基于指纹识别技术的职工考勤系统研究
|
摘要
随着信息技术的不断发展,安全、可靠的身份识别技术成为许多系统首先要考虑的问题。传统的身份识别手段如口令和IC卡技术已不能满足人们的需求,因此,生物特征识别技术因生物特征的唯一性和终生不变性而成为目前最为方便与安全的识别技术。指纹识别技术是最可靠、最有效的生物识别技术之一,自动指纹识别系统已经在众多领域有了广泛的应用。本文在现有的理论框架基础之上,对自动指纹识别技术的一些关键问题即指纹图像预处理、特征提取和匹配算法进行了深入研究,提出了一些改进的方法,并将指纹识别技术应用于职工考勤管理。
本文所做的主要工作和取得的研究成果如下:
(1)引进了一种改进的Gabor滤波器指纹图像增强算法,以不同的方式调节滤波器的形状、尺寸和频率,通过采用平均纹路频率进行增强,消除了块效应;通过采用圆形Gabor滤波器,消除了方向效应;将滤波器的尺寸按照图像的平均纹路频率进行调节,很好地适应了指纹图像平均纹路频率的变化。
(2)对指纹细节点特征提取算法进行了深入研究,采用8-邻域算法,提取指纹中所有的细节点,然后利用特征提取后处理算法去除伪细节点。
(3)提出了一种结合节点与方向场的细节匹配算法,在用节点进行旋转和平移对齐的基础上,计算两个指纹方向场的一致性。实验结果表明,该算法相比现有的基于节点的匹配算法能够更加准确地区分两个指纹。
(4)基于以上指纹识别算法开发了C/S与B/S混合模式的职工指纹考勤系统,并对提出的指纹图像增强、特征提取与匹配等算法进行了实验研究,对系统速度进行了测试,实验及测试结果表明,以上指纹识别算法可以有效地增强指纹图像,能准确提取指纹细节特征点并很好地进行匹配,系统能够满足日常考勤的需要。
本文所研究的指纹考勤系统将自动指纹识别技术应用于职工考勤管理,具有良好的市场前景和产业化前景。同时,由于自动指纹识别系统的通用性,本系统稍加修改就可以应用于其他需要身份认证的领域。
With the development of information technology,secure identity identification technology becomes the key problem in many systems.Traditional security systems based on token or IC card become fragile and cannot meet the demand of modern security system. So biometric technology is the most convenient and secure identity identification technology because of uniqueness and permanence of biometric character. Fingerprint identification is one of the most efficient biometric technologies.And Automatic Fingerprint Identification System (AFIS) has been widely employed in many applications. In this thesis, based on current theoretic framework, attention has been given to some key problems such as fingerprint image pre-processing、features extraction and minutiae matching for further improvement, and Fingerprint identification was applied in employee attendance management.
This thesis has mainly completed the following respects:
[1] A improved Gabor filter fingerprint enhancement algorithm is introduced, This thesis uses the average ridge frequency and the circle Gabor filter to enhance fingerprint images, and this method can remove the blocking effect and the orientation effect. Adaptive size of the filter can adapt to the change of the average ridge frequency of fingerprint images.
[2] The minutiae can be extracted by using 8-neighborhood algorithm. A feature extraction post-processing algorithm would delete all false minutiae.
[3] This thesis presents a fingerprint matching algorithm using minutiae and the orientation field. It first aligns two fingerprints based on their minutiae, and then computes the consistency of their orientation fields. Experiments show that this algorithm leads to substantial improvement in performance compared with the current minutiae-based algorithm.
[4] We developed a employee attendance system using fingerprint identification technology based on the hybrid mode of C/S and B/S. The thesis researched the algorithms of pre-processing and minutiae extraction ect. The experiments showed that the algorithms can be effectively enhance fingerprint images, and can accurately extract fingerprint image's minutiae. The system can meet the needs of attendance.
The fingerprint attendance system introduced in the thesis has can be used in employee attendance management, and also can be used in other area with a few changes. The system should have good market and industrialization future.
