国人员科研启动基金项目资助(No.2005383)

摘　　要：提出了一种基于灰度投影曲线和Harris角点检测进行人眼定位的新算法。首先利用原图的垂直灰度投影曲线确定人脸的左右边界,然后利用人脸区域的水平灰度投影确定头顶至鼻子中部的上下边界,最后利用Harris角点检测算法快速定位瞳孔,精确定位人眼的位置。文章算法成功地将Harris角点检测算法应用到瞳孔定位中,实验结果表明,该算法不受眉毛的干扰,具有较小的运算量和较高的处理速度,而且定位准确,准确率较高,很好地解决了简单背景下人眼的快速定位问题。A new fast method of pupils localization based on gray-level projection and Harris corner detection is proposed. First, the left and right boundaries of face is localized with vertical gray-level projection. Secondly,face region＇s horizontal gray-level projection is used to localize the top of the head and the middle of the nose. Finally, locating the exact positions of pupils rapidly using Harris corner detection,accordingly,the exact positions of the eyes is located. This algorithm is successful Harris corner detection algorithm applied to the pupil position, the experimental results demonstrate that the algorithm without the interference of eyebrow, a smaller computing capacity and higher processing speed and locating accuracy, higher accuracy rate, solve a human eye＇s rapid positioning in simple background.

关 键 词：瞳孔定位 垂直灰度投影 水平灰度投影 HARRIS角点检测 

分 类 号：TN27[电子电信—物理电子学] TP242.62[自动化与计算机技术—检测技术与自动化装置]