基于小波变换和奇异值分解的虹膜识别算法研究
|
摘要
随着信息技术的飞速发展,信息安全已成为当今重要的研究课题之一。目前,传统的安全技术已经不能满足当前的要求,于是人们把目光转向生物识别领域。虹膜识别是一种新兴的生物识别技术,由于其具有唯一性、稳定性、可采集性、非侵犯性等优点而逐步受到人们的重视。虹膜由于其特殊结构,与脸像、指纹、掌纹、声音等生物身份鉴别方法相比,具有更高的准确性。近些年来虹膜识别技术在研究和应用方面都得到了长足的发展,并表现出了广阔的前景和市场。
本文讨论了一种新的基于小波变换和奇异值分解相结合的虹膜识别算法。首先,针对已有虹膜定位算法耗时较长和准确率不高等问题,提出一种新的虹膜定位算法:对于虹膜内边界,根据虹膜灰度分布特点,利用灰度平均值法找到瞳孔内初始定位点,并通过边缘检测模板来搜索瞳孔的边界点,同时,引入C-均值动态聚类分析法提高定位精度;对于虹膜外边界,采用由粗到精两步定位的方法。在粗定位确定的虹膜大致范围内,并由虹膜特性分析,采用改进型Daugman微积分算子进行精定位,使用改进的一维参数空间搜索,避免了以往算法在搜索边界时的反复迭代,在保证精确度的前提下,大大提高了定位速度。
其次,提出了一种新的基于小波变换和奇异值分解的虹膜纹理特征提取方法。虹膜纹理分布内侧纹理比较密集,外侧纹理较稀疏。根据虹膜纹理分布的特征,将内半圆虹膜图像分成8个图像子块,对每个子块进行三层Bior1.5小波变换提取其中的5个子带并对每个子带奇异值分解降维融合构成最终的虹膜特征向量。
最后,在虹膜特征匹配上,给出了改进的加权自适应最小平均距离匹配准则。以CASIA标准虹膜库中的每幅图像作为测试样本,以库中各类聚类特征向量作为该类的特征进行匹配。
本文在CASIA虹膜数据库上进行了测试实验,实验结果表明本文提出的算法可靠有效,在识别速度上和识别准确率上都有所提高,识别准确率达到98.36%。
With the rapid development of information technology, the research on information security has become one of important topics. However, traditional identification technology is inherently insecure and cannot meet current requirement that leads to a massive rise in the interest for biometric personal identification. Iris recognition is an emerging biometric technology. For uniqueness, stability, available collection and noninvasiveness of iris, iris recognition is being more and more regarded by people. Compared with face, fingerprint, palm-print, voice, and other biometric technology, iris recognition has higher precision. In recent years, iris recognition has made progress in technology research and application, and has a wide prospect and market.
A new iris recognition algorithm based on discrete wavelet transform and singular value decomposition is presented in this thesis. Firstly, a new iris localization algorithm is proposed because of the slow speed of localization and inaccurate localization. For inner boundary, initial located point in pupil is gotten by average gray method according to gray distribution. Boundary points of pupil are fixed by the edge detection template, then C-Means dynamic clustering algorithm is brought up to improve precision in localization. For outer boundary, the method combining rude localization with accurate localization is adopted . In the range of rude localization and in light of characteristic analysis of iris, improved Daugman operator is applied for accurate localization in one dimension space. The localization algorithm not only avoids repeated iteration under precision condition but also greatly fastens the speed of localization.
Secondly, a method based on discrete wavelet transform and singular value decomposition is discussed to extract iris’s feature. After divided iris into eight small blocks according to its texture distribution, each small block is processed with bior1.5 wavelet transform and 5 strips are extracted.Then singular value decomposition is applied to each strip and the final feature vector is gained.
Finally, an improved weighted adaptive criterion of minimum average distance.is raised in feature matching of iris. Each image is chose as testing image and clustering feature vectors in the CASIA iris database is provided for matching by criterion mentioned above.
The results of testing experiments indicate that the algorithm is reliable, efficient. The presented iris recognition algorithm is improved both in speed and accuracy, and performs with good recognition rate of 98.36% on the images of CASIA iris database.
