摘要
针对经典虹膜定位算法速度较慢的问题,提出一种基于圆几何特征的粗定位与精定位结合的快速虹膜定位算法。基于行列扫描的方法找到瞳孔内4条弦,利用弦的中垂线结合瞳孔边界阈值定位四对切点,取切点坐标参数的均值为内边缘粗略定位参数,然后利用微积分方法对内边缘进行精确定位;利用内外边缘圆心非常接近的先验知识,缩小微积分方法定位外边缘的搜索范围,从而显著提高了虹膜定位速度。实验结果表明,该算法显著提高了虹膜定位速度且具有较高的定位精度。
to the slow speed problem of classic iris location algorithm, a fast iris location algorithm is proposed, which com-bined with fine positioning and coarse positioning based on the geometrical characteristic of circle.bined with fine positioning and coarse positioning based onthe geometrical characteristic of circle. First, four strings are found in iuner boundary based on the row and column scanning method, using perpendicular bisector of strings combine boundary threshold to locate four pairs oftangency point, making use of the mean of tangent point coordinates parameters as the coarse inner edge parameters, then use the priori knowledge that the center of inner boundary and outer boundary is very close, narrowing the search range of calculus method to locate outer boundary, and thus significantly improve the locating speed. The expermental results show that the algorithm has high location accuracy and improves location speed markedly.
出处
《计算机工程与设计》
CSCD
北大核心
2010年第18期4058-4061,共4页
Computer Engineering and Design
关键词
虹膜定位
圆几何特征
内边缘粗定位
外边缘定位
微积分方法
iris location
geometry characteristic
inner edge coarse detection
out edge detection
calculus method