指纹识别相关算法的改进研究
|
摘要
人类应用指纹的历史开始于远古。指纹是最古老的身份证,早在6000年前人类就会利用指纹来代替签名。考古学家证实,早在原始社会晚期,指纹作为身份鉴别的工具已经在我国开始应用。尽管指纹在我国古代应用广泛,但这种应用仅是一种感性应用,没有在此基础上进行分析综合和归纳推理,更没上升到科学及理论应用。随着社会发展和科学技术的进步,人们对指纹模式识别系统的研究越来越深入,并取得了巨大的进展。比如在很多企业和学校引入了指纹考勤系统,但是目前的考勤系统在识别速度和准确性上仍然存在一些问题,因此就要求我们对指纹模式识别算法做更进一步的研究。
本文在通过对国内外有关指纹识别技术研究成果的学习基础上,对指纹模式识别系统算法进行了研究。主要包括:指纹图像预处理、指纹图像特征点提取和指纹模式特征匹配。
论文详细地分析了国内外指纹模式识别技术的发展状况,在总结和学习前人的理论基础上,以提高指纹模式识别算法处理速度和性能作为主要研究目标,重点对指纹二值化算法及指纹模式特征匹配算法进行了深入的研究。首先,针对目前二值化算法存在的抗燥能力差、阈值不易选取等问题以及效率低的不足,提出了一种新的二值化灰度阈值分割法,该算法很好地体现了易实现和计算量小的特点,且把局部自适应和指纹灰度图像信息相结合,同时也起到了一定的抗干扰能力。接着针对指纹模式特征匹配,提出了一种新的基于遗传算法的二次匹配算法,其中的细节特征点初筛部分,提出了一种新的构建与变换无关的结构信息的方法;坐标校准部分,采用极坐标法;对于校准后得到的特征点,采用可变大小的限界盒方法,提高了算法效率。最后采用FVC2004指纹库中的指纹图像,通过与经典指纹模式特征匹配算法的结果比较分析,验证了本文算法的可行性。
Application of the fingerprint of human history began in the ancient. Fingerprint identification is the oldest, as early as 6000 years ago, will use fingerprints to replace the human signature. Archaeologists confirmed that, as early as the late primitive society, the fingerprint as identification tool has been applied in China.While fingerprints are widely used in ancient China, but this application is only an emotional application, not on the basis of this synthesis and inductive reasoning and did not rise to the science and application of theory. With the social development and scientific and technological progress, the people of fingerprint pattern recognition system, more and more in-depth research, and have made tremendous progress. Many enterprises and schools such as the introduction of the fingerprint attendance system, but the current time and attendance system in recognition speed and accuracy are still some problems, and therefore requires us to fingerprint pattern recognition algorithms to do further study.
In this paper, research on fingerprint recognition technology in learning rough home and abroad, is studied based on the fingerprint pattern recognition system algorithm. Mainly contains: fingerprint image preprocessing、fingerprint feature extraction and fingerprint matching.
In the thesis the development of fingerprint pattern recognition at home and abroad was summarized in detail, fingerprint binarization algorithm and fingerprint pattern character matching algorithm were further investigated based on previous theory in order to improve the processing speed and performance of fingerprint pattern recognition algorithm. Firstly, as binary algorithm had poor anti-noise properties and difficulties in selecting suitable threshold value, a new binarized gray threshold segmentation method, which combined local adaptive and fingerprints grayscale image information and had and the characteristics of less calculation and preferable antijamming, was come up. Then based on genetic algorithm a new re-matching algorithm, of which the detail screening part was figured out by a new mothod of building irrelevant transform structure information and the coordinates calibration part was settled by polar coordinates, was put forward. Then an adjustable Bounding Box is used to process the calibrated feature points. Finally, it was proved by comparing the finger images in the FVC2004 fingerprints database with the images obtained by classic finger print pattern matching algorithm that this algorithm was feasible.