本文讨论了一种新的基于小波变换和奇异值分解相结合的虹膜识别算法。首先,针对已有虹膜定位算法耗时较长和准确率不高等问题,提出一种新的虹膜定位算法:对于虹膜内边界,根据虹膜灰度分布特点,利用灰度平均值法找到瞳孔内初始定位点,并通过边缘检测模板来搜索瞳孔的边界点,同时,引入C-均值动态聚类分析法提高定位精度;对于虹膜外边界,采用由粗到精两步定位的方法。在粗定位确定的虹膜大致范围内,并由虹膜特性分析,采用改进型Daugman微积分算子进行精定位,使用改进的一维参数空间搜索,避免了以往算法在搜索边界时的反复迭代,在保证精确度的前提下,大大提高了定位速度。
其次,提出了一种新的基于小波变换和奇异值分解的虹膜纹理特征提取方法。虹膜纹理分布内侧纹理比较密集,外侧纹理较稀疏。根据虹膜纹理分布的特征,将内半圆虹膜图像分成8个图像子块,对每个子块进行三层Bior1.5小波变换提取其中的5个子带并对每个子带奇异值分解降维融合构成最终的虹膜特征向量。
最后,在虹膜特征匹配上,给出了改进的加权自适应最小平均距离匹配准则。以CASIA标准虹膜库中的每幅图像作为测试样本,以库中各类聚类特征向量作为该类的特征进行匹配。
本文在CASIA虹膜数据库上进行了测试实验,实验结果表明本文提出的算法可靠有效,在识别速度上和识别准确率上都有所提高,识别准确率达到98.36%。
With the rapid development of information technology, the research on information security has become one of important topics. However, traditional identification technology is inherently insecure and cannot meet current requirement that leads to a massive rise in the interest for biometric personal identification. Iris recognition is an emerging biometric technology. For uniqueness, stability, available collection and noninvasiveness of iris, iris recognition is being more and more regarded by people. Compared with face, fingerprint, palm-print, voice, and other biometric technology, iris recognition has higher precision. In recent years, iris recognition has made progress in technology research and application, and has a wide prospect and market.
A new iris recognition algorithm based on discrete wavelet transform and singular value decomposition is presented in this thesis. Firstly, a new iris localization algorithm is proposed because of the slow speed of localization and inaccurate localization. For inner boundary, initial located point in pupil is gotten by average gray method according to gray distribution. Boundary points of pupil are fixed by the edge detection template, then C-Means dynamic clustering algorithm is brought up to improve precision in localization. For outer boundary, the method combining rude localization with accurate localization is adopted . In the range of rude localization and in light of characteristic analysis of iris, improved Daugman operator is applied for accurate localization in one dimension space. The localization algorithm not only avoids repeated iteration under precision condition but also greatly fastens the speed of localization.
Secondly, a method based on discrete wavelet transform and singular value decomposition is discussed to extract iris’s feature. After divided iris into eight small blocks according to its texture distribution, each small block is processed with bior1.5 wavelet transform and 5 strips are extracted.Then singular value decomposition is applied to each strip and the final feature vector is gained.
Finally, an improved weighted adaptive criterion of minimum average distance.is raised in feature matching of iris. Each image is chose as testing image and clustering feature vectors in the CASIA iris database is provided for matching by criterion mentioned above.
The results of testing experiments indicate that the algorithm is reliable, efficient. The presented iris recognition algorithm is improved both in speed and accuracy, and performs with good recognition rate of 98.36% on the images of CASIA iris database.
引文
[1] DAUGMAN J . Biometric personal identification system based on iris analysis:US Patent,5291560[P].1994.
[2] WILDES R,ASMUTH J C,HANNA K.Automated,noninvasive iris recognition system and method:US Patent,5572596[P].1996.
[3]潘力立.虹膜识别算法的研究及实现[D].成都:电子科技大学,2007:2-4.
[4]徐中宇.虹膜识别算法的研究[D].吉林:吉林大学,2006:1-4.
[5] JAIN A K,LIN H,BOLLE R.On-line fingerprint verification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(4):302-313.
[6] MALTONI D , MAIO D , JAIN A K , ect . Handbook of fingerprint recognition[J].Springer,2003,31-34.
