人体掌形识别系统的设计
摘要
安全性是许多系统和场所要考虑的问题,如机场、银行、监狱、各政府部门、军事机构、企业计算机信息系统等,安全、方便的身份认证技术非常重要。而现行的系统安全技术已经遭遇严峻的挑战!
掌形识别作为生物特征识别的主流技术之一,以其采集设备实现简单(相对于指纹,虹膜识别等)、认证速度快而成为继指纹识别之后的又一项生物特征识别主要方法。目前国外的生物特征识别商品市场份额上,掌形识别己经基本和指纹识别持平,成为了又一个大的生物特征识别产品。但是由于技术上的原因和产品价格上的因素以及国外对技术的保密,我们国内还没有相应于掌形识别的成熟产品,这也正是本课题研究的动机和目标。
本文设计了一种基于数字信号处理器(DSP)的掌形识别系统。提出了有活体检测功能的手掌固定平台,该固定平台解决了传统固定栓平台对手指造成凹陷的缺点,使掌形图像采集更加精确。利用电容传感器进行活体检测,很好的杜绝了伪造掌形模板的可能。采用可编程逻辑器件(CPLD)驱动步进电机,从而带动扫描头对手掌进行纵向扫描,实现对人体手掌二维图像的采集。配合液晶显示、键盘扫描来实现ID号的输入,完成对系统使用权限的确认。增加USB和以太网功能使系统很方便与外部实现数据传输和联机工作。与国外传统的掌形识别系统相比,本系统降低了成本,简化了图像处理算法,减少了识别时间,提高了图像采集精度。所以本硬件平台既很好地实现了功能,又完成了掌形识别设备的国产化。
Security is the consideration of many systems and sites, such as airports, banks, prisons, government departments, military institutions, computer information systems of enterprises, safe and convenient authentication technology is very important. But existing system security techniques are facing severe challenges!
As one of the mainstream techniques of biometric identification, hand geometry recognition has been another biometrics identification method except fingerprint because of the simple collection instrument (as opposed to fingerprints, iris recognition, etc.) and the high verification speed. At present, foreign biometric commodity market share, fortune has been the basic shape recognition and fingerprint recognition balanced, and then become a major biometric products. However, due to technical reasons and product prices on the factors, as well as the confidentiality of technology abroad, we also did not correspond to domestic palm-shaped identification mature product, and this is precisely the motive of this research and goals.
In this thesis, a hand geometry recognition system id designed based on digital signal processor (DSP). A hand-fixed platform with live detect function is put forward, and the disadvantage of finger hollow due to the traditional platform with finger-fixed poles is eliminated and the palm image collecting becomes more accurate. Capacity sensors are adopted in live detection to eliminate the possibility of fractal palm template. Using programmable logic devices (CPLD) drive stepper motor, thereby giving impetus to the palm-scanning first vertical scanning, two-dimensional realization of the human hand image acquisition. With liquid crystal display, keyboard, scanning ID to achieve the import, use of the system to complete the confirmation authority. USB and Ethernet functionality to increase the system very convenient and external data transmission and on-line work. And the traditional palm-shaped foreign identification systems, the system reduces costs and simplifies the image processing algorithm to reduce the recognition time and improve the accuracy of image acquisition. So this is a good hardware platform to achieve the function, completed a palm-recognition of domestic equipment.
掌形识别作为生物特征识别的主流技术之一,以其采集设备实现简单(相对于指纹,虹膜识别等)、认证速度快而成为继指纹识别之后的又一项生物特征识别主要方法。目前国外的生物特征识别商品市场份额上,掌形识别己经基本和指纹识别持平,成为了又一个大的生物特征识别产品。但是由于技术上的原因和产品价格上的因素以及国外对技术的保密,我们国内还没有相应于掌形识别的成熟产品,这也正是本课题研究的动机和目标。
本文设计了一种基于数字信号处理器(DSP)的掌形识别系统。提出了有活体检测功能的手掌固定平台,该固定平台解决了传统固定栓平台对手指造成凹陷的缺点,使掌形图像采集更加精确。利用电容传感器进行活体检测,很好的杜绝了伪造掌形模板的可能。采用可编程逻辑器件(CPLD)驱动步进电机,从而带动扫描头对手掌进行纵向扫描,实现对人体手掌二维图像的采集。配合液晶显示、键盘扫描来实现ID号的输入,完成对系统使用权限的确认。增加USB和以太网功能使系统很方便与外部实现数据传输和联机工作。与国外传统的掌形识别系统相比,本系统降低了成本,简化了图像处理算法,减少了识别时间,提高了图像采集精度。所以本硬件平台既很好地实现了功能,又完成了掌形识别设备的国产化。
Security is the consideration of many systems and sites, such as airports, banks, prisons, government departments, military institutions, computer information systems of enterprises, safe and convenient authentication technology is very important. But existing system security techniques are facing severe challenges!