本文所做的主要工作和取得的研究成果如下:
(1)引进了一种改进的Gabor滤波器指纹图像增强算法,以不同的方式调节滤波器的形状、尺寸和频率,通过采用平均纹路频率进行增强,消除了块效应;通过采用圆形Gabor滤波器,消除了方向效应;将滤波器的尺寸按照图像的平均纹路频率进行调节,很好地适应了指纹图像平均纹路频率的变化。
(2)对指纹细节点特征提取算法进行了深入研究,采用8-邻域算法,提取指纹中所有的细节点,然后利用特征提取后处理算法去除伪细节点。
(3)提出了一种结合节点与方向场的细节匹配算法,在用节点进行旋转和平移对齐的基础上,计算两个指纹方向场的一致性。实验结果表明,该算法相比现有的基于节点的匹配算法能够更加准确地区分两个指纹。
(4)基于以上指纹识别算法开发了C/S与B/S混合模式的职工指纹考勤系统,并对提出的指纹图像增强、特征提取与匹配等算法进行了实验研究,对系统速度进行了测试,实验及测试结果表明,以上指纹识别算法可以有效地增强指纹图像,能准确提取指纹细节特征点并很好地进行匹配,系统能够满足日常考勤的需要。
本文所研究的指纹考勤系统将自动指纹识别技术应用于职工考勤管理,具有良好的市场前景和产业化前景。同时,由于自动指纹识别系统的通用性,本系统稍加修改就可以应用于其他需要身份认证的领域。
With the development of information technology,secure identity identification technology becomes the key problem in many systems.Traditional security systems based on token or IC card become fragile and cannot meet the demand of modern security system. So biometric technology is the most convenient and secure identity identification technology because of uniqueness and permanence of biometric character. Fingerprint identification is one of the most efficient biometric technologies.And Automatic Fingerprint Identification System (AFIS) has been widely employed in many applications. In this thesis, based on current theoretic framework, attention has been given to some key problems such as fingerprint image pre-processing、features extraction and minutiae matching for further improvement, and Fingerprint identification was applied in employee attendance management.
This thesis has mainly completed the following respects:
[1] A improved Gabor filter fingerprint enhancement algorithm is introduced, This thesis uses the average ridge frequency and the circle Gabor filter to enhance fingerprint images, and this method can remove the blocking effect and the orientation effect. Adaptive size of the filter can adapt to the change of the average ridge frequency of fingerprint images.
[2] The minutiae can be extracted by using 8-neighborhood algorithm. A feature extraction post-processing algorithm would delete all false minutiae.
[3] This thesis presents a fingerprint matching algorithm using minutiae and the orientation field. It first aligns two fingerprints based on their minutiae, and then computes the consistency of their orientation fields. Experiments show that this algorithm leads to substantial improvement in performance compared with the current minutiae-based algorithm.
[4] We developed a employee attendance system using fingerprint identification technology based on the hybrid mode of C/S and B/S. The thesis researched the algorithms of pre-processing and minutiae extraction ect. The experiments showed that the algorithms can be effectively enhance fingerprint images, and can accurately extract fingerprint image's minutiae. The system can meet the needs of attendance.
The fingerprint attendance system introduced in the thesis has can be used in employee attendance management, and also can be used in other area with a few changes. The system should have good market and industrialization future.
引文
[1]Jain A.K.,Hong L.,PanKanti S.,Biometrics:Promising Frontiers for Emerging Identification Market,Communication ACM,2000.
[2]尹义龙.自动指纹识别技术的发展与应用[J].南京大学学报(自然科学版),2002,38(1).
[3]Jain A.K.,Pankanti S.,Prabhakar S.,Ross A..Recent Advances in Fingerprint Verification.Proceedings of the Third International Conference on Audio-and-Video-Based Biometric Person Authentication,June 2001.
[4]Maio D.,Maltoni D.,Cappelli R.,Wayman J.L.,Jain A.K..FVC2000:Fingerprint Verification Competition.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(3):402-419.
[5]FVC2000.http://bias.csr.unibo.it/fvc2000.
[6]Maio D.,Maltoni D.,Cappelli R.,Wayman J.L.,Jain A.K..FVC2002:Second Fingerprint Verificatio Competition.16th International Conference on Pattern Recognition(ICPR'02)Volume 3 August 11-15,2002.
[7]FVC2002.http://bias.csr.unibo.it/fvc2002..
[8]Maio D.,Maltoni D.,Cappelli R.,Wayman J.L.,Jain A.K..FVC2004:Third Fingerprint Verification Competition.Proc.Int.Conf.Biometric Authentication,2004.
[9]FVC2004.http://bias.csr.unibo.it/fvc2004.
