基于DSP的指纹识别系统的算法研究
|
摘要
传统的安全系统主要采用基于信物或口令的方式，随着社会的发展，这种系统显得越来越脆弱。为了应对这些挑战，人们把目光转向了生物识别技术，希望能借助人体的生理特征或行为动作来提高身份识别的精度。
所谓指纹就是在人们的手指表面上的凸凹不平的各种各样的纹路。现代统计学已经表明，指纹具有稳定性和唯一性。最近，随着计算机技术和嵌入式系统技术的发展，自动指纹识别技术取得了很快的发展，指纹图像处理技术是自动指纹识别系统的关键技术之一，本论文重点介绍的就是这种指纹图像处理技术。
作者在收集和分析了近年来大量的国内外的关于指纹图像处理技术的学术文献基础上，分析了指纹图像的特性，提出了一套适用于光学指纹传感器采集的指纹图像的处理算法，这些算法包括指纹图像滤波、指纹图像的细化、特征点的提取、指纹图像的点模式匹配等步骤。
本文在最后将整套算法移植到DSP平台上，并且结合DSP处理器的性能特点对算法做了进一步的优化，合理地对DSK片上资源进行了配置，使之有利于DSP实现。
Traditional security system mainly uses token or password for secrecy, but this system has become frailer with the development of society. To cope with this challenge, mankind has turned to biometrics technique and hoped enhancing identity verification definition by using people's physical character and behavior.
The so-called fingerprint is the pattern of ridges and valleys on the surface of a fingertip. Modern statistics has proved that fingerprint is unique and steady. With the development of micro-computer technique and embedded developing system technique, automated fingerprint identification system (AFIS) has made a great progress in the recent period. This article mainly stresses on one of the key techniques of AFIS, the fingerprint image processing technique.
The author analyzed the characteristics of fingerprint image based on a number of internal and overseas academic articles and documents on fingerprint images processing technique which were published in these recent years, then developed a set of fingerprint image processing arithmetic that adapts to the fingerprint image gathered by optical device. The arithmetic includes several steps: filtering waves, thinning, refining the minutiae, fingerprint matching on dot mode, etc.
It has transformed the arithmetic to DSP platform at the end of this article. The progress of optimizing the arithmetic and deploying the resources of the DSK reasonably by combination with the features and performance of DSP processor benefits for realization of DSP.
所谓指纹就是在人们的手指表面上的凸凹不平的各种各样的纹路。现代统计学已经表明，指纹具有稳定性和唯一性。最近，随着计算机技术和嵌入式系统技术的发展，自动指纹识别技术取得了很快的发展，指纹图像处理技术是自动指纹识别系统的关键技术之一，本论文重点介绍的就是这种指纹图像处理技术。
作者在收集和分析了近年来大量的国内外的关于指纹图像处理技术的学术文献基础上，分析了指纹图像的特性，提出了一套适用于光学指纹传感器采集的指纹图像的处理算法，这些算法包括指纹图像滤波、指纹图像的细化、特征点的提取、指纹图像的点模式匹配等步骤。
本文在最后将整套算法移植到DSP平台上，并且结合DSP处理器的性能特点对算法做了进一步的优化，合理地对DSK片上资源进行了配置，使之有利于DSP实现。
Traditional security system mainly uses token or password for secrecy, but this system has become frailer with the development of society. To cope with this challenge, mankind has turned to biometrics technique and hoped enhancing identity verification definition by using people's physical character and behavior.
The so-called fingerprint is the pattern of ridges and valleys on the surface of a fingertip. Modern statistics has proved that fingerprint is unique and steady. With the development of micro-computer technique and embedded developing system technique, automated fingerprint identification system (AFIS) has made a great progress in the recent period. This article mainly stresses on one of the key techniques of AFIS, the fingerprint image processing technique.
The author analyzed the characteristics of fingerprint image based on a number of internal and overseas academic articles and documents on fingerprint images processing technique which were published in these recent years, then developed a set of fingerprint image processing arithmetic that adapts to the fingerprint image gathered by optical device. The arithmetic includes several steps: filtering waves, thinning, refining the minutiae, fingerprint matching on dot mode, etc.
It has transformed the arithmetic to DSP platform at the end of this article. The progress of optimizing the arithmetic and deploying the resources of the DSK reasonably by combination with the features and performance of DSP processor benefits for realization of DSP.
