虹膜识别特征提取技术关键算法分析研究
|
摘要
随着互联网技术的高速发展,身份认证技术得到了广泛的应用,传统的密码认证技术已经不满足当今社会的要求,生物特征识别技术应运而生。虹膜识别技术以其独特的生物识别优越性成为信息安全领域的研究热点,虹膜识别的研究涉及到计算机视觉、数字图像处理、模式识别等众多学科领域。本文针对虹膜识别中的特征提取技术及相关算法进行重点研究。
通过对传统滤波器算法的分析研究,由于虹膜纹理的固有复杂度及滤波器的构造缺陷,会导致滤波器的构造不能被普遍适用。针对滤波器存在的问题,本文在2D Log-Gabor滤波器的基础上提出了一种二维奇对称Log-Gabor滤波器改进算法。首先将2DLog-Gabor滤波器进行坐标系转换,屏蔽了角度方向带宽过大的影响,其次对滤波器进行奇对称变换,提高有效特征提取率,最后对提取出的系数矩阵进行特征融合,从而减少冗余特征数量。该算法通过对虹膜纹理的相位和幅度信息在不同频率和方向进行分析,采用结构化纹理分析找出空间域中虹膜纹理的灰度分布规律,采用特征融合技术减少海明距离总编码长度,提高有效编码率,有效地解决了传统滤波器存在的问题。
通过实验对改进算法进行验证,并设计实现了虹膜识别系统。实验结果表明,本算法对噪声和干扰具有较强的鲁棒性,能有效提高虹膜识别率,具有较高的理论和实用价值。
With the rapid development of Internet technology, Identity Authentication technology has been widely used, the traditional password authentication technology have can't been adapted the requirement of security today. Biometric identification technology came into being. Iris identity authentication technology has been wildly researched in security fields by its unique advantages. Iris recognition research related to multidisciplinary, such as computer vision, digital image processing, pattern recognition and many other subject fields. So iris recognition have great mean in researching. Feature extraction is mainly researched in this paper.
Researched by the traditional wavelet filter algorithms, because of the inherent complexity of iris texture and the filter construct defects, not all filters can be used in every condition. Aiming at the defects of traditional filters, an improved algorithm which is odd symmetry 2D Log-Gabor filter is proposed in this article, the algorithm is based on 2D Log-Gabor filter. Firstly, transform the coordinate of original filter; it shielded the influence that the angle direction of bandwidth is always overflowing. Secondly, extract odd symmetry filter from the transformed filter, the effective rate of feature extraction are raised by the process. Finally, in order to reduce the number of redundant features, the extracted feature coefficient matrix is fused. The algorithm analyzed the phase position and amplitude of iris texture in different frequency and directions; the iris spatial grayscale distribution can be found by structured texture analysis, and take feature fusion to reduce the length of Hamming distance, enhance coding rate and solve the problem of traditional filters effectively.
By taking experiments, the improving algorithm is verified; and iris recognition system is designed and finished. The experimental result shows that the odd symmetry 2D Log-Gabor filters have strong robustness with noise and interferences. This algorithm has a high value of theoretical and practical.
通过对传统滤波器算法的分析研究,由于虹膜纹理的固有复杂度及滤波器的构造缺陷,会导致滤波器的构造不能被普遍适用。针对滤波器存在的问题,本文在2D Log-Gabor滤波器的基础上提出了一种二维奇对称Log-Gabor滤波器改进算法。首先将2DLog-Gabor滤波器进行坐标系转换,屏蔽了角度方向带宽过大的影响,其次对滤波器进行奇对称变换,提高有效特征提取率,最后对提取出的系数矩阵进行特征融合,从而减少冗余特征数量。该算法通过对虹膜纹理的相位和幅度信息在不同频率和方向进行分析,采用结构化纹理分析找出空间域中虹膜纹理的灰度分布规律,采用特征融合技术减少海明距离总编码长度,提高有效编码率,有效地解决了传统滤波器存在的问题。
通过实验对改进算法进行验证,并设计实现了虹膜识别系统。实验结果表明,本算法对噪声和干扰具有较强的鲁棒性,能有效提高虹膜识别率,具有较高的理论和实用价值。
With the rapid development of Internet technology, Identity Authentication technology has been widely used, the traditional password authentication technology have can't been adapted the requirement of security today. Biometric identification technology came into being. Iris identity authentication technology has been wildly researched in security fields by its unique advantages. Iris recognition research related to multidisciplinary, such as computer vision, digital image processing, pattern recognition and many other subject fields. So iris recognition have great mean in researching. Feature extraction is mainly researched in this paper.