本文在通过对国内外有关指纹识别技术研究成果的学习基础上,对指纹模式识别系统算法进行了研究。主要包括:指纹图像预处理、指纹图像特征点提取和指纹模式特征匹配。
论文详细地分析了国内外指纹模式识别技术的发展状况,在总结和学习前人的理论基础上,以提高指纹模式识别算法处理速度和性能作为主要研究目标,重点对指纹二值化算法及指纹模式特征匹配算法进行了深入的研究。首先,针对目前二值化算法存在的抗燥能力差、阈值不易选取等问题以及效率低的不足,提出了一种新的二值化灰度阈值分割法,该算法很好地体现了易实现和计算量小的特点,且把局部自适应和指纹灰度图像信息相结合,同时也起到了一定的抗干扰能力。接着针对指纹模式特征匹配,提出了一种新的基于遗传算法的二次匹配算法,其中的细节特征点初筛部分,提出了一种新的构建与变换无关的结构信息的方法;坐标校准部分,采用极坐标法;对于校准后得到的特征点,采用可变大小的限界盒方法,提高了算法效率。最后采用FVC2004指纹库中的指纹图像,通过与经典指纹模式特征匹配算法的结果比较分析,验证了本文算法的可行性。
Application of the fingerprint of human history began in the ancient. Fingerprint identification is the oldest, as early as 6000 years ago, will use fingerprints to replace the human signature. Archaeologists confirmed that, as early as the late primitive society, the fingerprint as identification tool has been applied in China.While fingerprints are widely used in ancient China, but this application is only an emotional application, not on the basis of this synthesis and inductive reasoning and did not rise to the science and application of theory. With the social development and scientific and technological progress, the people of fingerprint pattern recognition system, more and more in-depth research, and have made tremendous progress. Many enterprises and schools such as the introduction of the fingerprint attendance system, but the current time and attendance system in recognition speed and accuracy are still some problems, and therefore requires us to fingerprint pattern recognition algorithms to do further study.
In this paper, research on fingerprint recognition technology in learning rough home and abroad, is studied based on the fingerprint pattern recognition system algorithm. Mainly contains: fingerprint image preprocessing、fingerprint feature extraction and fingerprint matching.
In the thesis the development of fingerprint pattern recognition at home and abroad was summarized in detail, fingerprint binarization algorithm and fingerprint pattern character matching algorithm were further investigated based on previous theory in order to improve the processing speed and performance of fingerprint pattern recognition algorithm. Firstly, as binary algorithm had poor anti-noise properties and difficulties in selecting suitable threshold value, a new binarized gray threshold segmentation method, which combined local adaptive and fingerprints grayscale image information and had and the characteristics of less calculation and preferable antijamming, was come up. Then based on genetic algorithm a new re-matching algorithm, of which the detail screening part was figured out by a new mothod of building irrelevant transform structure information and the coordinates calibration part was settled by polar coordinates, was put forward. Then an adjustable Bounding Box is used to process the calibrated feature points. Finally, it was proved by comparing the finger images in the FVC2004 fingerprints database with the images obtained by classic finger print pattern matching algorithm that this algorithm was feasible.
引文
[1]陈梁.嵌入式指纹识别系统研系统研究与实现[D].南京:南京航空航天大学硕士学位论文,2007.
[2]陈少春.智能楼宇的指纹门禁系统[D].硕士学位论文,东华大学,2008.1.
[3] J.Daugman.Complete discrete 2-D Gabor transform by neural networks for image analysis and Compression [J].IEEE Trans on ASSP,1988(7) :1169-1179.
[4] Jain A.K,RossA. Prebake S.An introduction to biometric recognition [J]. IEEE Transactions on Circuits for Video Technology. 2004,14(l):4-20.
[5] Hreehak AK,Mehugh J A,et al.Automated fingerprint recognition using structural matching[J].Patten Recognition,1990(8):893-904.
[6] Jain AK,Hong L, Bolle R.Online fingerprint verification[J].IEEE Trans PAMI,1997(4): 302-314.
[7]王芳.基于生物特征的身份认证技术研究与发展[J].科技信息.2009,28:433-434.
[8] Higgins P T.An Introduction of Biometrics[C].proceedings of Biometrics Consortium Conference. Arlington, VA, USA:[s.n.],2005.
[9]柴晓光,岑宝炽,民用指纹识别技术[M].北京:人民邮电出版社,2004.
[10] Kass M,Witkin A,FerzoPoulos D. Snakes:active on our model[C].Proe of First int Conf Computer Vision,1987:259-268.
