基于非接触式掌纹特征的加解密算法研究
|
摘要
在信息时代里,信息安全已经变得越来越重要,密码学是保障信息安全的一种基本手段。传统的密码系统都是基于口令或密钥的,而这些口令或密钥容易受到字典攻击,很难记忆和容易被非法窃取,是因为口令或密钥和用户之间缺乏必然的联系,系统不能区分使用者的身份。为了解决这个问题,我们必须在加密的信息或密钥和用户之间建立某种对应关系,而基于生物特征的加解密系统可以克服传统密码系统的不足。基于掌纹特征的数据加解密技术是生物加解密技术中的一个重要的研究领域。
目前大部分掌纹加解密系统中的设备是接触式的,在使用时会让用户产生被侵犯感,且不同人频繁地接触设备,容易传播细菌和疾病,不容易被用户接受。本文使用非接触式掌纹采集设备可以解决这一问题。因此,基于非接触式掌纹特征的加解密算法研究具有重要的研究意义和广阔的应用前景。本文研究内容主要包括以下几个方面:
首先,鉴于本文采用的是非接触掌纹采集设备,这会给采集到的手掌带来一定的自由度,导致关键点定位不准确。针对关键点定位的准确性影响系统性能,提出了手指张开时的和手指并拢时的关键点定位算法,最后用掌纹识别技术进行实验,实验结果证明了这两种关键点定位算法的准确性和稳定性。
其次,提出了一种基于查找表的掌纹加解密算法。该算法直接使用掌纹模板对数据进行加解密,并不要求加密和解密阶段所使用的掌纹特征完全相同,只要求这二者足够相似就可以正确地完成数据加解密。使用查找表加解密算法进行数据加解密,并用RS纠错编解码技术进行数据恢复。该算法有效的消除了掌纹模板之间的模糊性且安全性高。
最后,提出了一种基于等概率量化方法的掌纹密钥生成算法。该算法可以从两个相似的掌纹特征中生成完全一样的掌纹密钥,并用该密钥对数据进行加解密,具有用户特异性。首先需要确定量化参数,然后用得到的量化参数量化特征矢量。该算法中量化概率的确定是基于最小错误率的,即找到最优量化区间使得FRR和FAR之和最小,再计算最优量化区间在全局特征分布概率密度函数上的概率,再等概率地量化全局特征的分布区域。实验结果证明该算法的有效性和通用性。
In the information age, information security has become increasingly important. The foundation of information security is cryptography. The traditional cryptographies are based on password or key which are vulnerable to dictionary attacks, difficult to remember and easy to be illegal stolen. It’s just because the lack of relation between the password or key and the genuine users, the system can not distinguish the users’identity. In order to overcome all those problems, we must establish a relationship between the encrypted information or keys and users. However, cryptographic system based on biometrics can overcome the shortages of traditional cryptographic system. The cryptographic technology based on palmprint is an important area of research.
At present the most devices used in palmprint cryptographic system are contact. When users use these devices, they have invasions of privacy. And it’s easy to spread bacteria and disease, because many people have touched the devices. In order to improve the user’s acceptance, a non-contact palmprint capture device is used. The research of the encryption and decryption algorithm based on non-contact palmprint feature has important significance and broad application prospects. This paper’s researching contents mainly include the following aspects:
Firstly, non-contact devices bring some degree of freedom, when capture the palmprint images. Cause the key points localization is difficult and inaccuracy. For the precision of cryptographic system influenced by the accuracy of key points localization, a localization method of key points based on non-contact palmprint images is presented in this paper, which performs on both finger-separated and finger-closed palmprint images. Finally do experiments by using the palmprint recognition technology. Experimental results show that the proposed method provides considerable performance in both localization accuracy and stability.
Secondly, a palmprint cryptography algorithm based on look-up table is presented. The algorithm directly uses palmprint template for data encryption and decryption, and does not require the palmprint features which are used in encryption phase and decryption phase are the same. Only requires that the features are sufficiently similar to correctly complete the data encryption and decryption. The look-up table method is used in encryption and decryption phase, and Reed-Solomon is used to recovery the data. This algorithm effectively eliminates the fuzziness of palmprint template and has high safety.