As one of the mainstream techniques of biometric identification, hand geometry recognition has been another biometrics identification method except fingerprint because of the simple collection instrument (as opposed to fingerprints, iris recognition, etc.) and the high verification speed. At present, foreign biometric commodity market share, fortune has been the basic shape recognition and fingerprint recognition balanced, and then become a major biometric products. However, due to technical reasons and product prices on the factors, as well as the confidentiality of technology abroad, we also did not correspond to domestic palm-shaped identification mature product, and this is precisely the motive of this research and goals.
In this thesis, a hand geometry recognition system id designed based on digital signal processor (DSP). A hand-fixed platform with live detect function is put forward, and the disadvantage of finger hollow due to the traditional platform with finger-fixed poles is eliminated and the palm image collecting becomes more accurate. Capacity sensors are adopted in live detection to eliminate the possibility of fractal palm template. Using programmable logic devices (CPLD) drive stepper motor, thereby giving impetus to the palm-scanning first vertical scanning, two-dimensional realization of the human hand image acquisition. With liquid crystal display, keyboard, scanning ID to achieve the import, use of the system to complete the confirmation authority. USB and Ethernet functionality to increase the system very convenient and external data transmission and on-line work. And the traditional palm-shaped foreign identification systems, the system reduces costs and simplifies the image processing algorithm to reduce the recognition time and improve the accuracy of image acquisition. So this is a good hardware platform to achieve the function, completed a palm-recognition of domestic equipment.
引文
[1]林喜荣.生物特征识别技术的标准化进程[J].清华大学学报,自然科学版, 2006,(2):194-198.
[2] D. Zhang, W. K. Kong, J. You, and M. Wong. Biometrics - Online palmprint identification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(9): 1041-1050, 2006.
[3]李雄军,苏廷弼.基于生物特征的Auto ID技术――BioID[J].计算机工程与应用,2002,(16):86-89.
[4] Ying Wu, T.Huang. Capturing Articulated Human hand Motion[J]. A Divide and Conquer Approach, IEEE, 1997, 18(16): 842-853.
[5]武瑞红.手掌形状身份识别系统特征参量提取技术[J].仪器仪表学报,2002,(6):678-679.
[6] Mihai Badoiu, Sariel Har-Peled, Piotr Indyk. Approximate clustering via core-sets[J]. Theory of Computing, 2004, 14(11): 250-257.
[7] Asa Ben-Hur, David Horn, Hava T. Siegelmann, Vladimir Vapnik. Support Vector Clustering[J]. Revised Version 2002, 2002, 18(16): 136-198.
[8]邢殿勇.掌形仪管理系统研制[J].计算机工程,2005,(2):229-230.
[9] Civi H. Implicit Algebraic Curves and Surfaces for Shape Modeling and Recognition[J]. Bogazici University, 1997, 7(11): 69-86.
[10]孙冬梅,裘正定,何冰.基于手形的生物特征认证技术--生物特征识别的新进展[J].计算机学报,2001,(23):8-13.
[11] Jain A.K, Ross A, Pankanti S, A Prototype Hand Geometry-Based Verification System[J]. in 2nd International Conference on Audio- and Video-based Biometric Person Authentication, Washington D.C, 1999, 7(11): 69-86.
[12] Ta dizen T, Tarel J P, Cooper D.B. Improving the Stability of Algebraic Curves for Applications[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 16(13): 1216-1218.