Researched by the traditional wavelet filter algorithms, because of the inherent complexity of iris texture and the filter construct defects, not all filters can be used in every condition. Aiming at the defects of traditional filters, an improved algorithm which is odd symmetry 2D Log-Gabor filter is proposed in this article, the algorithm is based on 2D Log-Gabor filter. Firstly, transform the coordinate of original filter; it shielded the influence that the angle direction of bandwidth is always overflowing. Secondly, extract odd symmetry filter from the transformed filter, the effective rate of feature extraction are raised by the process. Finally, in order to reduce the number of redundant features, the extracted feature coefficient matrix is fused. The algorithm analyzed the phase position and amplitude of iris texture in different frequency and directions; the iris spatial grayscale distribution can be found by structured texture analysis, and take feature fusion to reduce the length of Hamming distance, enhance coding rate and solve the problem of traditional filters effectively.
By taking experiments, the improving algorithm is verified; and iris recognition system is designed and finished. The experimental result shows that the odd symmetry 2D Log-Gabor filters have strong robustness with noise and interferences. This algorithm has a high value of theoretical and practical.
引文
[1]孙冬梅,裘正定.生物特征识别技术综述[J].电子学报,2001,29(12)：1744-1748.
[2]罗菜.生物识别技术的发展展望[J].重庆工商大学学报(自然科学版),2005,22(3)：249-252.
[3]景英娟,董育宁.生物特征识别技术综述[J].桂林电子工业学院学报,2005,25(2)：27-32.
[4]Wildes R P. Iris recognition:An Emerging Biometric Technology[J]. Processing of the IEEE,1997:185.
[5]W W Boles. A Security System Based on Human Iris Identification Using Wavelet Transform[J], Engineering Application of Artificial Intelligence,1998,11:77-85.
[6]刘冀,王向军.虹膜识别技术及应用[J].光学技术,2002,28(5)：459-461.
[7]Jain A K, Bolle R and Pankanti S. Biometrics Personal Identification in Networked Society[J]. Kluwer Academic Publishers,1999,22(4):366-370.
[8]浦昭邦,杨帆,陈炳义,陈世哲.虹膜识别技术的发展与应用[J].光学精密工程,2004,12(3)：316-322.
[9]Clarke R. Human Identification in Information System:Management Challenges and Public Policy Issues[J]. Information Technology& People,1994,7(4):6-37.
[10]A.K. Jain, R.Bolle, S.Pankanti, et al. Bioethics:Personal Identification in Networked Society[M]. Kluwer Academic Publishers,1999:32.
[11]黄峥.漫谈虹膜识别系统[J].电视技术,2003,249(3)：88-89.
[12]Mann I. The Development of the Human Eye [M]. New York:Grune and Stratton,1950:63.
[13]王森.虹膜生物识别软件系统框架设计[D].吉林大学,2005：10.
[14]康浩.虹膜识别系统研究[D].上海交通大学,1999：8.
[15]Daugman J G. Biometrical Personal Identification System Based on Iris Analysis [M]. US:Patent, 1994:32.
[16]Daugman J C. High confidence visual recognition of persons by a test of statistical independence[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1148-1161.
[17]Sanchez Avilaa, Sanchez Reillob. Two Different Approaches for Iris Recognition Using Gabor Filters and Multiscale Zero-Crossing Representation[J]. Pattern Recognition,2004,3(8):231-240.
