摘要
文中提出了一种改进的红外图像中瞳孔定位算法。在红外暗瞳图像中,首先用阈值分割获得候选瞳孔区域,通过形态学运算、团块筛选获得瞳孔区域,对该区域进行边缘检测、斑点去除和椭圆拟合等处理,精确定位瞳孔。实验结果表明,该算法能够很好的克服反射光斑、睫毛及阴影等干扰问题,保证较高的正确率。
An improved algorithm is proposed to locate pupil rapidly.Firstly,threshold segmentation is used to get candidate pupil area in infrared dark eye diagram after human eye localization.Then,the pupil area is determined through the morphological operation and blob screening.Finally,accurate pupil location is get through edge detection,spots removal and ellipse fitting.The experimental results show that,the algorithm has greater accuracy and can overcome interference problems including reflected light spot,eyelashes,and shadow excellently.
作者
胡艳红
魏江
HU Yan-hong;WEI Jiang(School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710072,China)
出处
《电子设计工程》
2019年第1期189-193,共5页
Electronic Design Engineering
关键词
瞳孔定位
阈值分割
椭圆拟合
形态学
pupil location
threshold segmentation
ellipse fitting
morphological