[11] Williams,O.Gerald.Iris Recognition Technology[J].IEEE Aerospace and Electronic Systems Magazine, 1997(4): 23-29.
[12] Caudela G T, Grother P J.A Pattem Level Classification Automation System for Fingerprint [J]. Technology Report NISTIR,1995:5647.
[13] Hreehak A.K, Mehugh J.A Automated fingerprint recognition using structural matching[J].Pattern Recognition,1990, 23(8):893-890.
[14]王崇文,李见为.一种基于点模式匹配的指纹识别算法[J].重庆大学自然科学版,2002,(6): 27- 31.
[15]田捷,杨鑫.生物特征识别技术理论与应用[M].北京:电子工业出版社,2005.
[16]毛巨勇.2009年国内生物识别市场状况分析[J].中国安防.2009,12:66-68.
[17] Ming-Tak Leung,W.E. Engeler,P.FRANK.Fingerprint image Professing using neural net works[J]. IEEE Region 10, conference on computer and communication systems, September 1990,HK.
[18]指纹采集技术及其发展趋势[J].中国防伪报道.2008,10:30-33.
[19]李昊,傅曦.精通-Visua1C++指纹模式识别系统算法及实现[M].北京:人民邮电出版社,2008.
[20] Zhu E, Yin J P,Zhang G M, Fingeerint enhancement using circular gabor filter. In:ICIAR2004,LNCS 3212.Porto,Portugal,Sep29-oct l,2004,750-75833.
[21]王家隆.指纹图像的预处理及改进算法[D].大连理工大学硕士学位论文,2003,3.
[22] R.Clarke.Human identification in information systems: Management challenges and Public policy issues. Information technology and people, 2004, 7(4):6-37.
[23] Serra J.Image Analysis and Mathematical Morphology [M].San Diego: Academic ,1982,1.
[24]穆国燕,田俊霞,陈树中.一种有效的指纹图像分割和细化方法[J].人工智人工智能及识别技术,2002,10.
[25] R.Wildes.lris recognition: An emerging biometric techno1ogy [J]. Proceeding of IEEE, 1997,85(9):1348-1363.
[26] A.K.Jain.Recent advances in fingerprint verification [J] .In Proc.of 3rdInt.Conf. on Audio and Video Based Person Authentication,2001,182-191.
[27]林喜荣,于政涛,苏晓生等.一种利用动态滤波模板进行指纹图像增强的算法[J].清华大学学报(自然科学报),2001,41(8).
[28] O’GORMAN,L.,and NICKERSON,J.V: Matched filter design for fingerprint image enhancement. IEEE International Conference on Acoustics, Speech, and Signal Professing, NewYork,1998,PP.916-919.
[29] A.K.Jain,F.Farrokhnia. Unsupervised texture segmentation using Gabor filters[J] Pattern Recognition,1991, 24(12):1167-1186.
[30] R.W.Hall.Optimally small operator supports for fully Parallel thinning algorithms IEEE trans[J]. Patter Analysis and Machine intelligence,1993,15(8):828-833.
[31] R.T.Chin,H.K.Wan,D.L.Stover.A one-Pass thinning algorithm and its Parallel. Implementation [J]. Computer Vison GraPhies Image Processing, 1987,40(l):30-40.
[32] N.Ratha,K.Karu,S. Chen and A.K.Jain.Areal-time matching system for large Fingerprint data base.IEEETrans. On PAMI, 1996, 18(8):799-813.
[33] D.C.D.Hung. Enhancement and Feature Purification of Fingerprint Images. Pattem Recognition, 1993, 26(11):1661-1671.
[34] Q.Xiao and H.Raffat. Fingerprint image post processing: a combined statistical And structural approach.Pattem Recognition, 1991, 24(10):595-992.
[35] X.Jiang,W.Y.Yau, W.Ser.Detecting fingerprint minutiae by adaptive tracing the gra level ridge[J].Pattern Recognition, 2001,34(11):999-1013.
[36]黎昱.指纹图像局部纹线周期的准确提取[J].重庆大学学报,2001,9,24(5).
