用于虹膜识别的轮廓波特征提取
收稿日期: 2010-02-25
修回日期: 2010-06-02
网络出版日期: 2011-01-25
基金资助
国家自然科学基金资助项目（60472006,60772117,60972136）;广州市科技计划项目（2009J1C401）
为获得高品质的虹膜纹理特征，针对小波变换方向选择性差的局限和虹膜图像纹理丰富的特点，本文提出了一种基于轮廓波(Contourlet)变换的虹膜特征提取方法。首先对预处理后的虹膜图像进行Contourlet分解，然后根据高低频子带所表征的信息，采用不同特征提取策略，提取其低频分量的均值及标准差和不同尺度、不同方向上高频子带变换系数矩阵的能量作为特征值，最后利用支持向量机和汉明距离的方法对CASIA Ver1.0和MMU两类虹膜库中的图像进行测试。实验结果表明，同基于Harr小波和离散余弦变换等特征提取方法相比，该方法可获得较好的识别性能。
罗忠亮1,2 ，林土胜1，李碧1,3 ，杨军1，张地2 . 用于虹膜识别的轮廓波特征提取[J]. 计算机工程与科学, 2011 , 33(1) : 77 -81 . DOI: 10.3969/j.issn.1007130X.2011.
In view of the limitation of poor direction selectivity about wavelet transform and iris image having rich texture features, an iris feature extraction method based on contourlet transform for obtaining high quality features is proposed in the paper. First of all, the preprocessed iris image is decomposed by contourlet, then, according to the information that high and low frequency subbands represent, it adopts different extraction ways, both the mean and variance of low frequency subband coefficients and the energy of high frequency subband coefficients are extracted to be the feature vectors. Finally, it carries the test on CASIA Ver1.0 and MMU iris databases with SVMs and Hamming distances. Compared with the feature extraction method based on the Harr wavelet and discrete cosine transform, the proposed method can achieve better performance.
［1］Daugman J G. New Methods in Iris Recognition ［ J ］. IEEE Trans on Systems, Man, and CyberneticsPart B: Cybernetics, 2007, 37(5):11671175.
［2］Daugman J G. How Iris Recognition Works［J］. IEEE Trans on Circuits and System for Video Technology, 2004,14(1):2130.
［3］Donald M M,Rakshit S,Zhang Dexin. DCTBased Iris Recognition［J］. IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29 (4):586595.
［4］Boles W，Boashash B. A Human Identification Technique Using Images of the Iris and Wavelet Transform ［J］. IEEE Trans on Signal Processing，1998，46(4)：11851188.
［5］Ma L,Tan T N, Wang Y H. Local Intensity Variation Analysis for Iris Recognition ［J］. Pattern Recognition, 2004,37(6):12871298.
［6］王蕴红,朱勇, 谭铁牛. 基于虹膜识别的身份鉴别［J］.自动化学报,2002, 28(1):110.
［7］Dorairaj V, Schmid N A, Fahmy G. Performance Evaluation of Iris Based Recognition System Implementing PCA and ICA Encoding Techniques［C］∥ Proc of SPIE on Biometric Technology for Human Identification III, 2005:5158.
［8］Huang Y P, Luo S W, Chen Y E. An Efficient Iris Recognition System［C］∥Proc of the 1st Int’l Conf on Machine Learning and Cybernetics, 2002:450454.
［9 ］Wildes R P,Asmuth J C,Green G L,et al. A MachineVision System for Iris Recognition［J］. Machine Vision and Applications,1996,9(1):18.
［10］DoM N,Vetterli M. The Contourlet Transform: An Efficient Directional Multiresolution Image Representation ［J］. IEEE Trans on Image Processing, 2005,14(12):20912106.
［11］罗忠亮,林土胜. 用于身份鉴别的虹膜图像预处理［J］. 华南理工大学学报(自然科学版), 2009,37(5):4348.
［12］Arivazhagan S, Ganesan L, Subash Kumar T G.Texture Classification Using Curvelet Statistical and Cooccurrence Features［C］∥Proc of the 18th Int’l Conf on Pattern Recognition, 2006:938941.
［13］黄传波,邵 杰,万鸣华,金忠. Contourlet 变换在图像检索中的应用［J］.计算机工程与应用,2009, 45(3):2427.
［14］中国科学院自动化研究所.CASIA 虹膜图像库(Ver1.0) ［DB/OL］.［20080526］.http://www.cbsr.ia.ac.cn/IrisDatabase/ irislogin.html.
［15］Multimedia University. MMU Iris Image Database［DB /OL］. ［ 20080312 ］. http://pesona.mmu.edu.my/~ccteo/.
/
| 〈 |
|
〉 |