Thirdly, a key generation algorithm based on equal probability quantization method of palmprint feature is proposed. This algorithm can generate exactly the same keys used in encryption and decryption from two similar palmprint features and has user specific. Firstly, determine the quantization parameters, and then use them to quantize any biometric feature vector. The quantization probability is based on minimum error ratio. It also means finding the optimal quantization interval to minimize the sum of FRR and FAR. Then compute the probability in the optimal quantization interval from the global probability density function as the quantization step size. And use the step to equally divide the global distribution domain. The experiments results which are very encouraging demonstrate the effectiveness and commonality of our proposed algorithm.
目前大部分掌纹加解密系统中的设备是接触式的,在使用时会让用户产生被侵犯感,且不同人频繁地接触设备,容易传播细菌和疾病,不容易被用户接受。本文使用非接触式掌纹采集设备可以解决这一问题。因此,基于非接触式掌纹特征的加解密算法研究具有重要的研究意义和广阔的应用前景。本文研究内容主要包括以下几个方面:
首先,鉴于本文采用的是非接触掌纹采集设备,这会给采集到的手掌带来一定的自由度,导致关键点定位不准确。针对关键点定位的准确性影响系统性能,提出了手指张开时的和手指并拢时的关键点定位算法,最后用掌纹识别技术进行实验,实验结果证明了这两种关键点定位算法的准确性和稳定性。
其次,提出了一种基于查找表的掌纹加解密算法。该算法直接使用掌纹模板对数据进行加解密,并不要求加密和解密阶段所使用的掌纹特征完全相同,只要求这二者足够相似就可以正确地完成数据加解密。使用查找表加解密算法进行数据加解密,并用RS纠错编解码技术进行数据恢复。该算法有效的消除了掌纹模板之间的模糊性且安全性高。
最后,提出了一种基于等概率量化方法的掌纹密钥生成算法。该算法可以从两个相似的掌纹特征中生成完全一样的掌纹密钥,并用该密钥对数据进行加解密,具有用户特异性。首先需要确定量化参数,然后用得到的量化参数量化特征矢量。该算法中量化概率的确定是基于最小错误率的,即找到最优量化区间使得FRR和FAR之和最小,再计算最优量化区间在全局特征分布概率密度函数上的概率,再等概率地量化全局特征的分布区域。实验结果证明该算法的有效性和通用性。
In the information age, information security has become increasingly important. The foundation of information security is cryptography. The traditional cryptographies are based on password or key which are vulnerable to dictionary attacks, difficult to remember and easy to be illegal stolen. It’s just because the lack of relation between the password or key and the genuine users, the system can not distinguish the users’identity. In order to overcome all those problems, we must establish a relationship between the encrypted information or keys and users. However, cryptographic system based on biometrics can overcome the shortages of traditional cryptographic system. The cryptographic technology based on palmprint is an important area of research.
At present the most devices used in palmprint cryptographic system are contact. When users use these devices, they have invasions of privacy. And it’s easy to spread bacteria and disease, because many people have touched the devices. In order to improve the user’s acceptance, a non-contact palmprint capture device is used. The research of the encryption and decryption algorithm based on non-contact palmprint feature has important significance and broad application prospects. This paper’s researching contents mainly include the following aspects:
Firstly, non-contact devices bring some degree of freedom, when capture the palmprint images. Cause the key points localization is difficult and inaccuracy. For the precision of cryptographic system influenced by the accuracy of key points localization, a localization method of key points based on non-contact palmprint images is presented in this paper, which performs on both finger-separated and finger-closed palmprint images. Finally do experiments by using the palmprint recognition technology. Experimental results show that the proposed method provides considerable performance in both localization accuracy and stability.
Secondly, a palmprint cryptography algorithm based on look-up table is presented. The algorithm directly uses palmprint template for data encryption and decryption, and does not require the palmprint features which are used in encryption phase and decryption phase are the same. Only requires that the features are sufficiently similar to correctly complete the data encryption and decryption. The look-up table method is used in encryption and decryption phase, and Reed-Solomon is used to recovery the data. This algorithm effectively eliminates the fuzziness of palmprint template and has high safety.
Thirdly, a key generation algorithm based on equal probability quantization method of palmprint feature is proposed. This algorithm can generate exactly the same keys used in encryption and decryption from two similar palmprint features and has user specific. Firstly, determine the quantization parameters, and then use them to quantize any biometric feature vector. The quantization probability is based on minimum error ratio. It also means finding the optimal quantization interval to minimize the sum of FRR and FAR. Then compute the probability in the optimal quantization interval from the global probability density function as the quantization step size. And use the step to equally divide the global distribution domain. The experiments results which are very encouraging demonstrate the effectiveness and commonality of our proposed algorithm.
