自动指纹识别关键算法的研究
|
摘要
随着社会信息化、智能化与自动化的高速发展,传统的身份识别技术已经远远不能满足实际应用中准确性、快速性的需求,取而代之的是基于信息处理技术的现代生物识别技术。其中,指纹识别以其所特有优越性质,已成为应用范围最广的生物识别技术之一。尽管自动指纹识别技术的相关研究已经取得了一定程度的进展,但是由于信息的飞速膨胀,如何准确、快速的识别指纹仍然是一个亟待解决的难题。
自动指纹识别是通过综合图像处理、模式识别、计算智能等多领域知识,自动处理指纹图像中相关的特征信息,来判断指纹身份的生物识别技术。在分析和总结前人研究成果的基础上,本文对指纹识别过程中的图像增强、特征匹配进行了深入细致的研究,设计并实现了集成本文研究成果的自动指纹识别系统。
(1)为了尽可能地保留指纹纹理信息的同时减少噪声的影响,借助小波变换的多分辨率分析特征,提出了一种基于小波的指纹图像增强方法。该方法通过小波多尺度分解,将原始图像分为频率不同的子图,然后根据各频率子图信息与噪声含量不同的特性,对低频子图进行方向滤波,对高频子图进行降噪处理,将处理后的小波系数重构得到初步增强的指纹图像,为了进一步突出细节信息,再对指纹图像进行反锐化掩膜后处理。实验结果表明,该方法可以在增强指纹的纹理信息的同时滤除噪声,从而较好的改善了图像的质量。
(2)针对指纹匹配过程中基准点定位不准确与耗时太长问题,提出了一种基于改进基准点定位的指纹匹配算法。该算法借助指纹图像的中心点,构造局部细节结构,并在此结构上利用全等三角形原则求取基准点,然后将所有细节特征转化到极坐标中,利用可变界限盒的方法进行匹配。实验结果表明,该算法所确定的基准点较为准确,而且耗时缩短,有效地提高了识别率与执行效率。
(3)在详细需求分析的基础上,设计并实现了本文的自动指纹识别系统,集成了本文所有研究成果。该系统能够直观地展示用户操作的处理结果,较为方便、实用,为将来的实际应用奠定了基础。
With the rapid development of intelligence and automation, the traditional identification technology can not meet the demand for speed and accuracy more and more, on the contrary, modern biological recognition technology based on the information processing becomes a research hotspot. The automatic fingerprint identification has become one of the most extensive applications of biometrics because of its superior properties. Although the research on automatic fingerprint identification technology has made some progress, how to improve the accuracy and speed is still an urgent problem due to the rapid expansion of information.
Automatic fingerprint identification is to determine the identification of the fingerprint by automatic processing the relevant feature information in fingerprint image through integrated image processing and pattern recognition, computational intelligence and other fields of knowledge. Based on the analyzing and summarizing the results of previous studies, the fingerprint image enhancement and feature matching method have been studied deeply in this paper. The automatic fingerprint identification system (AFIS) has also been designed and implemented, which integrates all of the research.
(1) In order to keep more texture features of fingerprint while denoising, a new fingerprint enhancement method based on wavelet transform and unsharp masking was proposed in this paper according to the multiresolution and local time-frequency analysis of wavelet. First of all, a fingerprint image was decomposed by wavelet, and then some different treatments were made by the characteristics of the different frequency graphs. Finally, the initial enhanced fingerprint image was reconstructed by the wavelet coefficients which had been adjusted before. In addition, for highlighting the details, unsharp masking was used to process the fingerprint image. Experimental results show that this method can filter out the noise while enhance the texture features and thus improve the quality of the images.
(2) Because the location of the fiducial point is inaccuracy and time-consuming in fingerprint matching, a new matching algorithm based on improved fiducial point locating is proposed in this paper. The algorithm constructs a local structure with the help of the core point, and figures out a fiducial point in this structure by using the principle of congruent triangles. And then all the minutiae features are expressed in polar coordinates, at last the final decision can be made with a changeable boundary box method. Experiments prove that the location of the fiducial point is more accuracy and the time is saved, thereby the recognition rate and efficiency are enhanced
(3) Based on detailed requirements analysis, Automated Fingerprint Identification System has been designed and implemented, which integrating all the results in this paper. The system can visually display the user’s operating results, more convenient and practical, and create a foundation for the future practical application.