引文
[1] 王蕴红，谭铁牛．现代身份鉴别新技术—生物特征识别技术．中国基础科学．2000(9)：4-10页
[2] Liu-Jimenez J, Sanchez-Reillo R, Sanchez-Avila C. Biometric Co-Processor for an Authentication System using Iris Biometrics. Security Technology, 2004 (38): 131-135 P
[3] 王波涛，蔡安妮，孙景鳌．指纹图像识别技术及其应用．计算机工程与应用．2001，7(1)：79-83页
[4] 方志刚，叶伟中．多种生物特征识别技术．计算机工程．2003，29(9)：140-143页
[5] 王崇文，李见为，周宏文等．指纹识别系统的设计与实现．计算机应用．2001，21(12)：61-64页
[6] 吕知辛，黄遵令．指纹识别方法及其应用．应用技术．2004，1：20-24页
[7] 刘中秋，贺晓明．指纹传感器综述．第一届长三角地区传感技术学术交流会论文集．2004：9-12页
[8] D C Douglas Hung. Enhancement and feature purification of fingerprint images. Pattern Tecognition, 1993, 26(11): 1661-1671P
[9] Lin Hong, Anil Jain. Fingerprint Enhancement. In: Proc First IEEE WACV, 1996: 202-207P
[10] Lin Hong, Yifei Wang, Anil Jain. Fingerprint Image Enhancement: Algorithm and Performance Evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998, 20(8): 777-789P
[11] Nalini K Ratha, Shaoyun Chen, Anil K Jain. Adaptive flow orientation-based feature extraction in fingerprint images. Pattern Recognition, 1995, 28(11): 1657-1672P
[12] Anil Jain, Lin Hong. On-line fingerprint verification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1991, 19(4): 302-314P
[13] A P Fitz, R J Green. Fingerprint classification using a hexagonal fast Fourier transform. Pattern Recognition. 1996, 29(10): 1587-1597P
[14] Lawrence O'Gorman, Jeffrey V Nickfrson. An approach to fingerprint filter design. Pattern Recognitong. 1989, 22(1): 29-38P
[15] 陈昌，徐晓明．指纹预处理中的图像增强．中国科技信息．2005(24A)：32-32页
[16] 何东宇，蔡远利．基于方向图的指纹预处理方法研究[J]．计算机工程与应用．2004，40(14)：77-80，108页
[17] 周媛媛，张成，林嘉字．基于块方向的指纹图像预处理算法．微型机与应用．2004，23(12)：56-59页
[18] O'Gorman L, Nickersion J V. An approach to fingerprint filter design. Pattern Recognition. 1989, 22(1): 29—38P
[19] 刘勇，晏蒲柳，郭成城．指纹图像脊线提取．武汉大学学报．2001，47(1)：106-110页
[20] 张明，吴陈，陈楠．基于方向滤波的指纹图像增强算法．微机发展．2005，15(6)：85-87，133页
[21] 张正言，聂桂军，徐荣青．基于连续方向图的指纹图像预处理算法．计算机测量与控制．2006，14(12)：1707-1710页
[22] 刘爽，王芙蓉．一种改进的指纹图像二值化算法．计算机与数字工程．2006，34(12)：48-50页
[23] 郭雷，陈大海，李刚，李海．指纹自动识别中二值化对指纹特征的影响．计算机应用研究．2006，23(9)：49-50，53页
[24] 楚亚蕴，詹小四，孙兆才，王峰，陈蕴．一种结合方向信息的指纹图像二值化算法．中国图象图形学报．2006，11(6)：855-860页
[25] 孙以雷，陈红卫．指纹图像的二值化方法研究．舰船电子工程．2006，26(1)：110-112页
[26] 叶四民，陈福祥．指纹图像预处理中的二值化技术．自动化与仪器仪表．2001(2)：30-32，39页
[27] 邹奉庭，叶四民等．指纹图像纹线细化处理的几种方法．陕西建材．2001(6)：54-56页
[28] 王业琳，宁新宝，尹义龙．指纹图像细化算法的研究．南京大学学报：自然科学版．2003，39(4)：468-475页
[29] 梁广民，蔡学军．OPTA算法的改进及其在指纹图像细化中的应用．计算机工程与设计．2006，27(23)：4607-4608页
[30] 李徐周，于飞．有效的指纹纹线细化方法．计算机工程与设计．2006，27(4)：626-628，647页
[31] 陶刚，李吉桂．细化指纹图中伪特征点的一体化去除算法．现代计算机：下半月版．2002(10)：40-42，55页
[32] 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．中国图象图形学报．2003，8(12)：1467-1474页
[33] 刘灵丽，李丽娟．一种滤除细化指纹图像中伪特征点的新方法．计算机应用研究．2006，23(11)：239-240，243页
[34] 王崇文，李见为等．指纹细节特征提取与剪枝．光电工程．2002，29(4)：68-71页
[35] 刘文星，王肇圻等．细化指纹上岛屿的判别与滤除．光电子激光．2002，13(3)：282-284页
[36] 王崇文，李见为．一种基于点模式匹配的指纹识别算法．重庆大学学报．2002，(6)：27-37页
[37] Kalle Karu. Fingerprint Classification. Pattern Recognition. 1996, 29(3): 27-40P