引文
[1] Uludag U, Pankanti S, Prabhakar S, et al. Biometric Cryptosystems: Issues and Challenges[C]. Proc. IEEE, 2004, 92(6): 948-960.
[2] Bodo. Method for Producing a Digital Signature with Aid of a Biometric Feature[J]. German Patent. 1994, NO. DE4243908A1.
[3] Linnartz J, Tuyls P. New Shielding Functions to Enhance Privacy and Prevent Misuse of Biometric Templates[C]. 4th International Conference on Audio and Video based Biometric Person Authentication, 2003: 393-402.
[4] Juels, Watenberg M. A Fuzzy Commitment Scheme[C]. 6th ACM Conference on Computer and Communications Security, 1999: 28-36.
[5] Juels, Sudan M. A Fuzzy Vault Scheme[C]. Proceedings of IEEE International Symposium on Information Theory, 2002: 408.
[6] Dodis Y, Reyzin L, Smith A. Fuzzy Extractors: How to Generate Strong Keys from Biometrics and Other Noisy Data[C]. Proc. International Conference on the Theory and Applications of Cryptographic Techniques (EUROCRYPT), 2004: 523-540.
[7] Soutar C, Roberge D, Stojanov S, et al. Biometric Encryption[J]. In R. K. Nichols, editor, ICSA Guide to Cryptography, McGraw Hill, 1999.
[8] Clancy T, Kiyavash N, Lin D. Secure Smart Card-Based Fingerprint Authentication[C]. In Proc. ACM SIGMM Multimedia, Biometrics Methods and Applications Workshop, 2003: 45-52.
[9] Uludag U. Secure Biometric System[J]. PhD Dissertation, Michigan State University, 2006.
[10] Davida G I, Frankel Y, Matt B J. On The Relation of Error Correction and Cryptography to An Offline Biometric based Identification Scheme[C]. In Proc. Workshop on Coding and Cryptography(WCC), 1999: 129-138.
[11] Hao F, Anderson R, Daugman J. Combining Crypto with Biometrics Effectively[C]. IEEE Transactions on Computer, 2006, 55(9): 1081–1088.
[12] Monrose F, Reiter M K, Wetzel S. Password Hardening Based on Keystroke Dynamics[C]. In Proc. 6th ACM Conference on Computer and Communications Security, 1999: 73-82.
[13] Monrose F, Reiter M, Li Q, et al. Cryptographic Key Generation from Voice[C]. In Proceedings of the 2001 IEEE Symposium on Security and Privacy, May 2001.
[14] Zhao Zeng, Paul A Watters. A Novel Face Hashing Method with Feature Fusion for Biometric Cryptosystems[C]. Proceedings of the Fourth European Conference on Universal Multi-service Networks(ECUMN'07), 2007.
[15] Santosa M F, Aguilara J F, Garciaa J O. Cryptographic Key Generation Using Handwritten Signature[J]. Biometric Technologies for Human Identification III, Proceedings of SPIE, 2006, 6202.
[16]李琼.生物识别模糊性与生物密钥算法研究[D].哈尔滨:哈尔滨工业大学,2005.
[17]林煌.指纹密钥算法研究[D].哈尔滨:哈尔滨工业大学,2006.
[18]顾震苏,李兴国,张涛.一种基于击键的生物密钥产生算法研究[J].微计算机信息(管控一体化),2007, 24(5-3): 26-27.
[19]周小燕,张清荣.基于模糊提取技术生物指纹的密钥提取的实现[J].焦作大学学报,2007, 4: 42-44.
[20]常郝.基于动态手写签名的生物特征密钥生成研究[D].合肥:合肥工业大学,2007.
[21] Wu X, Zhang D, Wang K. A Palmprint Cryptosystem[C]. International Conference on Biometrics, 2007: 1035-1042.
[22] Wu X, Zhang D, Wang K. A Cryptosystem Based on Palmprint Feature[C]. IEEE International Conference on Pattern Recognition, 2008: 1-4.
[23] Chang Y, Zhang W, Chen T. Biometrics-based Cryptographic Key Generation[C]. In IEEE Int. Conf on Multim. and Expo., 2004: 2203-2206.
[24] Wu X, Wang P, Wang K, et al. Biometric Cryptographic Key Generation Based on City Block Distance[C]. IEEE Workshop on Applications of Computer Vision (WACV), 2009: 1-5.
[25]邬向前,张大鹏,王宽全.掌纹识别技术[M].北京:科学出版社,2006.