[18]S Mallat. Zero-Crossings of a Wavelet Transform[J], IEEE Transactions on Information Theory,1991, 137(4):10-30.
[19]Wildes R P. Automated,Non-invasive Iris Recognition System and Method[M]. US:Patent 5572596,1996:153.
[20]吕亦生.虹膜识别综述[D].安防科技,2003：5.
[21]孙哲南,王蕴红.虹膜图像的质量评价[M].生物特征识别与认证,2004：54
[22]Kronfeld P C. The Gross Anatomy and the Embryology of the Eye[J]. The Eye,1986,32(1):1-66.
[23]Flom L and Safir A. Iris Recognition System[M]. US:Patent 4641349,1987.
[24]Adler F H. Physiology of the Eye[M]. Mosby St. Louis:MO.1965.
[25]卢光明,杨文,廖庆敏.基于局部纹理分析的虹膜识别算法[J].计算机应用,2007；27(6)：1001-9081.
[26]Daugman J. High confidence recognition of person by rapid video analysis of iris texture[C].In: European Convention on Security and Detection. Brighton, UK:INSPEC,1995:244-251.
[27]王郑耀.数字图像的边缘检测[D].西安交通大学,2000：5.
[28]Miguel Mulet-Parada,Alison Noble.2D+T acoustic boundary detection in echocardiography [J]. Medical Image Analysis 4(2000),21-30.
[29]阮秋琦.数字图像处理学[D].北京：电子工业出版社,2001：38.
[30]徐涛,刘畅,明星,胡朝晖.基于实数形式Gabor变换的虹膜识别方法[J].吉林大学学报(工学版),2004,34(1)：46-50.
[31]王金涛.虹膜识别及图像处理内核实现研究[D].天津大学博士学位论文,2002.6：32.
[32]田启川.不完美虹膜的定位、分割、特征提取与分类识别[D].西北工业大学,2005.11：16.
[33]苑玮琪,马军防,狄文斌等.基于主动轮廓线的虹膜内边界定位方法[J].红外线与激光工程,2003.32(6)：605-609.
[34]汪林峰.计算机虹膜识别系统的研究[D].浙江大学,2002：42
[35]曹江中,戴青云,何家峰.基于纹理分布和Gabor滤波器的虹膜识别算法[J].计算机工程,2006.32(9)：1000-3428.
[36]孙大瑞,吴乐南.基于Gabor变换的人眼定位[J].电路与系统学报,2001.6(4)：29-32.
[37]应忍冬,徐国治.基于小波变换过零检测的虹膜识别技术.上海交通大学学报,2002.336(3),355-358.
[38]刘辉,黄欢.虹膜识别关键技术研究[J].昆明理工大学学报(理工版),2004,29(4)：121-125.
[39]L Ma, T N Tan. Efficient Iris Recognition by Characterizing Key Local Variations [J]. IEEE Transactions on Image Processing,2004,13(6):739-749.
[40]崔圻.图像处理分析-数学形态学方法及应用[M].北京：科学出版社,2000：32.
[41]姚鹏,叶学义,张文聪,庄镇泉.基于改进的Log-Gabor滤波器的虹膜识别算法[J].计算机辅助设计与图形学学报,2007, 19(5)：64-68.
[42]M.M.Gifford, D. J. McCartney, C. H. Seal. Networked Biometrics System Requirements Based on iris Recognition[J]. BT Technology Journal,1999,17(2):163-169.
[43]徐滔,刘畅,明星等.基于实数形式的Gabor变换虹膜识别方法[J].吉林大学学报.2004：46-51.
[44]Wildes R P. Iris. Recognition:An emerging biometric technology[J]. Proceeding of the IEEE, 1997,85(9):348-363.
[45]Boles W W. A Security System Based on Human Iris Identification Using Wavelet Transform[J]. IEEE, 1997 First International Conference on Knowledge-based Intelligent Electronic Systems.1997:533-541.