[13]刘宏,李锦涛,苗军.多方法融合解决人脸检测中的光照补偿[J].系统仿真学报,2001,(13):46-49.
[14] TCD1501D数据手册.日本东芝公司:2001:6-9.
[15]常丹华.基于CPLD技术的CCD驱动时序产生方法[J].仪表技术与传感器,2001,(3):26-28.
[16]邓华,方滨.基于CPLD技术的CMOS图像传感器高速采集系统[J].现代电子技术,2004(7):6-8.
[17] R.L. Zunkel. Hand Geometry Based Verification[J]. pp. 87-101, in Biometrics, Eds. A. Jain, R. Bolle, S. Pankanti, Kluwer Academic Publishers, 1999.
[18]兰荣清.线阵CCD驱动器设计新方法[J].光电子激光,1997,8(4):295~297.
[19] A. K. Jain, L. Hong , S. Pankanti. Biometric Identification[J]. Comm. ACM, 2007: 91-98.
[20] A. K. Jain, R. P. W. Duin, J. Mao. Statistical Pattern Recognition Review [J]. IEEE Transactions on PAMI, 2001, 22(4): 87-101.
[21] A.K. Jain, A. Ross, S. Pankanti. A Prototype Hand Geometry-based Verification System[J]. 2nd Int'l Conference on Audio- and Video-based Biometric Person Authentication, Washington D.C, 1999: 166-171.
[22] K. Jain, A. Ross, S. Prabhakar. Biometrics-Based Web Access[J]. MSU Technical Report TR98-33, 1998: 36-48.
[23] Biometric Market Group. Biometric Market Report 2000[P]. 2000: 1-3.
[24] International Biometric Group. Biometrics: An overview[P]. 1999: 2-4.
[25] Sandia National Laboratories. The Sandia Report on Biometrical Identification[J]. 2001:36-48.
[26] M. S. Bartlett, H. M. Lades, T. J. Sejnowski. Independent component representations for face recognition[M]. Conference on Human Vision and Electronic Imaging III, San Jose, California, 1998: 250-316.
[27] Y. Boykov, O. Veksler, R. Zabih. Fast approximation energy minimization via graph cuts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11): 1222-1239.
[28] J. F. Canny. A computational approach to edge detection[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2003, 8(6): 679-698.
[29] T. F. Cootes, G. J. Edwards, C.J. Taylor. Active appearance models[J]. IEEE PAMI, 2005: 681-685.
[30]李永远,谢小平.CCD输出信号处理[J].应用光学,1997,18(1):20-23.
[31]王鑫,陈健.高速并行模/数转换器在数据采集系统中的应用[J].电子元器件应用,2003(12):36-42.
[32] MIHAI B, SARIEL H P, PIOTR I. Approximate clustering via Core-sets[J]. Theory of Computing,2002,14(11):250-257.
[33]贡晟.CPLD和FPGA高密度可编程逻辑器件的比较[J].电子产品世界,2003(4):26 -29.
[34] Texas Instruments. TMS320C6713, TMS320C6713b FLOATING-POINT DIGITAL SIGNAL PROCESSORS, 2004
[35] TexasInstruments. TPS70345, TPS70348, TPS70351, TPS70358, TPS70302 DUAL-OUTPUT.
[36] Micron Technology. SYNCHRONOUS DRAM MT48LC2M32B2-512K x 32 x 4 banks, 2002.
[37] Texas Instruments. TMS320c6000 EMIF-to-External SDRAM Interface, 2003.
[38]广州周立功单片机发展有限公司.ZLG7290 I2C接口键盘及LED驱动器.
[39] Philips Semiconductors. THE I2C-BUS SPECIFICATION VERSION 2.1, 2000.
[40] Texas Instruments.TMS320C6000 DSP Inter-Integrated Circuit(I2C)Module Reference Guide, 2002
[41]北京精电蓬远显示技术有限公司.内藏T6963C控制器图形液晶显示模块使用手册.
[42] KANG L S, LI Y. Asynchronous Parallelization of Algorithm For Function Optimization[J]. Press,2002,23(8):876-881.
[43] G. H. Golub, C. F. van Loan. Matrix Computation[J]. 3rd Edition, The John Hopkins University Press, Baltimore, 1996: 36-40.