[37] Zs.M.Kovacs-Vajna, R.Rovatti,M.Frazzoni. Fingerprint ridge distance computation method loonies [J].Patten Reeognition,2000,33:69-80.
[38] Wahab A,Chin S H,Tan E C.Novel approach to automated fingerprint recognition.IEE Processing: Vision,Image&Signal Processing,1998,145(3):160-166.
[39] Jain A.K,RossA. Prabhakar S.An introduction to biometric recognition [J]. IEEE Transact- ons on Circuits for Video Technology. 2004,14(l):4-20.
[40]黄林波,杜坤梅,谢建阳等.基于ARM的指纹识别算法的研究与开发[J].哈尔滨商业大学学报(自然科学版),2005,02.
[41] Isenor D K,Zaky S G. Fingerprint Identification Using Graph Matching[J]. Patten Recognition, 1986,19(2):113-122.
[42]谭台哲,宁新宝,尹义龙,詹小四.一种基于中心点的指纹匹配算法[J].仪器仪表学报.2003,8:471-475.
[43] Jun G,Huo-Ming D, Ding-Guo C et al. Research on synergetic fingerprint Classification and matching[J].Machine Learning and Cybemeties.2003, 5(2):3066-3071.
[44] X.Jiang,W.Yau.Fingerprint Minutiae Matching Based on the Local And Global Structures, ICPR2000,Spain, 2000.
[45] M.Ballan,F.A.Sakarya,B.L.Evans.A fingerprint classification technique using directional images[J].Inproe.IEEEAsilomar Conf.on Signais Systems and Computers,1997,1:101-104.
[46] D.Maltoni,D.Maio, A.K.Jain,etal. Handbook of Fingerprint Recognition. Springer , New York, 2003.
[47]祝恩,殷建平,张国敏.基于多参考节点的指纹匹配方法[J].计算机研究与发展,2005, 42(10):1733-1739.
[48] G Stockman,S KoPstein,S Benett. Matching Images to Models for Registration and Objeet Detection via Clustering. IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol.4,No.3, pp:229-241.1982.
[49]陶刚.基于结构特征的指纹识别系统的匹配算法研究[D].华南师范大学硕士研究生学位论文,2002,7.
[50]杨海军.图像检测中若干低级处理问题及在指纹识别中应用的研究[D].西安:西安交通大学博士论文,2000.
[51] B.M.Mehtre,N.N. Murthy,S.Kapoor,etal. Segmentation of fingerprint images usin directional image[J].Pattern Recognition,1987, 20(4):429-435.
[52] R Kenneth.Castleman.Digital Image Processing[M]. Prentice-Hall International.2002.
[53]沈庭芝,方子文.数字图像处理及模式识别[M].北京:北京理工大学出版社,1998.
[54] Jiang,Xu-dong,Yau, Wei-Yun.Fingerprint minutiae matching based on the local and Globalstructures.In:sanfeliu.A, Villanueva.J.J,eds. Proceedings of the 15‘h International conference on Pattern Recognition.Los Alajnitos,CA:IEEE Computer Society Press, 2000:1042-1045.
[55] khan M A U,khan M K,khan M A. Fingerprint image enhancement using decimation-free direction filter bank .Information Technology Journal 2005,4(1):16-20.
[56] Zhu G C,Zhang C.A Top-Down fingerprint image enhancement method on Fourier analysis. In: Advances in Biometric recognition,Proc,Guangzhou,China,Dec 13-14,2004,439-448
[57]卢朝阳,张岗山,刘琳.指纹识别系统性能评价方法[J].西安电子科技大学学报:自然科学版,2002,29(6):804-808.
[2]陈少春.智能楼宇的指纹门禁系统[D].硕士学位论文,东华大学,2008.1.
[3] J.Daugman.Complete discrete 2-D Gabor transform by neural networks for image analysis and Compression [J].IEEE Trans on ASSP,1988(7) :1169-1179.
[4] Jain A.K,RossA. Prebake S.An introduction to biometric recognition [J]. IEEE Transactions on Circuits for Video Technology. 2004,14(l):4-20.
[5] Hreehak AK,Mehugh J A,et al.Automated fingerprint recognition using structural matching[J].Patten Recognition,1990(8):893-904.
