一种Log-Gabor滤波器结合多分辨率分析的虹膜识别方法  

An Iris Recognition Method Using Log-Gabor Filter and Multi-Resolution Analysis

作　　者：唐荣年[1] 韩九强[1] 张新曼[1] 

机构地区：[1]西安交通大学电子与信息工程学院,西安710049

出　　处：《西安交通大学学报》2009年第4期30-33,61,共5页Journal of Xi'an Jiaotong University

基　　金：国家自然科学基金资助项目(60602025);教育部高等学校博士学科点专项科研基金资助项目(20050698025)

摘　　要：为提高虹膜识别算法的性能,提出了一种采用虹膜纹理全局信息的识别方法——全局信息识别法(IRBGT).该方法使用下采样运算得到不同分辨率下的虹膜图像,然后通过不同方向尺度的Log-Gabor滤波器组提取虹膜纹理的全局特征.最后,运用加权最小海明距离对生成的虹膜特征码进行匹配.与传统的Gabor虹膜识别方法相比,IRBGT方法在虹膜识别时更多地考虑了全局信息的可辨识力,能够降低等错误率和相同错误接收率下的错误拒绝率.对CASIA和UBIRIS虹膜库的测试结果表明,相比传统的Gabor虹膜识别方法,IRBGT方法在错误接受率为0.01%和0.1%时使错误拒绝率分别减小了0.54%±0.2%和0.35%±0.15%,使等错误率降低了约0.2%.A new method is proposed to improve the performance of iris recognition, which is named iris recognition based on global texture （IRBGT）. The method based on global information of iris texture, is realized through obtaining iris texture image with different resolutions by the down-sample algorithm. 2D Log-Gabor filters with different orientations are used to extract the global features of iris texture. The minimum weighted Hamming distance is used to test the similarity of two iris feature codes. The proposed method has lower equal error rate and lower false rejection rate at the same false acceptance rate than the traditional Gabor filter method has. Experiment results on the CASIA and UBIRIS iris database show that when the false acceptance rates are at 0.01% and 0. 1%, the false rejection rates of IRBGT are decreased by 0. 54%±0. 2% and 0. 35%±0. 15% respectively, and the equal error rate is decreased by about 0. 2%.

关 键 词：虹膜识别 Log—Gobar滤波器 多分辨率 全局信息 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]