[44] C. Xu, J. L. Prince. Snakes shapes and gradient vector flow[J]. IEEE Transactions on Image Processing, 2004, 7(3): 25-31.
[45] B. Takacs. Comparing face images using the modified Hausdorff distance[J]. Pattern Recognition, 1998: 1873-1881.
[46] R. Sanches-Reillo, C. Sanchez-Avila, A. Gonzalez-Marcos. Biometric Identification through Hand Geometry Measurements[J]. IEEE Transactions of Pattern Analysis and Machine Intelligence, 2000, 22(10): 42-53.
[47] Y. L. Lay. Hand shape recognition[J]. Optics and Laser Technology, 2000, 32(1):1–5.
[48]李长贵.线阵CCD用于实时动态测量技术[J].光学技术,1999,(2):5-8.
[49]彭启综.DSP与实时数字信号处理[M].成都:电子科技大学出版社,1995:2-478.
[50]江思敏,刘畅.TMS320C6000 DSP应用开发教程[M].北京:机械工业出版社,2004:153-196.
[51]王庆有.CCD应用技术[M].天津:天津大学出版社,2000:173-249.
[2] D. Zhang, W. K. Kong, J. You, and M. Wong. Biometrics - Online palmprint identification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(9): 1041-1050, 2006.
[3]李雄军,苏廷弼.基于生物特征的Auto ID技术――BioID[J].计算机工程与应用,2002,(16):86-89.
[4] Ying Wu, T.Huang. Capturing Articulated Human hand Motion[J]. A Divide and Conquer Approach, IEEE, 1997, 18(16): 842-853.
[5]武瑞红.手掌形状身份识别系统特征参量提取技术[J].仪器仪表学报,2002,(6):678-679.
[6] Mihai Badoiu, Sariel Har-Peled, Piotr Indyk. Approximate clustering via core-sets[J]. Theory of Computing, 2004, 14(11): 250-257.
[7] Asa Ben-Hur, David Horn, Hava T. Siegelmann, Vladimir Vapnik. Support Vector Clustering[J]. Revised Version 2002, 2002, 18(16): 136-198.
[8]邢殿勇.掌形仪管理系统研制[J].计算机工程,2005,(2):229-230.
[9] Civi H. Implicit Algebraic Curves and Surfaces for Shape Modeling and Recognition[J]. Bogazici University, 1997, 7(11): 69-86.
[10]孙冬梅,裘正定,何冰.基于手形的生物特征认证技术--生物特征识别的新进展[J].计算机学报,2001,(23):8-13.
[11] Jain A.K, Ross A, Pankanti S, A Prototype Hand Geometry-Based Verification System[J]. in 2nd International Conference on Audio- and Video-based Biometric Person Authentication, Washington D.C, 1999, 7(11): 69-86.
[12] Ta dizen T, Tarel J P, Cooper D.B. Improving the Stability of Algebraic Curves for Applications[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 16(13): 1216-1218.
[13]刘宏,李锦涛,苗军.多方法融合解决人脸检测中的光照补偿[J].系统仿真学报,2001,(13):46-49.
[14] TCD1501D数据手册.日本东芝公司:2001:6-9.
[15]常丹华.基于CPLD技术的CCD驱动时序产生方法[J].仪表技术与传感器,2001,(3):26-28.
[16]邓华,方滨.基于CPLD技术的CMOS图像传感器高速采集系统[J].现代电子技术,2004(7):6-8.
[17] R.L. Zunkel. Hand Geometry Based Verification[J]. pp. 87-101, in Biometrics, Eds. A. Jain, R. Bolle, S. Pankanti, Kluwer Academic Publishers, 1999.
[18]兰荣清.线阵CCD驱动器设计新方法[J].光电子激光,1997,8(4):295~297.
[19] A. K. Jain, L. Hong , S. Pankanti. Biometric Identification[J]. Comm. ACM, 2007: 91-98.
[20] A. K. Jain, R. P. W. Duin, J. Mao. Statistical Pattern Recognition Review [J]. IEEE Transactions on PAMI, 2001, 22(4): 87-101.