[38] Hong Lin. Automatic personal identification using fingerprints. Michigan State University. 1998: 5-46P
[39] Mehtre B M, Chatterjee B. Segmentation of fingerprint images-a composite method. Pattern Recognition. 1989, 22(4): 381～385P
[40] Wang Sen, Zhang Weiwei, Wang Yangsheng. Fingerprint classification by directional fields. In: Proceedings of the 4th IEEE International Conference on Multimodal Interfaces. 2002, 397-398P
[41] 程建刚，田捷，任群等．基于奇异点的指纹分类．第6届国际青年计算机工作者会议暨第2届生物特征识别研讨会会议论文集．杭州，2001：27-34页
[42] Karu K, Jain A K. Fingerprint classification. Pattern Recognition. 1996, 29(3): 389～404P
[43] Nakamura O, Goto K, Minami T. Fingerprint Classification by Directional Distribution Patterns. Systems, Computers, Controls. 1982(13)5: 81-89P
[44] 张伟伟，王森，王阳生．基于点检测的指纹图像奇异点检测．见：第6届国际青年计算机工作者会议暨第2届生物特征识别研讨会会议论文集．杭州，2001：51-56页
[45] Srinivasan V S, Murthy N N. Detection of singular points in fingerprint images. Pattern Recognition. 1992, 25(2): 139～153P
[46] 谭台哲，宁新宝，尹义龙等．一种指纹图像奇异点检测的方法．软件学报．2003，14(6)：1082～1088页
[47] Kawagoe M, Tojo A. Fingerprint pattern classification. Pattern Recognition. 1984, 17(3): 295-303P
[48] A. R. Rao and R. C. Jain, Computerized Flow Field Analysis: Oriented Texture Fields. IEEE Trans on PAMI. 1992, 14(7): 693-709P
[49] Sanjay Ranade, Azriel Rosenfeld. Point pattern matching by relaxation Pattern Recognition. 1980(5): 269-275P
[50] G. Stockman, S. Kopstain, S. Benett. Matching images to models for registration and object detection via clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1992(3): 229-241P
[51] J. P. Statink, E. Backer. Finding point correspondences using simulated annealing. Pattern Recognition. 1995(2): 231-241P
[52] Ratkovic JP. Increasing efficiency in the criminal just ice system: the use og new technology for criminal identification and latent print processing. California: The Rand Coipomtion. 1980
[53] Liu J H, Lin C H, Ostetbetg J Weta. Fingerprint comparison the develop of a single fingerprint filing and searching system. Journal of Forensic Science. 1982(27): 305-317P
[54] Hrechak A. K, Mchugh H.A. Automated fingerprint recognition using structural matching. Pattern Recognition, 1990, 23(8): 893-904P
[55] Isenor D,K, Zaky S. G. Fingerprint identification using matching pattern. Pattern Recogniton. 1986(2): 113-122P
[56] Smljan Sobajic, Amit Manwani, Barbastathis G. Fingerprint Recognition. California Institute of Technology, 1997
[57] D. Lavine, B. A. Lambaird, L. N. Kana. Recognition of spatial point patterns. Pattern Recognition. 1983(3): 289-295P
[58] J. Hong, X. Tan. A new approach to point pattern matching. Pattern Recognition. 1988(8): 82-84P
[59] 漆远，田捷，邓翔．基于遗传算法的指纹图象匹配算法及应用．软件学报．2000，11(4)：488-493页
[60] 张雄伟，陈亮，徐光辉．DSP芯片的原理与开发应用．第三版．北京：电子工业出版社，2003：1-10页
[61] TMS320VC5509 Fixed-Point Digital Signal Processor Date Sheet. Texas Instruments, April 2001
[62] ICETEK-VC5509-A板及教学实验箱说明书．北京瑞泰创新科技有限公
[63]TMS320C55xOptimizing C/C++ Compiler User's Guide. Texas Instruments, 2003
