结合小波变换和Log-Gabor滤波的虹膜识别方法  

Iris recognition algorithm combining wavelet transform and Log-Gabor filter

作　　者：周治平[1] 吴会军[1] 

机构地区：[1]江南大学通信与控制工程学院,江苏无锡214122

出　　处：《计算机应用》2009年第8期2095-2097,共3页journal of Computer Applications

摘　　要：提出了一种将小波变换和Log-Gabor滤波结合起来进行虹膜识别的方法:小波分解后的低频子带包含了虹膜图像的主要信息,而Log-Gabor滤波能有效提取图像的纹理信息。将归一化的虹膜图像进行两层小波分解,再取其低频子带进行Log-Gabor滤波并量化生成虹膜模板,采用汉明距进行快速分类。实验结果验证了本算法具有很好的识别率和等错率。An algorithm combining wavelet transform and Log-Gabor filter was presented for iris recognition. The low frequency sub-image of the wavelet transform contains the primary information of the iris, and the Log-Gabor filter can effectively extract the iris texture information. The combination of these two approaches is an effective way to extract iris texture. This algorithm firstly decomposed the normalized image by the wavelet transform, then the low frequency sub-image was filtered by Log-Gabor to generate the iris code, finally Hamming distance was used to classify the iris images. The experimental results show the algorithm is superior in terms of recognition rate and equal error rate.

关 键 词：虹膜识别 小波变换 Log—Gabor滤波器 汉明距 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]