[46]Maki Murakami, Hironobu Takano, Kiyomi Nakamura. Real-Time Iris Recognition by a Rotation Spreading Neural Network[J]. SICE Annual Conference in Fukui,2003,4(6):283-289.
[47]黄惠芳,胡广书.一种基于小波变换的虹膜识别方法[J].清华大学学报.2003,43(9),1210-1213.
[48]Sylvain Fischer,Laurent Perrinet. Self-Invertible 2D Log-Gabor Wavelets[J]. International Journal of Computer Vision,2007;75(2):231-246.
[49]叶文东,肖刚.基于二维Log-Gabor变换的虹膜识别方法研究[D].浙江大学,2005：38.
[50]顾小风,王东华.基于小波变换的虹膜识别算法的设计与实现[D].西安电子科技大学,2007：22.
[51]Boles W W, Boashah B. A human identification technique using image of the iris and wavelet transform [J]. IEEE Trans. On Signal Processing,1998,46(4):1185-1188.
[52]Xose R.Fdez-Vidal, J.A.Garcia, J.Fdez-Valdivia. Aperceptual measure to predict the visual distinction between two color images[J]. Pattern Recognition Letters,1998,19:1137-1152.
[53]黄雅平,罗四维,陈恩义.基于独立分量分析的虹膜识别方法[J].计算机研究与发展,2003,40(10),1451-1457.
[54]康浩,徐治国.虹膜纹理的相位编码[J].上海交通大学学报,1999,33(5)：542-544.
[55]Lim S,Lee K,Byeon O. Efficient iris recognition through improvement of feature and classifier[J]. ETRI Journal 2001,23(2):61-70.
[56]Wildes R P, Jane C Asmuth, Gilbert L Green, et al. A machine-vision system for iris recognition[J]. Machine Vision and Applications,1996,9:1-10.
[57]石勇涛,覃颖.基于卷缩轮编码的虹膜识别[J].计算机与数字工程.2007,35(3)：119-121.
[58]王成儒,胡正平.基于几何特征的虹膜定位算法[J].中国图象图形学报2003,8(6)：683-685.
[59]古红英,庄越挺,吴飞,潘云鹤.基于纹理特征融合约减和非对称支持向量机的虹膜识别研究[J].计算机研究发展,2005,16(8)：422-428.
[60]Zhitao Xiao, Zhengxin Hou. Phase based feature detector consistent with human visual system characteristics[J]. Pattern Recognition Letters.2004,20(6):213-221.
[61]L Flom. A Safir Iris recognition system[M]. U S. Patent 46413491.1987,30.
[62]何家峰,叶虎年,叶妙元.虹膜图像质量评价的研究[J].中国图像学报,2003,BA(4)：387-391.
[63]高贵鹏.虹膜识别算法研究[D].哈尔滨：哈尔滨工程大学,2005：10.
[2]罗菜.生物识别技术的发展展望[J].重庆工商大学学报(自然科学版),2005,22(3)：249-252.
[3]景英娟,董育宁.生物特征识别技术综述[J].桂林电子工业学院学报,2005,25(2)：27-32.
[4]Wildes R P. Iris recognition:An Emerging Biometric Technology[J]. Processing of the IEEE,1997:185.
[5]W W Boles. A Security System Based on Human Iris Identification Using Wavelet Transform[J], Engineering Application of Artificial Intelligence,1998,11:77-85.
[6]刘冀,王向军.虹膜识别技术及应用[J].光学技术,2002,28(5)：459-461.
[7]Jain A K, Bolle R and Pankanti S. Biometrics Personal Identification in Networked Society[J]. Kluwer Academic Publishers,1999,22(4):366-370.
[8]浦昭邦,杨帆,陈炳义,陈世哲.虹膜识别技术的发展与应用[J].光学精密工程,2004,12(3)：316-322.
