摘要
针对虹膜定位中存在的速度与准确性相互制约的问题,该文提出一种分步式的灰度垂直投影和数理统计相结合的新颖定位算法:首先利用最小二乘法和二值化图像完成瞳孔定位;接着利用Canny算子对平滑去噪后的虹膜进行边缘检测;然后通过灰度垂直投影筛选边缘信息,去除无用噪声干扰;最后利用数理统计的方法求出外圆参数,完成虹膜外圆定位。与经典Daugman和Wildes算法相比较,该文算法在速度、准确率、鲁棒性方面均表现理想。
For the problem of speed and accuracy are constrained each other on the iris localization,this pa per proposes a new localization algorithm based on the gray vertical projection and the mathematical statis tics:Firstly,using the least squares method and the binary image to complete the pupil localization;secondly, using Canny operator for edge detection;then through gray vertical projection to eliminate the edge noise;Fi nally by using the mathematical statistics method to derive the circle Parameters,and complete the iris outer location.Compared with the Daugman and Wildes algorithm,the proposed algorithm stand out in speed,ac curacy and robustness.
出处
《电子质量》
2014年第2期12-16,共5页
Electronics Quality
关键词
虹膜内外圆定位
分步式
灰度垂直投影
CANNY算子
数理统计
Iris inner and outer location
Multiple-Step
Gray Vertical Projection
Canny Operator
Mathemati-cal statistics