[2] Liu-Jimenez J, Sanchez-Reillo R, Sanchez-Avila C. Biometric Co-Processor for an Authentication System using Iris Biometrics. Security Technology, 2004 (38): 131-135 P
[3] 王波涛，蔡安妮，孙景鳌．指纹图像识别技术及其应用．计算机工程与应用．2001，7(1)：79-83页
[4] 方志刚，叶伟中．多种生物特征识别技术．计算机工程．2003，29(9)：140-143页
[5] 王崇文，李见为，周宏文等．指纹识别系统的设计与实现．计算机应用．2001，21(12)：61-64页
[6] 吕知辛，黄遵令．指纹识别方法及其应用．应用技术．2004，1：20-24页
[7] 刘中秋，贺晓明．指纹传感器综述．第一届长三角地区传感技术学术交流会论文集．2004：9-12页
[8] D C Douglas Hung. Enhancement and feature purification of fingerprint images. Pattern Tecognition, 1993, 26(11): 1661-1671P
[9] Lin Hong, Anil Jain. Fingerprint Enhancement. In: Proc First IEEE WACV, 1996: 202-207P
[10] Lin Hong, Yifei Wang, Anil Jain. Fingerprint Image Enhancement: Algorithm and Performance Evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998, 20(8): 777-789P
[11] Nalini K Ratha, Shaoyun Chen, Anil K Jain. Adaptive flow orientation-based feature extraction in fingerprint images. Pattern Recognition, 1995, 28(11): 1657-1672P
[12] Anil Jain, Lin Hong. On-line fingerprint verification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1991, 19(4): 302-314P
[13] A P Fitz, R J Green. Fingerprint classification using a hexagonal fast Fourier transform. Pattern Recognition. 1996, 29(10): 1587-1597P
[14] Lawrence O'Gorman, Jeffrey V Nickfrson. An approach to fingerprint filter design. Pattern Recognitong. 1989, 22(1): 29-38P
[15] 陈昌，徐晓明．指纹预处理中的图像增强．中国科技信息．2005(24A)：32-32页
[16] 何东宇，蔡远利．基于方向图的指纹预处理方法研究[J]．计算机工程与应用．2004，40(14)：77-80，108页
[17] 周媛媛，张成，林嘉字．基于块方向的指纹图像预处理算法．微型机与应用．2004，23(12)：56-59页
[18] O'Gorman L, Nickersion J V. An approach to fingerprint filter design. Pattern Recognition. 1989, 22(1): 29—38P
[19] 刘勇，晏蒲柳，郭成城．指纹图像脊线提取．武汉大学学报．2001，47(1)：106-110页
[20] 张明，吴陈，陈楠．基于方向滤波的指纹图像增强算法．微机发展．2005，15(6)：85-87，133页
[21] 张正言，聂桂军，徐荣青．基于连续方向图的指纹图像预处理算法．计算机测量与控制．2006，14(12)：1707-1710页
[22] 刘爽，王芙蓉．一种改进的指纹图像二值化算法．计算机与数字工程．2006，34(12)：48-50页
[23] 郭雷，陈大海，李刚，李海．指纹自动识别中二值化对指纹特征的影响．计算机应用研究．2006，23(9)：49-50，53页
[24] 楚亚蕴，詹小四，孙兆才，王峰，陈蕴．一种结合方向信息的指纹图像二值化算法．中国图象图形学报．2006，11(6)：855-860页
[25] 孙以雷，陈红卫．指纹图像的二值化方法研究．舰船电子工程．2006，26(1)：110-112页
[26] 叶四民，陈福祥．指纹图像预处理中的二值化技术．自动化与仪器仪表．2001(2)：30-32，39页
[27] 邹奉庭，叶四民等．指纹图像纹线细化处理的几种方法．陕西建材．2001(6)：54-56页
[28] 王业琳，宁新宝，尹义龙．指纹图像细化算法的研究．南京大学学报：自然科学版．2003，39(4)：468-475页
[29] 梁广民，蔡学军．OPTA算法的改进及其在指纹图像细化中的应用．计算机工程与设计．2006，27(23)：4607-4608页
[30] 李徐周，于飞．有效的指纹纹线细化方法．计算机工程与设计．2006，27(4)：626-628，647页
[31] 陶刚，李吉桂．细化指纹图中伪特征点的一体化去除算法．现代计算机：下半月版．2002(10)：40-42，55页
[32] 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．中国图象图形学报．2003，8(12)：1467-1474页
[33] 刘灵丽，李丽娟．一种滤除细化指纹图像中伪特征点的新方法．计算机应用研究．2006，23(11)：239-240，243页
[34] 王崇文，李见为等．指纹细节特征提取与剪枝．光电工程．2002，29(4)：68-71页
[35] 刘文星，王肇圻等．细化指纹上岛屿的判别与滤除．光电子激光．2002，13(3)：282-284页
[36] 王崇文，李见为．一种基于点模式匹配的指纹识别算法．重庆大学学报．2002，(6)：27-37页
[37] Kalle Karu. Fingerprint Classification. Pattern Recognition. 1996, 29(3): 27-40P
[38] Hong Lin. Automatic personal identification using fingerprints. Michigan State University. 1998: 5-46P