[7] TURK M , PENTLAND A . Eigenfaces for recgnition[J] . Journal of Cognitive Neurosciences,1991,3(1):71-86.
[8] DAUGMAN J . Face and gesture recognition : overview[J] . IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):675-676.
[9] LI S Z,JAIN A K.Handbook of face recognition[M].New York :Springer New York,2004:349-369.
[10] DAUGMAN J.High confidence visual recognition of persons by a test of statistical independence[J] . IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1148-1160.
[11] WILDES R.A system for automated iris recognition[J].Proceedings of the Second IEEE Workshop on Applications of Computer Vision,1994:121-128.
[12] MA L,TAN T,WANG Y,etc.Personal recognition based on iris texture analysis[J] . IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(12):1519-1533.
[13] WU Y,HUANG T S.Hand modeling,analysis and recognition[J].IEEE Signal Processing Magazine,2001,18(3):51-60.
[14] YORUK E , KONUKOGLU E , SANKUR B , etc . Shape-based hand recognition[J].IEEE Transactions on Image Processing,2003,15(7):1803-1815.
[15]李云峰,尚振东.基于Gabor小波变换和最佳鉴别特征的掌纹识别[J].计算机工程与应用,2008,44(22):189-191.
[16] WU X Q,ZHANG D,WANG K Q,etc.Palmprint classification using principal lines[J].Pattern Recognition,2004,37:1987-1998.
[17] SHEIKHZADEH H,DENGENG L.Waveform-based speech recognition using hidden filter models:parameter selection and sensitivity to power normalization[J].IEEE Transactions on Speech and Audio Processing,2004,2(1):80-89.
[18] JI M,HAZEN T J,GALASS J R,ect.Robust Speaker Recognition in Noisy Conditions[J] Audio,IEEE Transactions on Speech,and Language Processing,2007,15(5):1711-1723.
[19]明星.虹膜识别技术中的小波变换的应用原理与方法[M],吉林:吉林大学,2006:1-3.
[20] FLOM L , SAFIR A . Iris recognition system : US Patent ,4641349[P].1987.
[21] JOHNSON R G.Can iris patterns be used to identify people?[R].Chemical and Laser Sciences Division LA-12331-PR : Los Alamos National Laboratory,1991.
[22] WILDES R,ASMUTH J,GREEN G,etc.A machine-vision system for iris recognition[J].Machine Vision and Applications,1996,9:1-8.
[23] Institute of Automation,Chinese Academy of Sciences.CASIA Iris Image Database(ver 1.0)[DB/OL].2004.http://www.sinobio-metrics.com.
[24]张贤达,保铮.非平稳信号分析与处理[M].北京:国防工业出版社,1998:23-35.
[25] MEYER F G,COIFMAN.Adaptive directional image compression with oriented wavelets[C] . Dept. of Math , Yale Univ . Proceedings of International Conference on Image Processing,New Haven,CT,USA,1996:601-604
[26]崔锦泰.小波分析导论[M].程正兴译.西安:西安交通大学出版社,1991:54-63.
[27]飞思科技产品研发中心.小波分析理论与MATLAB7实现[M].北京:电子工业出版社,2005:3-117.
[28]吴琼,李国辉,孙韶杰等.基于小波和奇异值分解的图像复制伪造区域检测[J].小型微型计算机系统,2008,29(4):136-139.
[29]罗小桂,何雁.矩阵奇异值分解在计算技术中的应用[J].计算机与现代化,2006,6:67-68.
[30]罗仁泽,冉瑞生,王汝言.基于奇异值分解的基图像的人脸识别[J].电讯技术,2008,8(2):52-55.
[31]谢永华,陈伏兵,张生亮等.基于分块小波变换与奇异值阈值压缩的人脸特征提取与识别算法[J].计算机应用与软件,2008,25(1):30-33.
[32]李清华.虹膜定位算法研究[D].重庆:重庆大学,2006:5-8.
[33] WILDES R P . Iris recognition : an emerging biometric technology[J].Proceedings of the IEEE,1997,85(9):1348-1363.
[34] BALLARD D H,BROWN C M.Computer Vision[C].Englewood Cliffs:NJ:Prentice-Hall,1982:124-149.
