摘要
为了更有效地提取虹膜纹理特征区域和进一步减小虹膜特征的存储空间,提出了一种基于分块相关性分析的二维不可分B-样条小波的虹膜识别方法,通过对虹膜归一化图像进行二维不可分B-样条小波变换并提取小波系数特征,把这些特征等分成正方形的特征块并按照相关性由大到小排序,保留相关性大的特征块进行匹配。实验表明,本文算法比经典的虹膜识别方法能更准确地捕捉识别效果好的特征区域。
In order to reduce storage space for saving iris feature and extract features efficiently for the iris texture, a correlation-based 2-D nonseparable B-spline wavelet transform approach is proposed for iris recognition. The proposed iris recognition algorithm extracts wavelet coefficients features from the normalized iris images by 2-D nonseparable Prspline wavelet transform, divides these features into square feature blocks equally, sorts the feature blocks in descending order, and preserves the feature blocks with large correlation value to match. Experiments show that the proposed algorithm can capture feature areas of good recognition performance more accurately than the classical iris recognition algorithms.
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2010年第4期593-597,共5页
Journal of Optoelectronics·Laser
基金
国家自然科学基金资助项目(60672078)
关键词
虹膜识别
小波
不可分
B-样条
相关性
iris recognition
wavelet
nonseparable
B-spline
correlation