[6] Jain AK,Hong L, Bolle R.Online fingerprint verification[J].IEEE Trans PAMI,1997(4): 302-314.
[7]王芳.基于生物特征的身份认证技术研究与发展[J].科技信息.2009,28:433-434.
[8] Higgins P T.An Introduction of Biometrics[C].proceedings of Biometrics Consortium Conference. Arlington, VA, USA:[s.n.],2005.
[9]柴晓光,岑宝炽,民用指纹识别技术[M].北京:人民邮电出版社,2004.
[10] Kass M,Witkin A,FerzoPoulos D. Snakes:active on our model[C].Proe of First int Conf Computer Vision,1987:259-268.
[11] Williams,O.Gerald.Iris Recognition Technology[J].IEEE Aerospace and Electronic Systems Magazine, 1997(4): 23-29.
[12] Caudela G T, Grother P J.A Pattem Level Classification Automation System for Fingerprint [J]. Technology Report NISTIR,1995:5647.
[13] Hreehak A.K, Mehugh J.A Automated fingerprint recognition using structural matching[J].Pattern Recognition,1990, 23(8):893-890.
[14]王崇文,李见为.一种基于点模式匹配的指纹识别算法[J].重庆大学自然科学版,2002,(6): 27- 31.
[15]田捷,杨鑫.生物特征识别技术理论与应用[M].北京:电子工业出版社,2005.
[16]毛巨勇.2009年国内生物识别市场状况分析[J].中国安防.2009,12:66-68.
[17] Ming-Tak Leung,W.E. Engeler,P.FRANK.Fingerprint image Professing using neural net works[J]. IEEE Region 10, conference on computer and communication systems, September 1990,HK.
[18]指纹采集技术及其发展趋势[J].中国防伪报道.2008,10:30-33.
[19]李昊,傅曦.精通-Visua1C++指纹模式识别系统算法及实现[M].北京:人民邮电出版社,2008.
[20] Zhu E, Yin J P,Zhang G M, Fingeerint enhancement using circular gabor filter. In:ICIAR2004,LNCS 3212.Porto,Portugal,Sep29-oct l,2004,750-75833.
[21]王家隆.指纹图像的预处理及改进算法[D].大连理工大学硕士学位论文,2003,3.
[22] R.Clarke.Human identification in information systems: Management challenges and Public policy issues. Information technology and people, 2004, 7(4):6-37.
[23] Serra J.Image Analysis and Mathematical Morphology [M].San Diego: Academic ,1982,1.
[24]穆国燕,田俊霞,陈树中.一种有效的指纹图像分割和细化方法[J].人工智人工智能及识别技术,2002,10.
[25] R.Wildes.lris recognition: An emerging biometric techno1ogy [J]. Proceeding of IEEE, 1997,85(9):1348-1363.
[26] A.K.Jain.Recent advances in fingerprint verification [J] .In Proc.of 3rdInt.Conf. on Audio and Video Based Person Authentication,2001,182-191.
[27]林喜荣,于政涛,苏晓生等.一种利用动态滤波模板进行指纹图像增强的算法[J].清华大学学报(自然科学报),2001,41(8).
[28] O’GORMAN,L.,and NICKERSON,J.V: Matched filter design for fingerprint image enhancement. IEEE International Conference on Acoustics, Speech, and Signal Professing, NewYork,1998,PP.916-919.
[29] A.K.Jain,F.Farrokhnia. Unsupervised texture segmentation using Gabor filters[J] Pattern Recognition,1991, 24(12):1167-1186.
[30] R.W.Hall.Optimally small operator supports for fully Parallel thinning algorithms IEEE trans[J]. Patter Analysis and Machine intelligence,1993,15(8):828-833.
[31] R.T.Chin,H.K.Wan,D.L.Stover.A one-Pass thinning algorithm and its Parallel. Implementation [J]. Computer Vison GraPhies Image Processing, 1987,40(l):30-40.
[32] N.Ratha,K.Karu,S. Chen and A.K.Jain.Areal-time matching system for large Fingerprint data base.IEEETrans. On PAMI, 1996, 18(8):799-813.