[35] PRATT W K.Digital Image Processing[M].New York:Wiley,1978:263-268.
[36] HOUGH P V C.Method and means for recognizing complex patterns:US Patent,3069654[P],1962.
[37]容观澳.计算机图象处理[M].北京:清华大学出版社,2000:267-268.
[38]苑玮琦,林忠华,徐露.一种基于人眼结构特征的新颖虹膜定位算法[J].光电工程,2007,34(1):112-117.
[39]孙即祥等.现代模式识别[M].长沙:国防科技大学出版社,2002:30-36.
[40]石勇涛,胡钢.一种改进的虹膜定位算法[J].计算机与数字工程,2008,36(1):32-35.
[41]陈颖,陆亨立.一种新的虹膜定位算法[J].上海大学学报(自然科学版),2007,13(2):148-150.
[42]郭巧丽.基于虹膜识别的身份鉴别技术的研究与应用[D].大连:大连海事大学,2007:44-50.
[43]王森,杨克俭.基于双线性插值的图像缩放算法[J].图形图像处理,2008,10:53-55.
[44]徐小明.图像的特征提取与描述的研究[D].重庆:重庆大学,2007:18-22.
[45]龚声蓉,刘纯平,王强等.数字图像处理与分析[M],北京:清华大学出版社,2006:209-210.
[46]龙云利.虹膜特征提取的方法研究[D].长沙:国防科学技术大学,2005:32-33.
[47]姚静,林锦国,梅雪.虹膜识别中几种特征提取方法的比较研究[J].计算机测量与控制,2007,15(l):112-116.
[48]甘俊英,张有为.一种基于奇异值特征的神经网络人脸识别新途径[J].电子学报,2004,32(1):170-173.
[49]马伟.虹膜识别系统算法研究[D].南京:南京理工大学,2008:42-44.
[2] WILDES R,ASMUTH J C,HANNA K.Automated,noninvasive iris recognition system and method:US Patent,5572596[P].1996.
[3]潘力立.虹膜识别算法的研究及实现[D].成都:电子科技大学,2007:2-4.
[4]徐中宇.虹膜识别算法的研究[D].吉林:吉林大学,2006:1-4.
[5] JAIN A K,LIN H,BOLLE R.On-line fingerprint verification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(4):302-313.
[6] MALTONI D , MAIO D , JAIN A K , ect . Handbook of fingerprint recognition[J].Springer,2003,31-34.
[7] TURK M , PENTLAND A . Eigenfaces for recgnition[J] . Journal of Cognitive Neurosciences,1991,3(1):71-86.
[8] DAUGMAN J . Face and gesture recognition : overview[J] . IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):675-676.
[9] LI S Z,JAIN A K.Handbook of face recognition[M].New York :Springer New York,2004:349-369.
[10] DAUGMAN J.High confidence visual recognition of persons by a test of statistical independence[J] . IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1148-1160.
[11] WILDES R.A system for automated iris recognition[J].Proceedings of the Second IEEE Workshop on Applications of Computer Vision,1994:121-128.
[12] MA L,TAN T,WANG Y,etc.Personal recognition based on iris texture analysis[J] . IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(12):1519-1533.
[13] WU Y,HUANG T S.Hand modeling,analysis and recognition[J].IEEE Signal Processing Magazine,2001,18(3):51-60.
[14] YORUK E , KONUKOGLU E , SANKUR B , etc . Shape-based hand recognition[J].IEEE Transactions on Image Processing,2003,15(7):1803-1815.
[15]李云峰,尚振东.基于Gabor小波变换和最佳鉴别特征的掌纹识别[J].计算机工程与应用,2008,44(22):189-191.
[16] WU X Q,ZHANG D,WANG K Q,etc.Palmprint classification using principal lines[J].Pattern Recognition,2004,37:1987-1998.
[17] SHEIKHZADEH H,DENGENG L.Waveform-based speech recognition using hidden filter models:parameter selection and sensitivity to power normalization[J].IEEE Transactions on Speech and Audio Processing,2004,2(1):80-89.
[18] JI M,HAZEN T J,GALASS J R,ect.Robust Speaker Recognition in Noisy Conditions[J] Audio,IEEE Transactions on Speech,and Language Processing,2007,15(5):1711-1723.