[39] Mehtre B M, Chatterjee B. Segmentation of fingerprint images-a composite method. Pattern Recognition. 1989, 22(4): 381～385P
[40] Wang Sen, Zhang Weiwei, Wang Yangsheng. Fingerprint classification by directional fields. In: Proceedings of the 4th IEEE International Conference on Multimodal Interfaces. 2002, 397-398P
[41] 程建刚，田捷，任群等．基于奇异点的指纹分类．第6届国际青年计算机工作者会议暨第2届生物特征识别研讨会会议论文集．杭州，2001：27-34页
[42] Karu K, Jain A K. Fingerprint classification. Pattern Recognition. 1996, 29(3): 389～404P
[43] Nakamura O, Goto K, Minami T. Fingerprint Classification by Directional Distribution Patterns. Systems, Computers, Controls. 1982(13)5: 81-89P
[44] 张伟伟，王森，王阳生．基于点检测的指纹图像奇异点检测．见：第6届国际青年计算机工作者会议暨第2届生物特征识别研讨会会议论文集．杭州，2001：51-56页
[45] Srinivasan V S, Murthy N N. Detection of singular points in fingerprint images. Pattern Recognition. 1992, 25(2): 139～153P
[46] 谭台哲，宁新宝，尹义龙等．一种指纹图像奇异点检测的方法．软件学报．2003，14(6)：1082～1088页
[47] Kawagoe M, Tojo A. Fingerprint pattern classification. Pattern Recognition. 1984, 17(3): 295-303P
[48] A. R. Rao and R. C. Jain, Computerized Flow Field Analysis: Oriented Texture Fields. IEEE Trans on PAMI. 1992, 14(7): 693-709P
[49] Sanjay Ranade, Azriel Rosenfeld. Point pattern matching by relaxation Pattern Recognition. 1980(5): 269-275P
[50] G. Stockman, S. Kopstain, S. Benett. Matching images to models for registration and object detection via clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1992(3): 229-241P
[51] J. P. Statink, E. Backer. Finding point correspondences using simulated annealing. Pattern Recognition. 1995(2): 231-241P
[52] Ratkovic JP. Increasing efficiency in the criminal just ice system: the use og new technology for criminal identification and latent print processing. California: The Rand Coipomtion. 1980
[53] Liu J H, Lin C H, Ostetbetg J Weta. Fingerprint comparison the develop of a single fingerprint filing and searching system. Journal of Forensic Science. 1982(27): 305-317P
[54] Hrechak A. K, Mchugh H.A. Automated fingerprint recognition using structural matching. Pattern Recognition, 1990, 23(8): 893-904P
[55] Isenor D,K, Zaky S. G. Fingerprint identification using matching pattern. Pattern Recogniton. 1986(2): 113-122P
[56] Smljan Sobajic, Amit Manwani, Barbastathis G. Fingerprint Recognition. California Institute of Technology, 1997
[57] D. Lavine, B. A. Lambaird, L. N. Kana. Recognition of spatial point patterns. Pattern Recognition. 1983(3): 289-295P
[58] J. Hong, X. Tan. A new approach to point pattern matching. Pattern Recognition. 1988(8): 82-84P
[59] 漆远，田捷，邓翔．基于遗传算法的指纹图象匹配算法及应用．软件学报．2000，11(4)：488-493页
[60] 张雄伟，陈亮，徐光辉．DSP芯片的原理与开发应用．第三版．北京：电子工业出版社，2003：1-10页
[61] TMS320VC5509 Fixed-Point Digital Signal Processor Date Sheet. Texas Instruments, April 2001
[62] ICETEK-VC5509-A板及教学实验箱说明书．北京瑞泰创新科技有限公
[63]TMS320C55xOptimizing C/C++ Compiler User's Guide. Texas Instruments, 2003
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |