指纹识别系统核心算法的研究
|
摘要
指纹识别技术作为最传统、最成熟的生物识别方式之一已在许多领域得以应用。但指纹识别的核心技术仍存在许多尚未解决的问题，自动指纹识别技术现在是，未来几年仍将是一个重要且极具挑战性的模式识别研究课题。我们的指纹识别课题组在此方面作了深入的研究，并取得了一定的成果。本文在前期算法的基础上，主要进行了以下几个方面的研究：
(1)考虑纹线切线方向和法线方向的灰度变化，准确地求取方向图。根据纹线走向特点进行对方向图进行点平滑与块平滑，有效地消除指纹部分折痕。
(2)采用动态阈值法进行二值化，比较了不同的分块大小对二值化效果的影响。提出新的二值化增强算法，对纹线进行修复与孔洞填充。
(3)完善了特征提取算法。并结合局部纹线方向信息，针对不同的噪声采用针对性的算法，将各类噪声引起的伪特征点分别予以删除。
(4)提出了一种基于纹线拟合的指纹匹配方法。该算法基于指纹纹线的相似程度寻找一对基准特征点，并且使用误差分层扩散的方法进行特征点的细匹配。实验结果证明，该算法匹配速度很快，误识率低，准确性高。
(5)使用“指纹+密码”试验性的设计了系统的工作流程。录入时采用三枚指纹作为模板，在比对时三次拒认后输入密码后再比对。小规模的实验证明，该流程在具有较好的安全性并保证了一定的速度与准确率
我们在Windows 2000的平台上，综合以上算法的修改及完善，实现指纹识别系统FV2004，并利用我们建立的指纹库，对系统进行了测试和评价。测试结果表明处理和识别性能均有不同程度的提高，具体细节可参考各章的描述。
As one of most reliable biometric technology, Automatic fingerprint verification has been apply to many field. We develop some key algorithms of automatic fingerprint identification system (AFIS), main contexts are as following:
(1) The direction map of fingerprint image is computed accurately by the change of gray on the tangent direction and the dircection of nomal. It brings outs a new method on smooth of the direction map. Experimental results show tht it is feasible for fingerprint processing.
(2) We discuss the dynamic thresholding binarization method in fingerprint image preprocessing and present a new algorithm about binarization enhancement.it can fill the little hole on the ridge effectively.
(3) The set of original minutiae is directly extracted from thinned fingerprint images. Then combining with the information of local ridge direction, special algorithms are designed with respect to various noises to delete pseudo minutiae from original minutiae set.
(4) An algorithm based on ridge fitting for seeking pairs of reference minutiae is presented .It use the algorithm of error diffused by level in the stage of matching minutiae .
(5) A system combined with password and fingerprint is proposed.Experimental results show it is more secure and mord accurate than customary system.
All the algorithm in this thesis have been carry out and test in the PC. The result show that the function of the system has been improved greatly .
(1)考虑纹线切线方向和法线方向的灰度变化，准确地求取方向图。根据纹线走向特点进行对方向图进行点平滑与块平滑，有效地消除指纹部分折痕。
(2)采用动态阈值法进行二值化，比较了不同的分块大小对二值化效果的影响。提出新的二值化增强算法，对纹线进行修复与孔洞填充。
(3)完善了特征提取算法。并结合局部纹线方向信息，针对不同的噪声采用针对性的算法，将各类噪声引起的伪特征点分别予以删除。
(4)提出了一种基于纹线拟合的指纹匹配方法。该算法基于指纹纹线的相似程度寻找一对基准特征点，并且使用误差分层扩散的方法进行特征点的细匹配。实验结果证明，该算法匹配速度很快，误识率低，准确性高。
(5)使用“指纹+密码”试验性的设计了系统的工作流程。录入时采用三枚指纹作为模板，在比对时三次拒认后输入密码后再比对。小规模的实验证明，该流程在具有较好的安全性并保证了一定的速度与准确率
我们在Windows 2000的平台上，综合以上算法的修改及完善，实现指纹识别系统FV2004，并利用我们建立的指纹库，对系统进行了测试和评价。测试结果表明处理和识别性能均有不同程度的提高，具体细节可参考各章的描述。
As one of most reliable biometric technology, Automatic fingerprint verification has been apply to many field. We develop some key algorithms of automatic fingerprint identification system (AFIS), main contexts are as following:
(1) The direction map of fingerprint image is computed accurately by the change of gray on the tangent direction and the dircection of nomal. It brings outs a new method on smooth of the direction map. Experimental results show tht it is feasible for fingerprint processing.
(2) We discuss the dynamic thresholding binarization method in fingerprint image preprocessing and present a new algorithm about binarization enhancement.it can fill the little hole on the ridge effectively.
(3) The set of original minutiae is directly extracted from thinned fingerprint images. Then combining with the information of local ridge direction, special algorithms are designed with respect to various noises to delete pseudo minutiae from original minutiae set.
(4) An algorithm based on ridge fitting for seeking pairs of reference minutiae is presented .It use the algorithm of error diffused by level in the stage of matching minutiae .
(5) A system combined with password and fingerprint is proposed.Experimental results show it is more secure and mord accurate than customary system.
All the algorithm in this thesis have been carry out and test in the PC. The result show that the function of the system has been improved greatly .
引文
[1] Lin Hong Automatic personal identif ication using fingerprints.Dissertation for Ph.D. [D],1998, Michigan State University, 45-46
[2] A. K. Jain, S. Prabhakar and L. Hong. A multichannel approach to fingerprint classification. IEEE Transactions on Pattern Recognition and Machine Analysis, 1999, 21(4): 348-359.
[3] NALINI K, RATHA, KALLE KARU, CHEN SHAOYUN, et al. A real-time maching system for large fingerprint database[J]. IEEE Trans on Pattern Analysis and Machine intelligence. 1996, 18(8): 799-812
[4] LinHong, Yifei Wan, and AnAl Jain. Fingerprint image enhancement algorithm and performance evaluation. IEEE Trans On Pattern Analysis And Machine Intelligence. 1998, 20(8): 777-789
[5] HONG L, JAIN A K, PANKANTIS, et al. Fingerpaint image enchancement[A]. Proc. First IEEE WACV[C].1996, Sarasota, Fla: 1661-1671
[6] 黄席樾，马笑潇，汪鹏等 基于方向基元集描述的求取指纹方向图的方法及应用[J] 重庆大学学报(自然科学版)。2000，23(5)：57-61
[7] KAWAGOE M, TOJO A Fingerprint pattern classification[J].Pattern Recognition. 1984, 17(3): 295-303
[8] MeHTREBM, CHATTERJEEB. Segmentation of fingerprint image a composite method, Pattern Recognition. 1989, 22(4): 381 385.
[9] RAO A R. A taxonomy for texture description and identification[M].New York; Springer Verlag, 1990
[10] MICNAEL M. S. CHONG, TAN NAN NGEE, LIU JUN, Geometric framework for fingerprint image classification[J]. Pattern Recognition, 1997, 30(9): 1475-1488.
[11] 赵向欣 中华指纹学[M]．北京：群众出版社，1977．
[12] 刘少聪．新指纹学．北京：中国刑事警察学院出版社，19842
[13] 徐建华．图象处理与分析．第一版，北京：科学出版社，1992
[14] 穆国燕等 一种有效的指纹图象分割和细化方法 计算机工程 2002，28(10)：128-129
[15] Jain A, Hong L, Bolle R. On-Line Fingerprint Verfication. IEEE Trans on Pattern Analysis and Machine Intelligence. 1997, 19(4): 302-314
[16 Huang D C. Enhancement and Feature Purification of Fingerprint Images. Pattern Recognition. 1993, 26(11): 1661-1671
[17] 周新伦 柳健 刘华志《数字图象处理》国防工业出版社，1986
[18] 黄裕霞，指纹图象处理中若干算法的研究，研究生硕士论文，1996
[19] Lin Hong. Automatic personal identification using fingerprints[D]. Dissertation for Ph. D., Michigan State University, 1998: 5～46.
[20] N. Ratha, S. Chen, and A. K. Jain. Adaptive flow orientation based feature extraction in fingerprint images[J]. Pattern Recognition, 1995, 28(11): 1657～1672.
[21] B. Mehtre. Fingerprint image analysis for automatic identification [J]. Machine Vision and Application, 1993, 6(2-3): 124～139.
[22] L. Hong, A. K. Jain, R. Bolle and S. Pankanti. Identity authentication using fingerprints[C]. Proc. of First Int'l Conference on Audio and Video-Based Biometric Person Authentication, Switzerland, 1997: 103-110.
[23] D. Maio and D. Maltoni. Direct gray-scale minutiae detection in fingerprints[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(1): 27-40.
[24] X. Fang, Wei-Yun Yau and Wee Ser. Detecting the fingerprint minutiae by adaptive tracing the gray-level ridge[J]. Pattern Recognition, 2001, 34(5): 999-1013
[25] Q. Xiao and H. Raafat. Fingerprint image processing: A combined statistical and structural approach[J]. Pattern Recognition, 1991, 24(10): 985-992.
[26] B. Moayer and K. S. Fu. Atree system approach for fingerprint. Pattern
Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 1986, (8): 376-387
[27] 尹义龙，宁新宝，张晓梅．自动指纹识别技术的发展与应用[J]．南京大学学报，2002，38(1)29～35．
[28] S. Ranade & A. Rosenfeld. Point pattern matching by relaxation[J]. Pattern Recognition, 1980, 12(5)269～275.
[29] D.H. Ballard. Generalized hough transform to detect arbitrary patterns[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1981, 3(2)111～122.
[30] G. Stockman, S. Kopstein & S. Benett. Matching images to models for registration and object detection via clustering[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1982, 4(3)229～241.
[31] S.H. Chang, F.H. Cheng, W.H. Hsu & G.Z. Wu. Fast algorithm for point pattern matching: Invariant to translations, rotations, and scale changes[J]. Pattern Recognition, 1997, 30(2)321～339.
[32] M. Sparrow & P. Sparrow. A topological approach to the matching of single fingerprints: Development of algorithms for use on rolled impressions[M]. U.S.A. Government Printing Office, Washington, D. C.: National Bureau of Standards Special Publication, 1985.
[33] A. Hrechak & J. Mchugh. Automated fingerprint recognition using structural matching[J]. Pattern Recognition, 1990, 23(8)893～904.
[34] D. Isenor & S. Zaky. Fingerprint identification using graph matching[J]. Pattern Recognition, 1986, 19(2)113～122.
[35] J.P. Pascual Starink & Eric Backer. Finding point correspondence using simulated annealing[J]. Pattern Recognition, 1995, 28(2) 231～240.
[36] V.V. Vinod & S. Ghose. Point Matching using asymmetric neural networks[J]. Pattern Recognition, 1993, 26(8)1207～1214.
[37] G. Scott & C. Longuet-Higgins. An algorithm for associating the features of two images[J]. Proc. Royal Society of London, 1991, 244
21～26.
[38] S. Sclaroff & A.P. Pentland. Modal matching for correspondence and recognition[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1995, 17(6)545～561.
[39] Lin Hong. Automatic personal identification using fingerprints[D]. East Lansing: Michigan State University, 1998.
