摘要
利用人眼图像的几何特征与灰度特征,提出一种改进的虹膜定位算法.首先采用圆 Hough 变换结合曲线段长度检测法提取虹膜的外边界,提高了对颗粒噪声的抵御能力;然后在虹膜外边缘内部使用阈值法提取内边界;最后,分别用几何方法和阈值法去眼睑和眼睫毛、反光点等干扰信息.由 Matlab 仿真结果可以看出,提出的定位算法具有良好的准确性和鲁棒性。
A new location algorithm is presented,which is based on geometric features and grey scale information.Firstly,because of iris's circular features,the advanced circular Hough transform is employed to deduce the radius and center coordinates of iris boundaries.The detection of the iris/pupil boundary is performed within the iris region,instead of the whole eye region.So a lot of useless information is isolated keeping the whole iris information.Successful results of noise(eyelids,eyelashes and specular reflections)isolation are achieved using geometric and thresholding methods,which is the base of the exact iris recognition.The:MATLAB simulation results show the good accuracy and robustness of the proposed location algorithm.
出处
《红外与激光工程》
EI
CSCD
北大核心
2006年第z4期102-106,共5页
Infrared and Laser Engineering