[10]H.Cummins,C.Midlo.Fingerprints,Palms and Soles.NewYork:Dover,1961:5-18
[11]Srdjan Sobajic,Amit Manwani,George Barbastathis.CNS286 project:fingerprint recognition.Technical RePort.1997,California Institute of Technology.
[12]张成海,张铎.现化自动识别技术与应用[M].北京:清华大学出版社,2003.
[13]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.
[14]霍宏涛.数字图像处理[M].北京:北京理工大学出版社,2002.
[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]王波涛,蔡安妮等.生物图像识别技术及其应用[J].计算机工程与设计,2001,22(4).
[17]苏彦华等.《数字图像分析与处理技术-VISUAL c++数字图像识别技术典型案例》[M].北京:人民邮电出版社,2004.
[18]赵向欣.中华指纹学[M].北京:群众出版社,1997.
[19]段少雄,田捷,李恒华.高效指纹考勤系统的研究与设计[J].计算机工程,2003(9).
[20]Kenneth.R.Castleman,朱志刚等译.数字图像处理[M].北京:电子工业出版社,2002
[21]马笑潇,黄席褪,周欣等.指纹自动识别系统中的关键技术——方向图[J].重庆大学学报(自然科学版),2001,24(3).
[22]边肇棋.模式识别[M].北京:清华大学出版社,1990.
[23]孙冬梅,裘正定.生物识别技术综述[J].电子学报,2001,29(12A).
[24]容观澳.计算机图像处理.北京:清华大学出版社,2000.
[25]张磊,卢朝阳,杨德英.几种指纹方向图算法及对比分析[J].微机发展,2003,13(6).
[26]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]芦焱.基于指纹识别的局域网登录系统[D].成都:成都理工大学,2005.
[28]曾明如,王慧.一种通用指纹考勤管理系统的开发[J].计算机与现代化,2003(2).
[29]Nalini K.Ratha,Kalle Karu,Shaoyun Chen,Anil K.Jain.A real-time matching system for large fingerprint databases.IEEE Transations on Pattern Analysis and Machine Intelligence,August 1996,18(8):799-813
[30]R.Germain,A Califano,S.Colville.Fingerprint matching using transformation parameter clustering.IEEE Computational Science and Engineering,1997,4(4):42-49.
[31]Bir Bhanu,Xuejun Tan.A triplet based approach for indexing of fingerprint database for identification.Proc.3rd International Conference on Audio- and Video-Based Person Authentication,Sweden,June 6～8,2001:205-210.
[32]Q.Guisheng,C.Minde,Q.Shi,N,Xue,A new automated fingerprint icentification system.Computer Science Technology,1989,4(4):289-294.
[33]B.Chatter jee,B.Mehtre.Autonatic fingerprint identification.Joumal of the Institution of Electronics and Telecom.,1991,37(5/6):493.
[34]Zsolt Miklos Kovocs-Vajna.A fingerprint verification system based on triangular matching and dynamic time warping.IEEE Transactions on Pattern Analysis and Machine Intelligence,November 2000,22(11);1266-1276.
[35]R.Cappelli,D.Maio,D.Maltoni.Modelling plastic distortion in fingerprint images.In proceedings of ICAPR2001,Second Int.Conf.Advances in Pattern Recognition,Riode Janeiro,March 2001.
[36]Shin-Hsu Chang,Fang-Hsuan Cheng,Wen-Shing Hsu,Guo-Zua Wu.Fast algorithm for point pattern matching:invariant to translations,rotations and scale changer.Pattern Recognition,30(2):311-316.
[37]何余良.基于关联概率模型的指纹识别算法.中国科学院自动化所[D].2003,7.
[38]Hong L.,Wang Y.F.,Janin A.K..Fingerprint Image Enhancement:Algorithm and Performance Evaluation,IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(8):777-789.
[39]Xiao Q,Raafat H.Fingerprint image postprocessing:a combined statistical and structural approach.Pattern Recognition.1991.24(10):985-992.
[40]K.Andrew.Hrechak,A.James.Automated fingerprint recognition using structural matching.Pattern Recognition.1990.23(8):893-904.
[41]G.Stockman,S.Kopstain and S.Benett.Matching images to models for registration and object detection via clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992 May,14(3).
[42]金英姿,邓少鹍.Visual Basic实用培训教程[M].北京:人民邮电出版社,2002.