自动指纹识别是通过综合图像处理、模式识别、计算智能等多领域知识,自动处理指纹图像中相关的特征信息,来判断指纹身份的生物识别技术。在分析和总结前人研究成果的基础上,本文对指纹识别过程中的图像增强、特征匹配进行了深入细致的研究,设计并实现了集成本文研究成果的自动指纹识别系统。
(1)为了尽可能地保留指纹纹理信息的同时减少噪声的影响,借助小波变换的多分辨率分析特征,提出了一种基于小波的指纹图像增强方法。该方法通过小波多尺度分解,将原始图像分为频率不同的子图,然后根据各频率子图信息与噪声含量不同的特性,对低频子图进行方向滤波,对高频子图进行降噪处理,将处理后的小波系数重构得到初步增强的指纹图像,为了进一步突出细节信息,再对指纹图像进行反锐化掩膜后处理。实验结果表明,该方法可以在增强指纹的纹理信息的同时滤除噪声,从而较好的改善了图像的质量。
(2)针对指纹匹配过程中基准点定位不准确与耗时太长问题,提出了一种基于改进基准点定位的指纹匹配算法。该算法借助指纹图像的中心点,构造局部细节结构,并在此结构上利用全等三角形原则求取基准点,然后将所有细节特征转化到极坐标中,利用可变界限盒的方法进行匹配。实验结果表明,该算法所确定的基准点较为准确,而且耗时缩短,有效地提高了识别率与执行效率。
(3)在详细需求分析的基础上,设计并实现了本文的自动指纹识别系统,集成了本文所有研究成果。该系统能够直观地展示用户操作的处理结果,较为方便、实用,为将来的实际应用奠定了基础。
With the rapid development of intelligence and automation, the traditional identification technology can not meet the demand for speed and accuracy more and more, on the contrary, modern biological recognition technology based on the information processing becomes a research hotspot. The automatic fingerprint identification has become one of the most extensive applications of biometrics because of its superior properties. Although the research on automatic fingerprint identification technology has made some progress, how to improve the accuracy and speed is still an urgent problem due to the rapid expansion of information.
Automatic fingerprint identification is to determine the identification of the fingerprint by automatic processing the relevant feature information in fingerprint image through integrated image processing and pattern recognition, computational intelligence and other fields of knowledge. Based on the analyzing and summarizing the results of previous studies, the fingerprint image enhancement and feature matching method have been studied deeply in this paper. The automatic fingerprint identification system (AFIS) has also been designed and implemented, which integrates all of the research.
(1) In order to keep more texture features of fingerprint while denoising, a new fingerprint enhancement method based on wavelet transform and unsharp masking was proposed in this paper according to the multiresolution and local time-frequency analysis of wavelet. First of all, a fingerprint image was decomposed by wavelet, and then some different treatments were made by the characteristics of the different frequency graphs. Finally, the initial enhanced fingerprint image was reconstructed by the wavelet coefficients which had been adjusted before. In addition, for highlighting the details, unsharp masking was used to process the fingerprint image. Experimental results show that this method can filter out the noise while enhance the texture features and thus improve the quality of the images.
(2) Because the location of the fiducial point is inaccuracy and time-consuming in fingerprint matching, a new matching algorithm based on improved fiducial point locating is proposed in this paper. The algorithm constructs a local structure with the help of the core point, and figures out a fiducial point in this structure by using the principle of congruent triangles. And then all the minutiae features are expressed in polar coordinates, at last the final decision can be made with a changeable boundary box method. Experiments prove that the location of the fiducial point is more accuracy and the time is saved, thereby the recognition rate and efficiency are enhanced
(3) Based on detailed requirements analysis, Automated Fingerprint Identification System has been designed and implemented, which integrating all the results in this paper. The system can visually display the user’s operating results, more convenient and practical, and create a foundation for the future practical application.