[19]明星.虹膜识别技术中的小波变换的应用原理与方法[M],吉林:吉林大学,2006:1-3.
[20] FLOM L , SAFIR A . Iris recognition system : US Patent ,4641349[P].1987.
[21] JOHNSON R G.Can iris patterns be used to identify people?[R].Chemical and Laser Sciences Division LA-12331-PR : Los Alamos National Laboratory,1991.
[22] WILDES R,ASMUTH J,GREEN G,etc.A machine-vision system for iris recognition[J].Machine Vision and Applications,1996,9:1-8.
[23] Institute of Automation,Chinese Academy of Sciences.CASIA Iris Image Database(ver 1.0)[DB/OL].2004.http://www.sinobio-metrics.com.
[24]张贤达,保铮.非平稳信号分析与处理[M].北京:国防工业出版社,1998:23-35.
[25] MEYER F G,COIFMAN.Adaptive directional image compression with oriented wavelets[C] . Dept. of Math , Yale Univ . Proceedings of International Conference on Image Processing,New Haven,CT,USA,1996:601-604
[26]崔锦泰.小波分析导论[M].程正兴译.西安:西安交通大学出版社,1991:54-63.
[27]飞思科技产品研发中心.小波分析理论与MATLAB7实现[M].北京:电子工业出版社,2005:3-117.
[28]吴琼,李国辉,孙韶杰等.基于小波和奇异值分解的图像复制伪造区域检测[J].小型微型计算机系统,2008,29(4):136-139.
[29]罗小桂,何雁.矩阵奇异值分解在计算技术中的应用[J].计算机与现代化,2006,6:67-68.
[30]罗仁泽,冉瑞生,王汝言.基于奇异值分解的基图像的人脸识别[J].电讯技术,2008,8(2):52-55.
[31]谢永华,陈伏兵,张生亮等.基于分块小波变换与奇异值阈值压缩的人脸特征提取与识别算法[J].计算机应用与软件,2008,25(1):30-33.
[32]李清华.虹膜定位算法研究[D].重庆:重庆大学,2006:5-8.
[33] WILDES R P . Iris recognition : an emerging biometric technology[J].Proceedings of the IEEE,1997,85(9):1348-1363.
[34] BALLARD D H,BROWN C M.Computer Vision[C].Englewood Cliffs:NJ:Prentice-Hall,1982:124-149.
[35] PRATT W K.Digital Image Processing[M].New York:Wiley,1978:263-268.
[36] HOUGH P V C.Method and means for recognizing complex patterns:US Patent,3069654[P],1962.
[37]容观澳.计算机图象处理[M].北京:清华大学出版社,2000:267-268.
[38]苑玮琦,林忠华,徐露.一种基于人眼结构特征的新颖虹膜定位算法[J].光电工程,2007,34(1):112-117.
[39]孙即祥等.现代模式识别[M].长沙:国防科技大学出版社,2002:30-36.
[40]石勇涛,胡钢.一种改进的虹膜定位算法[J].计算机与数字工程,2008,36(1):32-35.
[41]陈颖,陆亨立.一种新的虹膜定位算法[J].上海大学学报(自然科学版),2007,13(2):148-150.
[42]郭巧丽.基于虹膜识别的身份鉴别技术的研究与应用[D].大连:大连海事大学,2007:44-50.
[43]王森,杨克俭.基于双线性插值的图像缩放算法[J].图形图像处理,2008,10:53-55.
[44]徐小明.图像的特征提取与描述的研究[D].重庆:重庆大学,2007:18-22.
[45]龚声蓉,刘纯平,王强等.数字图像处理与分析[M],北京:清华大学出版社,2006:209-210.
[46]龙云利.虹膜特征提取的方法研究[D].长沙:国防科学技术大学,2005:32-33.
[47]姚静,林锦国,梅雪.虹膜识别中几种特征提取方法的比较研究[J].计算机测量与控制,2007,15(l):112-116.
[48]甘俊英,张有为.一种基于奇异值特征的神经网络人脸识别新途径[J].电子学报,2004,32(1):170-173.
[49]马伟.虹膜识别系统算法研究[D].南京:南京理工大学,2008:42-44.