[40] 赵向峰 指纹识别系统及其算法的研究 华南师范大学研究生学位论文 2000
[41] 陶刚 基于结构特征的指纹识别系统的匹配算法研究 华南师范大学研究生学位论文 2002
[42] 王峰 指纹身份验证系统的研究 华南师范大学研究生学位论文 2003
[43] 卢昀 利用光学活体指纹采集仪采集指纹图像的预处理算法研究 华南师大学研究学位论文 2002
[44] 漆远，田捷，邓翔．基于遗传算法的指纹图匹配算法及应用[J]．软件学报，2000，11(4)488～493．
[45] 罗希平，田捷 自动指纹识别中的图像增强与细节匹配 软件学报 2002，13(5)：946-956
[46] 张雄 贺贵明 模板更新的指纹密码联合系统 计算机工程 2002 29(2)：22-23
[47] 李吉桂 陈俊侠 基于方向图的指纹图像处理算法 计算机科学 2000 27(8)：75-76
[2] A. K. Jain, S. Prabhakar and L. Hong. A multichannel approach to fingerprint classification. IEEE Transactions on Pattern Recognition and Machine Analysis, 1999, 21(4): 348-359.
[3] NALINI K, RATHA, KALLE KARU, CHEN SHAOYUN, et al. A real-time maching system for large fingerprint database[J]. IEEE Trans on Pattern Analysis and Machine intelligence. 1996, 18(8): 799-812
[4] LinHong, Yifei Wan, and AnAl Jain. Fingerprint image enhancement algorithm and performance evaluation. IEEE Trans On Pattern Analysis And Machine Intelligence. 1998, 20(8): 777-789
[5] HONG L, JAIN A K, PANKANTIS, et al. Fingerpaint image enchancement[A]. Proc. First IEEE WACV[C].1996, Sarasota, Fla: 1661-1671
[6] 黄席樾，马笑潇，汪鹏等 基于方向基元集描述的求取指纹方向图的方法及应用[J] 重庆大学学报(自然科学版)。2000，23(5)：57-61
[7] KAWAGOE M, TOJO A Fingerprint pattern classification[J].Pattern Recognition. 1984, 17(3): 295-303
[8] MeHTREBM, CHATTERJEEB. Segmentation of fingerprint image a composite method, Pattern Recognition. 1989, 22(4): 381 385.
[9] RAO A R. A taxonomy for texture description and identification[M].New York; Springer Verlag, 1990
[10] MICNAEL M. S. CHONG, TAN NAN NGEE, LIU JUN, Geometric framework for fingerprint image classification[J]. Pattern Recognition, 1997, 30(9): 1475-1488.
[11] 赵向欣 中华指纹学[M]．北京：群众出版社，1977．
[12] 刘少聪．新指纹学．北京：中国刑事警察学院出版社，19842
[13] 徐建华．图象处理与分析．第一版，北京：科学出版社，1992
[14] 穆国燕等 一种有效的指纹图象分割和细化方法 计算机工程 2002，28(10)：128-129
[15] Jain A, Hong L, Bolle R. On-Line Fingerprint Verfication. IEEE Trans on Pattern Analysis and Machine Intelligence. 1997, 19(4): 302-314
[16 Huang D C. Enhancement and Feature Purification of Fingerprint Images. Pattern Recognition. 1993, 26(11): 1661-1671
[17] 周新伦 柳健 刘华志《数字图象处理》国防工业出版社，1986
[18] 黄裕霞，指纹图象处理中若干算法的研究，研究生硕士论文，1996
[19] Lin Hong. Automatic personal identification using fingerprints[D]. Dissertation for Ph. D., Michigan State University, 1998: 5～46.
[20] N. Ratha, S. Chen, and A. K. Jain. Adaptive flow orientation based feature extraction in fingerprint images[J]. Pattern Recognition, 1995, 28(11): 1657～1672.
[21] B. Mehtre. Fingerprint image analysis for automatic identification [J]. Machine Vision and Application, 1993, 6(2-3): 124～139.