[26] Zhang D, Kong W, You J. Online Palmprint Identification[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003, 25(9):1041–1050.
[27] Savi? T, Pave?i? N. Personal Recognition Based on An Image of the Palmar Surface of the Hand[C]. Pattern Recognition, 2007, 40(11): 3209-3224.
[28] Hu D, Feng G, Zhou Z. Two-Dimensional Locality Preserving Projections (2DLPP) with its Application to Palmprint Recognition[C]. Pattern Recognition,2007, 40(1): 339-342.
[29] Ekinci M, Aykut M. Gabor-based Kernel PCA for Palmprint Recognition[J]. Electronics Letters, 2007, 43(20): 1077-1079.
[30] Kong, Zhang D, Kamel M. Palmprint Identification Using Feature-Level Fusion[C]. Pattern Recognition, 2006, 39(3): 478-487.
[31]李强,裘正定.基于改进二维主成分分析的在线掌纹识别[J].电子学报,2005, 33(10):1886-1889.
[32] Kong, Zhang D. Competitive Coding Scheme for Palmprint Verification[C]. Proceedings of the 17th IEEE International Conference on Pattern Recognition, 2004, 1: 23-26.
[33] Sun Z, Tan T, Wang Y, et al. Ordinal Palmprint Representation for Personal Identification[C]. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005.
[34] Wu X, Zhang D, Wang K. Palm-line Extraction and Matching for Personal Authentication[C]. IEEE Transactions on Systems, Man, and Cybernetics, Part A. 2006, 36(5): 978-987.
[35] Huang D, Jia W, Zhang D. Palmprint Verification Based on Principal Lines[C]. Pattern Recognition, 2008, 41(4): 1316-1328.
[36] Jia W, Huang D, Zhang D. Palmprint Verification Based on Robust Line Orientation Code[C]. Pattern Recognition, 2008, 41(5): 1504-1513.
[37] Hennings-Yeomans P, Kumar B, Savvides M. Palmprint Classification Using Multiple Advanced Correlation Filters and Palm-Specific Segmentation[C]. IEEE Transactions on Information Forensics and Security, 2007, 2(3):613-622.
[38]戴青云,余英林.一种基于形态小波的在线掌纹的线特征提取方法[J].计算机学报,2003, 26(2): 234–239.
[39]李文新,夏胜雄.基于主线特征的双向匹配的掌纹识别新方法[J].计算机研究与发展,2004, 41(6): 996-1002.
[40] Wang Y H, Tan T N, Zhu Y. Face Identification Based on Singular Values Decomposition and Data Fusion[J]. Chinese J. Comput, 2000, 23(6).
[41] Negin M, Chmielewski T A, Salganicoff M G, et al. An Iris Biometric System for Public and Personal Use[J]. Computer., 2000, 33(2): 70-75.
[42] Ern L C, Sulong G. Fingerprint Classification Approaches an Overview[C]. Sixth International. Symposium on Signal Processing and its Applications, 2001, 1:347-350.
[43] Ramachandran P. A Comparative Study of Robust Linear Predictive Analysis Methods with Applications to Speaker Identification[C]. IEEE Trans. SAP, 1995, 3(2):117-125.
[44] Zhang D, Kong W K, You J, et al. Online Palmprint Identification[C]. IEEE Trans. Pattern Anal Mach Intell, 2003, 25:1041-1050.
[45] Wu X, Wang K, Zhang F, et al. Fusion of Phase and Orientation Information for Palmprint Authentication[C]. IEEE International Conference on Image Processing, 2005, 2: 29-32.
[46] Daugman J. High Confidence Visual Recognition of Persons by A Test of Statistical Independence[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(11): 1148–1161.
[47] Davida G, Frankel Y, Matt B. On Enabling Secure Applications Through Off-line Biometric Identification[C]. IEEE Symposium Privacy and Security, 1998: 148-157.
[48] Asker M, Raymond N J. Likelihood-ratio-based Biometric Verification[C]. IEEE Trans. Circuits Syst. Video Techn., 2004: 86-94.
[49] ORL ace database. http://www.cl.cam.ac.uk/Research/DTG/attarchive/facesatagl- ance.html.
[50] Zuo W, Liu L, Wang K, et al. Spatially Smooth Subspace Face Recognition Using LOG and DOG Penalties[J]. Lecture Notes on Computer Science, 2009: 439-448.
[51] Cui X, Wu X, Zhao Q, et al. A Contactless Hand Shape Identification System[C]. The 3rd IEEE International Conference on Advanced Computer Control (ICACC 2011), 2011: 561-565.