[9]Clarke R. Human Identification in Information System:Management Challenges and Public Policy Issues[J]. Information Technology& People,1994,7(4):6-37.
[10]A.K. Jain, R.Bolle, S.Pankanti, et al. Bioethics:Personal Identification in Networked Society[M]. Kluwer Academic Publishers,1999:32.
[11]黄峥.漫谈虹膜识别系统[J].电视技术,2003,249(3)：88-89.
[12]Mann I. The Development of the Human Eye [M]. New York:Grune and Stratton,1950:63.
[13]王森.虹膜生物识别软件系统框架设计[D].吉林大学,2005：10.
[14]康浩.虹膜识别系统研究[D].上海交通大学,1999：8.
[15]Daugman J G. Biometrical Personal Identification System Based on Iris Analysis [M]. US:Patent, 1994:32.
[16]Daugman J C. High confidence visual recognition of persons by a test of statistical independence[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1148-1161.
[17]Sanchez Avilaa, Sanchez Reillob. Two Different Approaches for Iris Recognition Using Gabor Filters and Multiscale Zero-Crossing Representation[J]. Pattern Recognition,2004,3(8):231-240.
[18]S Mallat. Zero-Crossings of a Wavelet Transform[J], IEEE Transactions on Information Theory,1991, 137(4):10-30.
[19]Wildes R P. Automated,Non-invasive Iris Recognition System and Method[M]. US:Patent 5572596,1996:153.
[20]吕亦生.虹膜识别综述[D].安防科技,2003：5.
[21]孙哲南,王蕴红.虹膜图像的质量评价[M].生物特征识别与认证,2004：54
[22]Kronfeld P C. The Gross Anatomy and the Embryology of the Eye[J]. The Eye,1986,32(1):1-66.
[23]Flom L and Safir A. Iris Recognition System[M]. US:Patent 4641349,1987.
[24]Adler F H. Physiology of the Eye[M]. Mosby St. Louis:MO.1965.
[25]卢光明,杨文,廖庆敏.基于局部纹理分析的虹膜识别算法[J].计算机应用,2007；27(6)：1001-9081.
[26]Daugman J. High confidence recognition of person by rapid video analysis of iris texture[C].In: European Convention on Security and Detection. Brighton, UK:INSPEC,1995:244-251.
[27]王郑耀.数字图像的边缘检测[D].西安交通大学,2000：5.
[28]Miguel Mulet-Parada,Alison Noble.2D+T acoustic boundary detection in echocardiography [J]. Medical Image Analysis 4(2000),21-30.
[29]阮秋琦.数字图像处理学[D].北京：电子工业出版社,2001：38.
[30]徐涛,刘畅,明星,胡朝晖.基于实数形式Gabor变换的虹膜识别方法[J].吉林大学学报(工学版),2004,34(1)：46-50.
[31]王金涛.虹膜识别及图像处理内核实现研究[D].天津大学博士学位论文,2002.6：32.
[32]田启川.不完美虹膜的定位、分割、特征提取与分类识别[D].西北工业大学,2005.11：16.
[33]苑玮琪,马军防,狄文斌等.基于主动轮廓线的虹膜内边界定位方法[J].红外线与激光工程,2003.32(6)：605-609.
[34]汪林峰.计算机虹膜识别系统的研究[D].浙江大学,2002：42
[35]曹江中,戴青云,何家峰.基于纹理分布和Gabor滤波器的虹膜识别算法[J].计算机工程,2006.32(9)：1000-3428.
[36]孙大瑞,吴乐南.基于Gabor变换的人眼定位[J].电路与系统学报,2001.6(4)：29-32.
[37]应忍冬,徐国治.基于小波变换过零检测的虹膜识别技术.上海交通大学学报,2002.336(3),355-358.
[38]刘辉,黄欢.虹膜识别关键技术研究[J].昆明理工大学学报(理工版),2004,29(4)：121-125.