[22] L. Hong, A. K. Jain, R. Bolle and S. Pankanti. Identity authentication using fingerprints[C]. Proc. of First Int'l Conference on Audio and Video-Based Biometric Person Authentication, Switzerland, 1997: 103-110.
[23] D. Maio and D. Maltoni. Direct gray-scale minutiae detection in fingerprints[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(1): 27-40.
[24] X. Fang, Wei-Yun Yau and Wee Ser. Detecting the fingerprint minutiae by adaptive tracing the gray-level ridge[J]. Pattern Recognition, 2001, 34(5): 999-1013
[25] Q. Xiao and H. Raafat. Fingerprint image processing: A combined statistical and structural approach[J]. Pattern Recognition, 1991, 24(10): 985-992.
[26] B. Moayer and K. S. Fu. Atree system approach for fingerprint. Pattern
Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 1986, (8): 376-387
[27] 尹义龙，宁新宝，张晓梅．自动指纹识别技术的发展与应用[J]．南京大学学报，2002，38(1)29～35．
[28] S. Ranade & A. Rosenfeld. Point pattern matching by relaxation[J]. Pattern Recognition, 1980, 12(5)269～275.
[29] D.H. Ballard. Generalized hough transform to detect arbitrary patterns[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1981, 3(2)111～122.
[30] G. Stockman, S. Kopstein & S. Benett. Matching images to models for registration and object detection via clustering[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1982, 4(3)229～241.
[31] S.H. Chang, F.H. Cheng, W.H. Hsu & G.Z. Wu. Fast algorithm for point pattern matching: Invariant to translations, rotations, and scale changes[J]. Pattern Recognition, 1997, 30(2)321～339.
[32] M. Sparrow & P. Sparrow. A topological approach to the matching of single fingerprints: Development of algorithms for use on rolled impressions[M]. U.S.A. Government Printing Office, Washington, D. C.: National Bureau of Standards Special Publication, 1985.
[33] A. Hrechak & J. Mchugh. Automated fingerprint recognition using structural matching[J]. Pattern Recognition, 1990, 23(8)893～904.
[34] D. Isenor & S. Zaky. Fingerprint identification using graph matching[J]. Pattern Recognition, 1986, 19(2)113～122.
[35] J.P. Pascual Starink & Eric Backer. Finding point correspondence using simulated annealing[J]. Pattern Recognition, 1995, 28(2) 231～240.
[36] V.V. Vinod & S. Ghose. Point Matching using asymmetric neural networks[J]. Pattern Recognition, 1993, 26(8)1207～1214.
[37] G. Scott & C. Longuet-Higgins. An algorithm for associating the features of two images[J]. Proc. Royal Society of London, 1991, 244
21～26.
[38] S. Sclaroff & A.P. Pentland. Modal matching for correspondence and recognition[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1995, 17(6)545～561.
[39] Lin Hong. Automatic personal identification using fingerprints[D]. East Lansing: Michigan State University, 1998.
[40] 赵向峰 指纹识别系统及其算法的研究 华南师范大学研究生学位论文 2000
[41] 陶刚 基于结构特征的指纹识别系统的匹配算法研究 华南师范大学研究生学位论文 2002
[42] 王峰 指纹身份验证系统的研究 华南师范大学研究生学位论文 2003
[43] 卢昀 利用光学活体指纹采集仪采集指纹图像的预处理算法研究 华南师大学研究学位论文 2002
[44] 漆远，田捷，邓翔．基于遗传算法的指纹图匹配算法及应用[J]．软件学报，2000，11(4)488～493．
[45] 罗希平，田捷 自动指纹识别中的图像增强与细节匹配 软件学报 2002，13(5)：946-956
[46] 张雄 贺贵明 模板更新的指纹密码联合系统 计算机工程 2002 29(2)：22-23
[47] 李吉桂 陈俊侠 基于方向图的指纹图像处理算法 计算机科学 2000 27(8)：75-76