[33] D.C.D.Hung. Enhancement and Feature Purification of Fingerprint Images. Pattem Recognition, 1993, 26(11):1661-1671.
[34] Q.Xiao and H.Raffat. Fingerprint image post processing: a combined statistical And structural approach.Pattem Recognition, 1991, 24(10):595-992.
[35] X.Jiang,W.Y.Yau, W.Ser.Detecting fingerprint minutiae by adaptive tracing the gra level ridge[J].Pattern Recognition, 2001,34(11):999-1013.
[36]黎昱.指纹图像局部纹线周期的准确提取[J].重庆大学学报,2001,9,24(5).
[37] Zs.M.Kovacs-Vajna, R.Rovatti,M.Frazzoni. Fingerprint ridge distance computation method loonies [J].Patten Reeognition,2000,33:69-80.
[38] Wahab A,Chin S H,Tan E C.Novel approach to automated fingerprint recognition.IEE Processing: Vision,Image&Signal Processing,1998,145(3):160-166.
[39] Jain A.K,RossA. Prabhakar S.An introduction to biometric recognition [J]. IEEE Transact- ons on Circuits for Video Technology. 2004,14(l):4-20.
[40]黄林波,杜坤梅,谢建阳等.基于ARM的指纹识别算法的研究与开发[J].哈尔滨商业大学学报(自然科学版),2005,02.
[41] Isenor D K,Zaky S G. Fingerprint Identification Using Graph Matching[J]. Patten Recognition, 1986,19(2):113-122.
[42]谭台哲,宁新宝,尹义龙,詹小四.一种基于中心点的指纹匹配算法[J].仪器仪表学报.2003,8:471-475.
[43] Jun G,Huo-Ming D, Ding-Guo C et al. Research on synergetic fingerprint Classification and matching[J].Machine Learning and Cybemeties.2003, 5(2):3066-3071.
[44] X.Jiang,W.Yau.Fingerprint Minutiae Matching Based on the Local And Global Structures, ICPR2000,Spain, 2000.
[45] M.Ballan,F.A.Sakarya,B.L.Evans.A fingerprint classification technique using directional images[J].Inproe.IEEEAsilomar Conf.on Signais Systems and Computers,1997,1:101-104.
[46] D.Maltoni,D.Maio, A.K.Jain,etal. Handbook of Fingerprint Recognition. Springer , New York, 2003.
[47]祝恩,殷建平,张国敏.基于多参考节点的指纹匹配方法[J].计算机研究与发展,2005, 42(10):1733-1739.
[48] G Stockman,S KoPstein,S Benett. Matching Images to Models for Registration and Objeet Detection via Clustering. IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol.4,No.3, pp:229-241.1982.
[49]陶刚.基于结构特征的指纹识别系统的匹配算法研究[D].华南师范大学硕士研究生学位论文,2002,7.
[50]杨海军.图像检测中若干低级处理问题及在指纹识别中应用的研究[D].西安:西安交通大学博士论文,2000.
[51] B.M.Mehtre,N.N. Murthy,S.Kapoor,etal. Segmentation of fingerprint images usin directional image[J].Pattern Recognition,1987, 20(4):429-435.
[52] R Kenneth.Castleman.Digital Image Processing[M]. Prentice-Hall International.2002.
[53]沈庭芝,方子文.数字图像处理及模式识别[M].北京:北京理工大学出版社,1998.
[54] Jiang,Xu-dong,Yau, Wei-Yun.Fingerprint minutiae matching based on the local and Globalstructures.In:sanfeliu.A, Villanueva.J.J,eds. Proceedings of the 15‘h International conference on Pattern Recognition.Los Alajnitos,CA:IEEE Computer Society Press, 2000:1042-1045.
[55] khan M A U,khan M K,khan M A. Fingerprint image enhancement using decimation-free direction filter bank .Information Technology Journal 2005,4(1):16-20.
[56] Zhu G C,Zhang C.A Top-Down fingerprint image enhancement method on Fourier analysis. In: Advances in Biometric recognition,Proc,Guangzhou,China,Dec 13-14,2004,439-448
[57]卢朝阳,张岗山,刘琳.指纹识别系统性能评价方法[J].西安电子科技大学学报:自然科学版,2002,29(6):804-808.