引文
[1] RAO A R. Taxonomy for Texture Description and Identification [M]. New York:Springer-Verlag, 1990
[2]罗希平,田捷.自动指纹识别中的图像增强和细节匹配算法[J].软件学报, 2002, 13(5):946~956
[3]李利,范九伦.基于Radon变换的指纹图像滤波增强方法[J].中国图象图形学报, 2009, 14(3):417~421
[4] Maio, D., Maltoni, D., Cappelli, R., et al. FVC2000: fingerprint verification competition. http://bias.csr.unibo.it/fvc2000
[5]祝恩,殷建平,张国敏,胡春风.一种基于机器学习的指纹纹路方向计算方法[J].计算机研究与发展, 2007, 44(12):2051~2057
[6]解梅,马争.基于脊向滤波算法[J].电子学报, 2004, 32(1):5~7
[7]徐晓明.指纹图像的预处理及特征提取,硕士学位论文,大连理工大学, 2008年6月
[8] Lin Hong, Wan Yifei, Jain A. Fingerprint image enhancement:algorithm and performanceevaluation[J] . IEEE Trans on Pattern Analysis and Machine Intelligence,1998, 20(8):777~789
[9] Hong L, Jain A K, Pankanti S, Bolle R. Fingerprint Enhancement.Proc. IEEE Workshop on Applications of Computer Vision, Sarasota, Fl, 1996, 10:202~207
[10]廖开阳,张学东,章明珠,潘晓红.基于Gabor滤波器的指纹图像快速增强[J].计算机工程与应用, 2009, 45(10):172~175
[11]徐杨,张学东.基于递归Gabor滤波的指纹图像处理方法的研究[J].计算机应用与软件, 2007, 24(12):163~165
[12]陈声登,刘杰.基于圆形滤波器的指纹识别系统[J].信息与电子工程, 2009, 7(2):127~131
[13]白洁,易扬.基于Gabor滤波的指纹图像增强方法[J].可编程控制器与工厂自动化, 2008, (11):77~79
[14]上官卫华,史仪凯,韦艳波,耶亚林.掩膜法与Gabor滤波在指纹增强中的应用[J].计算机仿真, 2009, 26(11):220~223
[15]邵志勇,温春友,田莹.指纹图像二值化方法的比较研究[J].鞍山科技大学学报, 2004, 27(3):186~189
[16]杨鸿雁,刘正光.基于指纹方向图的模糊二值化算法研究[J].计算机应用, 2008, 28(4):999~1000
[17] Otsu N. A threshold selection method from graylevel histograms[J]. IEEE Trans on Systems, Man, and Cybernetics, 1979, 9(1):62~66
[18]吕岳,施鹏飞.一种实用的并行细化算法及其实现[J].计算机工程与设计, 2000, (8):23~26
[19]冯星奎,李林艳,颜祖泉.一种新的指纹图像细化算法[J].中国图像图形学报,1999, 14(10):835~838
[20]王家隆,郭成安.一种改进的图像模板细化算法[J].中国图象图形学报, 2004, 3 (9):297~301
[21]杨凡,赵顺东.一种有效的混合式指纹快速细化算法[J].计算机应用研究, 2008, 25(10):3034~3035
[22]廖开阳,张学东,章明珠.一种新的指纹图像快速细化算法[J].计算机工程与应用, 2008, 44(5):93~95
[23]傅景广,许刚,王裕国.基于二值图像的指纹细节点提取[J].计算机研究与发展, 2004, 41(4):720~727
[24]孟祥萍,任纪川,王贤勇,等.一种有效的指纹细节点提取方法[J].计算机应用, 2005, 25(4):919~920
[25] A.K. Jain, L. Hong, and R. Bolle,“Online Fingerprint Verification,”IEEE Trans. Pattern Analysis and Machine Intelligence, Apr. 1997, 19:302-314
[26] S. Prabhakar, A.K.Jain, Jianguo Wang. Minutia verification and classification for fingerprint matching[C]. Pattern Recognition, 2000. Proceedings. 15th International Conference on, 2000, 1:25-29
[27] A.Ross, A.K.Jain, J.Reisman. Ahybrid fingerprint matcher[J]. Pattern Recognition, 2003, 36(7):1661~1673
[28] D. Skea, Barrodale, R. Kuwahara and R. Pocckert. A control matching algorithm[J].Pattern Recognition, 1993, 26(2):269~276