[43]罗希平,田捷,武岩.指纹识别中的一种细节匹配算法.中国科学院自动化研究所人工智能实验室,1999.
[44]魏朗,陈涛.Visual C++程序设计攻略教程[M].西安:西安电子科技大学出版社,2004.
[45]李晓黎,张巍,ASP+SQL Server网络应用系统开发与实例[M].北京:人民邮电出版社,2004.
[46]胡标.ASP网络编程技术与实例[M].北京:人民邮电出版社,2004.
[47]丁安国.自动指纹识别系统的研究[D].郑州:郑州大学,2005.
[48]卞志强.Visual Basic网络程序设计[M].北京:人民邮电出版社,2003.
[49]祝恩,殷建平,周婧.一种结合节点和方向场的指纹匹配方法[J].计算机工程与科学,2005,27(9):54-56.
[50]尹义龙,宁新宝,张晓梅.改进的指纹细节特征提取算法[J].中国图像图形学报,2002,7(12):1302-1306.
[51]文慧智.大型指纹门禁系统的设计与初步研究[D].天津:天津大学,2005.
[52]彭曙蓉,王耀南.一种基于指纹识别的网络考勤系统[J].长沙电力学院学报(自然科学版)2006(5).
[53]李群辉.自动指纹识别系统的研究[D].西安:西北大学2005.
[54]曹丽婷,杨荣,陈旌.自动指纹考勤管理系统设计[J].计算机系统应用,2005(8).
[55]齐金平,孟建军,蒋兆远.指纹考勤管理软件的研究与实现[J].信息技术,2003(10).
[2]尹义龙.自动指纹识别技术的发展与应用[J].南京大学学报(自然科学版),2002,38(1).
[3]Jain A.K.,Pankanti S.,Prabhakar S.,Ross A..Recent Advances in Fingerprint Verification.Proceedings of the Third International Conference on Audio-and-Video-Based Biometric Person Authentication,June 2001.
[4]Maio D.,Maltoni D.,Cappelli R.,Wayman J.L.,Jain A.K..FVC2000:Fingerprint Verification Competition.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(3):402-419.
[5]FVC2000.http://bias.csr.unibo.it/fvc2000.
[6]Maio D.,Maltoni D.,Cappelli R.,Wayman J.L.,Jain A.K..FVC2002:Second Fingerprint Verificatio Competition.16th International Conference on Pattern Recognition(ICPR'02)Volume 3 August 11-15,2002.
[7]FVC2002.http://bias.csr.unibo.it/fvc2002..
[8]Maio D.,Maltoni D.,Cappelli R.,Wayman J.L.,Jain A.K..FVC2004:Third Fingerprint Verification Competition.Proc.Int.Conf.Biometric Authentication,2004.
[9]FVC2004.http://bias.csr.unibo.it/fvc2004.
[10]H.Cummins,C.Midlo.Fingerprints,Palms and Soles.NewYork:Dover,1961:5-18
[11]Srdjan Sobajic,Amit Manwani,George Barbastathis.CNS286 project:fingerprint recognition.Technical RePort.1997,California Institute of Technology.
[12]张成海,张铎.现化自动识别技术与应用[M].北京:清华大学出版社,2003.
[13]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.
[14]霍宏涛.数字图像处理[M].北京:北京理工大学出版社,2002.
[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]王波涛,蔡安妮等.生物图像识别技术及其应用[J].计算机工程与设计,2001,22(4).
[17]苏彦华等.《数字图像分析与处理技术-VISUAL c++数字图像识别技术典型案例》[M].北京:人民邮电出版社,2004.
[18]赵向欣.中华指纹学[M].北京:群众出版社,1997.
[19]段少雄,田捷,李恒华.高效指纹考勤系统的研究与设计[J].计算机工程,2003(9).
[20]Kenneth.R.Castleman,朱志刚等译.数字图像处理[M].北京:电子工业出版社,2002
[21]马笑潇,黄席褪,周欣等.指纹自动识别系统中的关键技术——方向图[J].重庆大学学报(自然科学版),2001,24(3).
[22]边肇棋.模式识别[M].北京:清华大学出版社,1990.
[23]孙冬梅,裘正定.生物识别技术综述[J].电子学报,2001,29(12A).
[24]容观澳.计算机图像处理.北京:清华大学出版社,2000.
[25]张磊,卢朝阳,杨德英.几种指纹方向图算法及对比分析[J].微机发展,2003,13(6).