[2] Bodo. Method for Producing a Digital Signature with Aid of a Biometric Feature[J]. German Patent. 1994, NO. DE4243908A1.
[3] Linnartz J, Tuyls P. New Shielding Functions to Enhance Privacy and Prevent Misuse of Biometric Templates[C]. 4th International Conference on Audio and Video based Biometric Person Authentication, 2003: 393-402.
[4] Juels, Watenberg M. A Fuzzy Commitment Scheme[C]. 6th ACM Conference on Computer and Communications Security, 1999: 28-36.
[5] Juels, Sudan M. A Fuzzy Vault Scheme[C]. Proceedings of IEEE International Symposium on Information Theory, 2002: 408.
[6] Dodis Y, Reyzin L, Smith A. Fuzzy Extractors: How to Generate Strong Keys from Biometrics and Other Noisy Data[C]. Proc. International Conference on the Theory and Applications of Cryptographic Techniques (EUROCRYPT), 2004: 523-540.
[7] Soutar C, Roberge D, Stojanov S, et al. Biometric Encryption[J]. In R. K. Nichols, editor, ICSA Guide to Cryptography, McGraw Hill, 1999.
[8] Clancy T, Kiyavash N, Lin D. Secure Smart Card-Based Fingerprint Authentication[C]. In Proc. ACM SIGMM Multimedia, Biometrics Methods and Applications Workshop, 2003: 45-52.
[9] Uludag U. Secure Biometric System[J]. PhD Dissertation, Michigan State University, 2006.
[10] Davida G I, Frankel Y, Matt B J. On The Relation of Error Correction and Cryptography to An Offline Biometric based Identification Scheme[C]. In Proc. Workshop on Coding and Cryptography(WCC), 1999: 129-138.
[11] Hao F, Anderson R, Daugman J. Combining Crypto with Biometrics Effectively[C]. IEEE Transactions on Computer, 2006, 55(9): 1081–1088.
[12] Monrose F, Reiter M K, Wetzel S. Password Hardening Based on Keystroke Dynamics[C]. In Proc. 6th ACM Conference on Computer and Communications Security, 1999: 73-82.
[13] Monrose F, Reiter M, Li Q, et al. Cryptographic Key Generation from Voice[C]. In Proceedings of the 2001 IEEE Symposium on Security and Privacy, May 2001.
[14] Zhao Zeng, Paul A Watters. A Novel Face Hashing Method with Feature Fusion for Biometric Cryptosystems[C]. Proceedings of the Fourth European Conference on Universal Multi-service Networks(ECUMN'07), 2007.
[15] Santosa M F, Aguilara J F, Garciaa J O. Cryptographic Key Generation Using Handwritten Signature[J]. Biometric Technologies for Human Identification III, Proceedings of SPIE, 2006, 6202.
[16]李琼.生物识别模糊性与生物密钥算法研究[D].哈尔滨:哈尔滨工业大学,2005.
[17]林煌.指纹密钥算法研究[D].哈尔滨:哈尔滨工业大学,2006.
[18]顾震苏,李兴国,张涛.一种基于击键的生物密钥产生算法研究[J].微计算机信息(管控一体化),2007, 24(5-3): 26-27.
[19]周小燕,张清荣.基于模糊提取技术生物指纹的密钥提取的实现[J].焦作大学学报,2007, 4: 42-44.
[20]常郝.基于动态手写签名的生物特征密钥生成研究[D].合肥:合肥工业大学,2007.
[21] Wu X, Zhang D, Wang K. A Palmprint Cryptosystem[C]. International Conference on Biometrics, 2007: 1035-1042.
[22] Wu X, Zhang D, Wang K. A Cryptosystem Based on Palmprint Feature[C]. IEEE International Conference on Pattern Recognition, 2008: 1-4.
[23] Chang Y, Zhang W, Chen T. Biometrics-based Cryptographic Key Generation[C]. In IEEE Int. Conf on Multim. and Expo., 2004: 2203-2206.
[24] Wu X, Wang P, Wang K, et al. Biometric Cryptographic Key Generation Based on City Block Distance[C]. IEEE Workshop on Applications of Computer Vision (WACV), 2009: 1-5.
[25]邬向前,张大鹏,王宽全.掌纹识别技术[M].北京:科学出版社,2006.
[26] Zhang D, Kong W, You J. Online Palmprint Identification[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003, 25(9):1041–1050.