[29]D. Lavine, B. A. Lambaird and L. N. Kanal. Recognition of spatial point patterns[J]. Pattern Recognition, 1983, 16:289~295
[30]Yilong Yin, Hongwei Zhang, Xiukun Yang. A method based on delaunay triangulation for fingerprint matching. Biometric Technology for Human Identification II, Part of SPIE’S International Symposium on Defense and Security, 2005, 5779:274~281
[31]V.V.Vinod and S.Ghose,“Point matching using asymmetric neural networks”,Pattern Recognition, 1993, 26:1207~1214
[32]谭台哲,宁新宝,尹义龙,等.一种基于指纹中心点的匹配算法[J].南京大学学报(自然科学版), 2003, 39(4):483~489
[33]袁华强,叶阳东,邓见光,等.一种基于基准点的指纹匹配算法[J].计算机工程, 2008, 34(3):241~243
[34]尹义龙,张宏伟,刘宁.基于Delaunay三角化的指纹匹配方法[J].计算机研究与发展, 2005, 42(9):1622~627
[35]穆国燕,陈慧,陈树中.基于小波变换和纹理滤波的指纹图像增强方法[J].计算机工程, 2004, 30(1):150~152
[36]王建英,李临生,田启川.小波变换在指纹图像增强中的应用[J].太原科技大学学报, 2007, 28(6):433~436
[37]田俊,周定康.基于小波变换和Gabor滤波的指纹图像增强算法[J].华东交通大学学报, 2008, 25(4):51~55
[38]冯美仙.基于小波变换的指纹图像增强算法[J].廊坊师范学院学报(自然科学版), 2008, 8(5):5~7
[39] Rafael C. Gonzalez, Richard E. Woods. Digital Image Processing, Second Edition [M]. Beijing:Publishing House of Electronics Industry, 2007, 09
[40]邵志勇,温春友,田莹.指纹图像二值化方法的比较研究[J].鞍山科技大学学报, 2004, 27(3):186~189
[41]张理想,詹小四,张修如.基于信息熵的指纹图像二值化算法[J].计算机系统应用, 2010, 06:148~152
[42]陈桂友.自动指纹识别系统中的关键算法研究及应用,博士学位论文,山东大学,2005年10月
[43]王业琳,宁新宝,尹义龙.指纹图像细化算法的研究[J].南京大学学报:自然科学版, 2003, 39(4):468~475
[44] Kovcs V D.A fingerprint Verification System Based on Triangular Matching and Dynamic Time Warping.IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(11):1266~1276
[45] Tico M, Kuosmanen P. Fingerprint Matching Using an Orientation-based Minutia Descriptor.IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003, 25(8):1009~1014
[46] Queka C, Tana K B, Sagarb V K. Pseudo-outer Product Based Fuzzy Neural Network Fingerprint Verification System. Neural Networks, 2001, 14(3):305~323
[47] Ratha N K, Karu K, Chen S. A Real-time Matching System for Large Fingerprint Databases.IEEE Transaction on Pattern Analysis and Machine Intelligence, 1996, 18(8):799~813
[48] Zhu E, Yin J, Zhang G. Fingerprint Matching Based on Global Alignment of Multiple Reference Minutiae. Pattern Recognition, 2005, 38(10):1685~1694
[49] Jea T Y, Govindaraju V. A Minutia-based Partial Fingerprint Recognition System. Pattern Recognition, 2005, 38(10):1672~1684
[50] Tong X, Huang J, Tang X. Fingerprint Minutiae Matching Using the Adjacent Feature Vector. Pattern Recognition Letters, 2005, 26(9):1337~1345