[26]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]芦焱.基于指纹识别的局域网登录系统[D].成都:成都理工大学,2005.
[28]曾明如,王慧.一种通用指纹考勤管理系统的开发[J].计算机与现代化,2003(2).
[29]Nalini K.Ratha,Kalle Karu,Shaoyun Chen,Anil K.Jain.A real-time matching system for large fingerprint databases.IEEE Transations on Pattern Analysis and Machine Intelligence,August 1996,18(8):799-813
[30]R.Germain,A Califano,S.Colville.Fingerprint matching using transformation parameter clustering.IEEE Computational Science and Engineering,1997,4(4):42-49.
[31]Bir Bhanu,Xuejun Tan.A triplet based approach for indexing of fingerprint database for identification.Proc.3rd International Conference on Audio- and Video-Based Person Authentication,Sweden,June 6～8,2001:205-210.
[32]Q.Guisheng,C.Minde,Q.Shi,N,Xue,A new automated fingerprint icentification system.Computer Science Technology,1989,4(4):289-294.
[33]B.Chatter jee,B.Mehtre.Autonatic fingerprint identification.Joumal of the Institution of Electronics and Telecom.,1991,37(5/6):493.
[34]Zsolt Miklos Kovocs-Vajna.A fingerprint verification system based on triangular matching and dynamic time warping.IEEE Transactions on Pattern Analysis and Machine Intelligence,November 2000,22(11);1266-1276.
[35]R.Cappelli,D.Maio,D.Maltoni.Modelling plastic distortion in fingerprint images.In proceedings of ICAPR2001,Second Int.Conf.Advances in Pattern Recognition,Riode Janeiro,March 2001.
[36]Shin-Hsu Chang,Fang-Hsuan Cheng,Wen-Shing Hsu,Guo-Zua Wu.Fast algorithm for point pattern matching:invariant to translations,rotations and scale changer.Pattern Recognition,30(2):311-316.
[37]何余良.基于关联概率模型的指纹识别算法.中国科学院自动化所[D].2003,7.
[38]Hong L.,Wang Y.F.,Janin A.K..Fingerprint Image Enhancement:Algorithm and Performance Evaluation,IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(8):777-789.
[39]Xiao Q,Raafat H.Fingerprint image postprocessing:a combined statistical and structural approach.Pattern Recognition.1991.24(10):985-992.
[40]K.Andrew.Hrechak,A.James.Automated fingerprint recognition using structural matching.Pattern Recognition.1990.23(8):893-904.
[41]G.Stockman,S.Kopstain and S.Benett.Matching images to models for registration and object detection via clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992 May,14(3).
[42]金英姿,邓少鹍.Visual Basic实用培训教程[M].北京:人民邮电出版社,2002.
[43]罗希平,田捷,武岩.指纹识别中的一种细节匹配算法.中国科学院自动化研究所人工智能实验室,1999.
[44]魏朗,陈涛.Visual C++程序设计攻略教程[M].西安:西安电子科技大学出版社,2004.
[45]李晓黎,张巍,ASP+SQL Server网络应用系统开发与实例[M].北京:人民邮电出版社,2004.
[46]胡标.ASP网络编程技术与实例[M].北京:人民邮电出版社,2004.
[47]丁安国.自动指纹识别系统的研究[D].郑州:郑州大学,2005.
[48]卞志强.Visual Basic网络程序设计[M].北京:人民邮电出版社,2003.
[49]祝恩,殷建平,周婧.一种结合节点和方向场的指纹匹配方法[J].计算机工程与科学,2005,27(9):54-56.
[50]尹义龙,宁新宝,张晓梅.改进的指纹细节特征提取算法[J].中国图像图形学报,2002,7(12):1302-1306.
[51]文慧智.大型指纹门禁系统的设计与初步研究[D].天津:天津大学,2005.
[52]彭曙蓉,王耀南.一种基于指纹识别的网络考勤系统[J].长沙电力学院学报(自然科学版)2006(5).
[53]李群辉.自动指纹识别系统的研究[D].西安:西北大学2005.
[54]曹丽婷,杨荣,陈旌.自动指纹考勤管理系统设计[J].计算机系统应用,2005(8).
[55]齐金平,孟建军,蒋兆远.指纹考勤管理软件的研究与实现[J].信息技术,2003(10).