[21] A.K. Jain, A. Ross, S. Pankanti. A Prototype Hand Geometry-based Verification System[J]. 2nd Int'l Conference on Audio- and Video-based Biometric Person Authentication, Washington D.C, 1999: 166-171.
[22] K. Jain, A. Ross, S. Prabhakar. Biometrics-Based Web Access[J]. MSU Technical Report TR98-33, 1998: 36-48.
[23] Biometric Market Group. Biometric Market Report 2000[P]. 2000: 1-3.
[24] International Biometric Group. Biometrics: An overview[P]. 1999: 2-4.
[25] Sandia National Laboratories. The Sandia Report on Biometrical Identification[J]. 2001:36-48.
[26] M. S. Bartlett, H. M. Lades, T. J. Sejnowski. Independent component representations for face recognition[M]. Conference on Human Vision and Electronic Imaging III, San Jose, California, 1998: 250-316.
[27] Y. Boykov, O. Veksler, R. Zabih. Fast approximation energy minimization via graph cuts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11): 1222-1239.
[28] J. F. Canny. A computational approach to edge detection[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2003, 8(6): 679-698.
[29] T. F. Cootes, G. J. Edwards, C.J. Taylor. Active appearance models[J]. IEEE PAMI, 2005: 681-685.
[30]李永远,谢小平.CCD输出信号处理[J].应用光学,1997,18(1):20-23.
[31]王鑫,陈健.高速并行模/数转换器在数据采集系统中的应用[J].电子元器件应用,2003(12):36-42.
[32] MIHAI B, SARIEL H P, PIOTR I. Approximate clustering via Core-sets[J]. Theory of Computing,2002,14(11):250-257.
[33]贡晟.CPLD和FPGA高密度可编程逻辑器件的比较[J].电子产品世界,2003(4):26 -29.
[34] Texas Instruments. TMS320C6713, TMS320C6713b FLOATING-POINT DIGITAL SIGNAL PROCESSORS, 2004
[35] TexasInstruments. TPS70345, TPS70348, TPS70351, TPS70358, TPS70302 DUAL-OUTPUT.
[36] Micron Technology. SYNCHRONOUS DRAM MT48LC2M32B2-512K x 32 x 4 banks, 2002.
[37] Texas Instruments. TMS320c6000 EMIF-to-External SDRAM Interface, 2003.
[38]广州周立功单片机发展有限公司.ZLG7290 I2C接口键盘及LED驱动器.
[39] Philips Semiconductors. THE I2C-BUS SPECIFICATION VERSION 2.1, 2000.
[40] Texas Instruments.TMS320C6000 DSP Inter-Integrated Circuit(I2C)Module Reference Guide, 2002
[41]北京精电蓬远显示技术有限公司.内藏T6963C控制器图形液晶显示模块使用手册.
[42] KANG L S, LI Y. Asynchronous Parallelization of Algorithm For Function Optimization[J]. Press,2002,23(8):876-881.
[43] G. H. Golub, C. F. van Loan. Matrix Computation[J]. 3rd Edition, The John Hopkins University Press, Baltimore, 1996: 36-40.
[44] C. Xu, J. L. Prince. Snakes shapes and gradient vector flow[J]. IEEE Transactions on Image Processing, 2004, 7(3): 25-31.
[45] B. Takacs. Comparing face images using the modified Hausdorff distance[J]. Pattern Recognition, 1998: 1873-1881.
[46] R. Sanches-Reillo, C. Sanchez-Avila, A. Gonzalez-Marcos. Biometric Identification through Hand Geometry Measurements[J]. IEEE Transactions of Pattern Analysis and Machine Intelligence, 2000, 22(10): 42-53.
[47] Y. L. Lay. Hand shape recognition[J]. Optics and Laser Technology, 2000, 32(1):1–5.
[48]李长贵.线阵CCD用于实时动态测量技术[J].光学技术,1999,(2):5-8.
[49]彭启综.DSP与实时数字信号处理[M].成都:电子科技大学出版社,1995:2-478.
[50]江思敏,刘畅.TMS320C6000 DSP应用开发教程[M].北京:机械工业出版社,2004:153-196.
[51]王庆有.CCD应用技术[M].天津:天津大学出版社,2000:173-249.