[51]杨小冬,宁新宝,谭台哲.基于纹线跟踪的指纹细节提取算法[J].计算机应用, 2004, 24(3):75~78
[52]陈开志,胡爱群.基于二值化图像的指纹细节点精确提取方法[J].东南大学学报:自然科学版, 2010, 40(3):471~475
[53]王崇文.自动指纹识别方法研究,博士学位论文,重庆大学, 2002年7月
[54]傅景广,许刚,王裕国.模糊几何和纹理特征在指纹细节点后处理中的应用[J].计算机辅助设计与图形学学报, 2004, 16(4):487~491
[55]王建永,郭成安.一种基于局部结构信息的指纹伪特征滤除算法[J].中国图像图形学报, 2003, 8(12):1467-1475
[56]赵琪.自动指纹识别中若干关键技术的研究,硕士学位论文,中南大学, 2009年6月
[57]廖阔,杨万麟.点模式指纹匹配算法研究与实现[J].电子科技大学学报, 2004, 33(2):154~156
[58] Anil K Jain, Lin Hong, Sharat Pankanti, Ruud Bolle. An identity Fingerprint Recognition Technical Report. California Institute of Technology, 1997
[59]王磊.自动指纹识别系统的算法研究及实现,硕士学位论文,哈尔滨工程大学, 2008年6月
[60] Andrew K Hrechak, James A Mchugh. Automated fingerprint recognition using strctural matching [J]. PattrenRecognition, 1990
[61] B.G. Sherlock, D.M. Monro. A model for interpreting fingerprint topology[J]. Pattern Recognition, 1993, 26(7):1047~1055
[62]项明,吴小培,刘明生.基于独立分量分析的二级指纹分类算法[J].计算机工程, 2010, 36(10):16~18
[63] Stephen J Chapman. MATLAB Programming for Engineers, Second Edition [M]. Thomson-Engineering, 2004, 08:391~450
[64]赵书兰. MATLAB R2008数字图像处理与分析实例教程[M].化学工业出版社, 2009, 06
[65] Alan Dennis, Barbara Haley, Roberta M Roth. Systems Analysis & Desigin [M]. Posts & Telecom Press, 2009, 01:237~243
[2]罗希平,田捷.自动指纹识别中的图像增强和细节匹配算法[J].软件学报, 2002, 13(5):946~956
[3]李利,范九伦.基于Radon变换的指纹图像滤波增强方法[J].中国图象图形学报, 2009, 14(3):417~421
[4] Maio, D., Maltoni, D., Cappelli, R., et al. FVC2000: fingerprint verification competition. http://bias.csr.unibo.it/fvc2000
[5]祝恩,殷建平,张国敏,胡春风.一种基于机器学习的指纹纹路方向计算方法[J].计算机研究与发展, 2007, 44(12):2051~2057
[6]解梅,马争.基于脊向滤波算法[J].电子学报, 2004, 32(1):5~7
[7]徐晓明.指纹图像的预处理及特征提取,硕士学位论文,大连理工大学, 2008年6月
[8] Lin Hong, Wan Yifei, Jain A. Fingerprint image enhancement:algorithm and performanceevaluation[J] . IEEE Trans on Pattern Analysis and Machine Intelligence,1998, 20(8):777~789
[9] Hong L, Jain A K, Pankanti S, Bolle R. Fingerprint Enhancement.Proc. IEEE Workshop on Applications of Computer Vision, Sarasota, Fl, 1996, 10:202~207
[10]廖开阳,张学东,章明珠,潘晓红.基于Gabor滤波器的指纹图像快速增强[J].计算机工程与应用, 2009, 45(10):172~175
[11]徐杨,张学东.基于递归Gabor滤波的指纹图像处理方法的研究[J].计算机应用与软件, 2007, 24(12):163~165
[12]陈声登,刘杰.基于圆形滤波器的指纹识别系统[J].信息与电子工程, 2009, 7(2):127~131
[13]白洁,易扬.基于Gabor滤波的指纹图像增强方法[J].可编程控制器与工厂自动化, 2008, (11):77~79
[14]上官卫华,史仪凯,韦艳波,耶亚林.掩膜法与Gabor滤波在指纹增强中的应用[J].计算机仿真, 2009, 26(11):220~223
[15]邵志勇,温春友,田莹.指纹图像二值化方法的比较研究[J].鞍山科技大学学报, 2004, 27(3):186~189