[27] Savi? T, Pave?i? N. Personal Recognition Based on An Image of the Palmar Surface of the Hand[C]. Pattern Recognition, 2007, 40(11): 3209-3224.
[28] Hu D, Feng G, Zhou Z. Two-Dimensional Locality Preserving Projections (2DLPP) with its Application to Palmprint Recognition[C]. Pattern Recognition,2007, 40(1): 339-342.
[29] Ekinci M, Aykut M. Gabor-based Kernel PCA for Palmprint Recognition[J]. Electronics Letters, 2007, 43(20): 1077-1079.
[30] Kong, Zhang D, Kamel M. Palmprint Identification Using Feature-Level Fusion[C]. Pattern Recognition, 2006, 39(3): 478-487.
[31]李强,裘正定.基于改进二维主成分分析的在线掌纹识别[J].电子学报,2005, 33(10):1886-1889.
[32] Kong, Zhang D. Competitive Coding Scheme for Palmprint Verification[C]. Proceedings of the 17th IEEE International Conference on Pattern Recognition, 2004, 1: 23-26.
[33] Sun Z, Tan T, Wang Y, et al. Ordinal Palmprint Representation for Personal Identification[C]. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005.
[34] Wu X, Zhang D, Wang K. Palm-line Extraction and Matching for Personal Authentication[C]. IEEE Transactions on Systems, Man, and Cybernetics, Part A. 2006, 36(5): 978-987.
[35] Huang D, Jia W, Zhang D. Palmprint Verification Based on Principal Lines[C]. Pattern Recognition, 2008, 41(4): 1316-1328.
[36] Jia W, Huang D, Zhang D. Palmprint Verification Based on Robust Line Orientation Code[C]. Pattern Recognition, 2008, 41(5): 1504-1513.
[37] Hennings-Yeomans P, Kumar B, Savvides M. Palmprint Classification Using Multiple Advanced Correlation Filters and Palm-Specific Segmentation[C]. IEEE Transactions on Information Forensics and Security, 2007, 2(3):613-622.
[38]戴青云,余英林.一种基于形态小波的在线掌纹的线特征提取方法[J].计算机学报,2003, 26(2): 234–239.
[39]李文新,夏胜雄.基于主线特征的双向匹配的掌纹识别新方法[J].计算机研究与发展,2004, 41(6): 996-1002.
[40] Wang Y H, Tan T N, Zhu Y. Face Identification Based on Singular Values Decomposition and Data Fusion[J]. Chinese J. Comput, 2000, 23(6).
[41] Negin M, Chmielewski T A, Salganicoff M G, et al. An Iris Biometric System for Public and Personal Use[J]. Computer., 2000, 33(2): 70-75.
[42] Ern L C, Sulong G. Fingerprint Classification Approaches an Overview[C]. Sixth International. Symposium on Signal Processing and its Applications, 2001, 1:347-350.
[43] Ramachandran P. A Comparative Study of Robust Linear Predictive Analysis Methods with Applications to Speaker Identification[C]. IEEE Trans. SAP, 1995, 3(2):117-125.
[44] Zhang D, Kong W K, You J, et al. Online Palmprint Identification[C]. IEEE Trans. Pattern Anal Mach Intell, 2003, 25:1041-1050.
[45] Wu X, Wang K, Zhang F, et al. Fusion of Phase and Orientation Information for Palmprint Authentication[C]. IEEE International Conference on Image Processing, 2005, 2: 29-32.
[46] Daugman J. High Confidence Visual Recognition of Persons by A Test of Statistical Independence[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(11): 1148–1161.
[47] Davida G, Frankel Y, Matt B. On Enabling Secure Applications Through Off-line Biometric Identification[C]. IEEE Symposium Privacy and Security, 1998: 148-157.
[48] Asker M, Raymond N J. Likelihood-ratio-based Biometric Verification[C]. IEEE Trans. Circuits Syst. Video Techn., 2004: 86-94.
[49] ORL ace database. http://www.cl.cam.ac.uk/Research/DTG/attarchive/facesatagl- ance.html.
[50] Zuo W, Liu L, Wang K, et al. Spatially Smooth Subspace Face Recognition Using LOG and DOG Penalties[J]. Lecture Notes on Computer Science, 2009: 439-448.
[51] Cui X, Wu X, Zhao Q, et al. A Contactless Hand Shape Identification System[C]. The 3rd IEEE International Conference on Advanced Computer Control (ICACC 2011), 2011: 561-565.