[39]L Ma, T N Tan. Efficient Iris Recognition by Characterizing Key Local Variations [J]. IEEE Transactions on Image Processing,2004,13(6):739-749.
[40]崔圻.图像处理分析-数学形态学方法及应用[M].北京：科学出版社,2000：32.
[41]姚鹏,叶学义,张文聪,庄镇泉.基于改进的Log-Gabor滤波器的虹膜识别算法[J].计算机辅助设计与图形学学报,2007, 19(5)：64-68.
[42]M.M.Gifford, D. J. McCartney, C. H. Seal. Networked Biometrics System Requirements Based on iris Recognition[J]. BT Technology Journal,1999,17(2):163-169.
[43]徐滔,刘畅,明星等.基于实数形式的Gabor变换虹膜识别方法[J].吉林大学学报.2004：46-51.
[44]Wildes R P. Iris. Recognition:An emerging biometric technology[J]. Proceeding of the IEEE, 1997,85(9):348-363.
[45]Boles W W. A Security System Based on Human Iris Identification Using Wavelet Transform[J]. IEEE, 1997 First International Conference on Knowledge-based Intelligent Electronic Systems.1997:533-541.
[46]Maki Murakami, Hironobu Takano, Kiyomi Nakamura. Real-Time Iris Recognition by a Rotation Spreading Neural Network[J]. SICE Annual Conference in Fukui,2003,4(6):283-289.
[47]黄惠芳,胡广书.一种基于小波变换的虹膜识别方法[J].清华大学学报.2003,43(9),1210-1213.
[48]Sylvain Fischer,Laurent Perrinet. Self-Invertible 2D Log-Gabor Wavelets[J]. International Journal of Computer Vision,2007;75(2):231-246.
[49]叶文东,肖刚.基于二维Log-Gabor变换的虹膜识别方法研究[D].浙江大学,2005：38.
[50]顾小风,王东华.基于小波变换的虹膜识别算法的设计与实现[D].西安电子科技大学,2007：22.
[51]Boles W W, Boashah B. A human identification technique using image of the iris and wavelet transform [J]. IEEE Trans. On Signal Processing,1998,46(4):1185-1188.
[52]Xose R.Fdez-Vidal, J.A.Garcia, J.Fdez-Valdivia. Aperceptual measure to predict the visual distinction between two color images[J]. Pattern Recognition Letters,1998,19:1137-1152.
[53]黄雅平,罗四维,陈恩义.基于独立分量分析的虹膜识别方法[J].计算机研究与发展,2003,40(10),1451-1457.
[54]康浩,徐治国.虹膜纹理的相位编码[J].上海交通大学学报,1999,33(5)：542-544.
[55]Lim S,Lee K,Byeon O. Efficient iris recognition through improvement of feature and classifier[J]. ETRI Journal 2001,23(2):61-70.
[56]Wildes R P, Jane C Asmuth, Gilbert L Green, et al. A machine-vision system for iris recognition[J]. Machine Vision and Applications,1996,9:1-10.
[57]石勇涛,覃颖.基于卷缩轮编码的虹膜识别[J].计算机与数字工程.2007,35(3)：119-121.
[58]王成儒,胡正平.基于几何特征的虹膜定位算法[J].中国图象图形学报2003,8(6)：683-685.
[59]古红英,庄越挺,吴飞,潘云鹤.基于纹理特征融合约减和非对称支持向量机的虹膜识别研究[J].计算机研究发展,2005,16(8)：422-428.
[60]Zhitao Xiao, Zhengxin Hou. Phase based feature detector consistent with human visual system characteristics[J]. Pattern Recognition Letters.2004,20(6):213-221.
[61]L Flom. A Safir Iris recognition system[M]. U S. Patent 46413491.1987,30.
[62]何家峰,叶虎年,叶妙元.虹膜图像质量评价的研究[J].中国图像学报,2003,BA(4)：387-391.
[63]高贵鹏.虹膜识别算法研究[D].哈尔滨：哈尔滨工程大学,2005：10.