[16]杨鸿雁,刘正光.基于指纹方向图的模糊二值化算法研究[J].计算机应用, 2008, 28(4):999~1000
[17] Otsu N. A threshold selection method from graylevel histograms[J]. IEEE Trans on Systems, Man, and Cybernetics, 1979, 9(1):62~66
[18]吕岳,施鹏飞.一种实用的并行细化算法及其实现[J].计算机工程与设计, 2000, (8):23~26
[19]冯星奎,李林艳,颜祖泉.一种新的指纹图像细化算法[J].中国图像图形学报,1999, 14(10):835~838
[20]王家隆,郭成安.一种改进的图像模板细化算法[J].中国图象图形学报, 2004, 3 (9):297~301
[21]杨凡,赵顺东.一种有效的混合式指纹快速细化算法[J].计算机应用研究, 2008, 25(10):3034~3035
[22]廖开阳,张学东,章明珠.一种新的指纹图像快速细化算法[J].计算机工程与应用, 2008, 44(5):93~95
[23]傅景广,许刚,王裕国.基于二值图像的指纹细节点提取[J].计算机研究与发展, 2004, 41(4):720~727
[24]孟祥萍,任纪川,王贤勇,等.一种有效的指纹细节点提取方法[J].计算机应用, 2005, 25(4):919~920
[25] A.K. Jain, L. Hong, and R. Bolle,“Online Fingerprint Verification,”IEEE Trans. Pattern Analysis and Machine Intelligence, Apr. 1997, 19:302-314
[26] S. Prabhakar, A.K.Jain, Jianguo Wang. Minutia verification and classification for fingerprint matching[C]. Pattern Recognition, 2000. Proceedings. 15th International Conference on, 2000, 1:25-29
[27] A.Ross, A.K.Jain, J.Reisman. Ahybrid fingerprint matcher[J]. Pattern Recognition, 2003, 36(7):1661~1673
[28] D. Skea, Barrodale, R. Kuwahara and R. Pocckert. A control matching algorithm[J].Pattern Recognition, 1993, 26(2):269~276
[29]D. Lavine, B. A. Lambaird and L. N. Kanal. Recognition of spatial point patterns[J]. Pattern Recognition, 1983, 16:289~295
[30]Yilong Yin, Hongwei Zhang, Xiukun Yang. A method based on delaunay triangulation for fingerprint matching. Biometric Technology for Human Identification II, Part of SPIE’S International Symposium on Defense and Security, 2005, 5779:274~281
[31]V.V.Vinod and S.Ghose,“Point matching using asymmetric neural networks”,Pattern Recognition, 1993, 26:1207~1214
[32]谭台哲,宁新宝,尹义龙,等.一种基于指纹中心点的匹配算法[J].南京大学学报(自然科学版), 2003, 39(4):483~489
[33]袁华强,叶阳东,邓见光,等.一种基于基准点的指纹匹配算法[J].计算机工程, 2008, 34(3):241~243
[34]尹义龙,张宏伟,刘宁.基于Delaunay三角化的指纹匹配方法[J].计算机研究与发展, 2005, 42(9):1622~627
[35]穆国燕,陈慧,陈树中.基于小波变换和纹理滤波的指纹图像增强方法[J].计算机工程, 2004, 30(1):150~152
[36]王建英,李临生,田启川.小波变换在指纹图像增强中的应用[J].太原科技大学学报, 2007, 28(6):433~436
[37]田俊,周定康.基于小波变换和Gabor滤波的指纹图像增强算法[J].华东交通大学学报, 2008, 25(4):51~55
[38]冯美仙.基于小波变换的指纹图像增强算法[J].廊坊师范学院学报(自然科学版), 2008, 8(5):5~7
[39] Rafael C. Gonzalez, Richard E. Woods. Digital Image Processing, Second Edition [M]. Beijing:Publishing House of Electronics Industry, 2007, 09
[40]邵志勇,温春友,田莹.指纹图像二值化方法的比较研究[J].鞍山科技大学学报, 2004, 27(3):186~189
[41]张理想,詹小四,张修如.基于信息熵的指纹图像二值化算法[J].计算机系统应用, 2010, 06:148~152
[42]陈桂友.自动指纹识别系统中的关键算法研究及应用,博士学位论文,山东大学,2005年10月
[43]王业琳,宁新宝,尹义龙.指纹图像细化算法的研究[J].南京大学学报:自然科学版, 2003, 39(4):468~475
[44] Kovcs V D.A fingerprint Verification System Based on Triangular Matching and Dynamic Time Warping.IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(11):1266~1276
[45] Tico M, Kuosmanen P. Fingerprint Matching Using an Orientation-based Minutia Descriptor.IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003, 25(8):1009~1014
[46] Queka C, Tana K B, Sagarb V K. Pseudo-outer Product Based Fuzzy Neural Network Fingerprint Verification System. Neural Networks, 2001, 14(3):305~323
[47] Ratha N K, Karu K, Chen S. A Real-time Matching System for Large Fingerprint Databases.IEEE Transaction on Pattern Analysis and Machine Intelligence, 1996, 18(8):799~813
[48] Zhu E, Yin J, Zhang G. Fingerprint Matching Based on Global Alignment of Multiple Reference Minutiae. Pattern Recognition, 2005, 38(10):1685~1694
[49] Jea T Y, Govindaraju V. A Minutia-based Partial Fingerprint Recognition System. Pattern Recognition, 2005, 38(10):1672~1684
[50] Tong X, Huang J, Tang X. Fingerprint Minutiae Matching Using the Adjacent Feature Vector. Pattern Recognition Letters, 2005, 26(9):1337~1345
[51]杨小冬,宁新宝,谭台哲.基于纹线跟踪的指纹细节提取算法[J].计算机应用, 2004, 24(3):75~78
[52]陈开志,胡爱群.基于二值化图像的指纹细节点精确提取方法[J].东南大学学报:自然科学版, 2010, 40(3):471~475
[53]王崇文.自动指纹识别方法研究,博士学位论文,重庆大学, 2002年7月
[54]傅景广,许刚,王裕国.模糊几何和纹理特征在指纹细节点后处理中的应用[J].计算机辅助设计与图形学学报, 2004, 16(4):487~491
[55]王建永,郭成安.一种基于局部结构信息的指纹伪特征滤除算法[J].中国图像图形学报, 2003, 8(12):1467-1475
[56]赵琪.自动指纹识别中若干关键技术的研究,硕士学位论文,中南大学, 2009年6月
[57]廖阔,杨万麟.点模式指纹匹配算法研究与实现[J].电子科技大学学报, 2004, 33(2):154~156
[58] Anil K Jain, Lin Hong, Sharat Pankanti, Ruud Bolle. An identity Fingerprint Recognition Technical Report. California Institute of Technology, 1997
[59]王磊.自动指纹识别系统的算法研究及实现,硕士学位论文,哈尔滨工程大学, 2008年6月
[60] Andrew K Hrechak, James A Mchugh. Automated fingerprint recognition using strctural matching [J]. PattrenRecognition, 1990
[61] B.G. Sherlock, D.M. Monro. A model for interpreting fingerprint topology[J]. Pattern Recognition, 1993, 26(7):1047~1055
[62]项明,吴小培,刘明生.基于独立分量分析的二级指纹分类算法[J].计算机工程, 2010, 36(10):16~18
[63] Stephen J Chapman. MATLAB Programming for Engineers, Second Edition [M]. Thomson-Engineering, 2004, 08:391~450
[64]赵书兰. MATLAB R2008数字图像处理与分析实例教程[M].化学工业出版社, 2009, 06
[65] Alan Dennis, Barbara Haley, Roberta M Roth. Systems Analysis & Desigin [M]. Posts & Telecom Press, 2009, 01:237~243