基于脑电波信号的身份识别技术
|
摘要
脑电波信号是一种能够反映大脑活动的生物电现象。在过去的研究中,由医疗设备采集的多电极脑电波已被证明可以作为生物特征模态用于个人身份识别。然而,设备昂贵以及数据采集操作复杂等因素,影响了这项技术在个人身份识别方面的实用化。本文针对便携式设备采集的脑电波信号在身份识别中的应用进行了深入的研究,评估了脑电信号作为独立的模态进行个人身份识别和作为防伪、防入侵的手段提高现有生物特征识别系统安全性的实际价值。
本文的主要工作包括：
1.提出了基于贝叶斯模型的单电极脑电波信号的自动去噪方法,实验结果表明该算法在去除肌电、眼动等噪声信号的同时,最大限度的保留了脑电波信号的特征；
2.选择Burg AR模型参数和Burg功率谱密度作为脑电波的特征,在包含40人的数据库上实现身份识别,正确率中值达到96.9%。实验结果证明了便携式设备采集的单电极脑电波信号可以作为独立的生物特征模态应用于个体身份的识别；
3.提出了基于假设检验的方法来确定饮食、生物钟等因素对脑电波信号的影响,同时通过实验证明,在个人身份识别的应用中,脑电波信号会受到其它因素(如饮食和生物钟等)的一些影响,可以通过训练样本的多样化,来获得较高的识别率；
4.实现了脑电信号和指纹的多模态身份识别的原型系统,对脑电信号能否与现有的生物特征互补,提供附加的识别信息,从而提高现有生物特征识别系统的精度和系统的安全性进行了评估。实验结果表明,融合脑电波和指纹的个人身份识别系统的性能比单独模态下有提高。
Electroencephalography (EEG) is the recording of electrical activity along the scalp produced by the firing of neurons within the brain. Several studies have been proposed using EEG signals from multiple electrodes as a biometric modality for personal identification. However, the conventional EEG recording systems for medical use are expensive and the recording process is complex and time-consuming. These restrictions hinder the applications of EEG-based personal identification system in practice. To evaluate the feasibility of using EEG as an independent biometric modality in personal identification and to performance to improve the security and privacy of the existing biometric systems, this paper studied several problems in the applications of EEG based identification based on the portable recording system.
The main tasks of this paper are as follows:
1. The Bayes model based automatic noise removing method is proposed for the single channel EEG. Experimental results show that our method can remove the Electromyography and Electrooculogram effectively while keeping the EEG signal characteristic furthest.
2. The Burg AR model parameters and Burg PSD are selected as features of EEG and the median identification accuracy is 96.9% on the database including 40 subjects. Experimental results show the feasibility of using EEG as an independent biometric modality in personal identification.
3. The statistical hypothesis test method is proposed to evaluate the effects of person's diet and circadian on the EEG-based personal identification system. Experimental results show that the EEG recording factors would decrease the accuracy of the performance to a certain extent. However, the identification performance can be improved through building more representative training sets.
4. To evaluate whether EEG can be a supplemental modality of other biometric modalities and the possibility to improve the security and accuracy of the biometric systems, this paper realized a prototype dual-biometric-modality identification system based on fingerprint and EEG. Experimental results show that the matching performance under the dual-modal biometric system is higher than the single-mode system.
本文的主要工作包括：
1.提出了基于贝叶斯模型的单电极脑电波信号的自动去噪方法,实验结果表明该算法在去除肌电、眼动等噪声信号的同时,最大限度的保留了脑电波信号的特征；
2.选择Burg AR模型参数和Burg功率谱密度作为脑电波的特征,在包含40人的数据库上实现身份识别,正确率中值达到96.9%。实验结果证明了便携式设备采集的单电极脑电波信号可以作为独立的生物特征模态应用于个体身份的识别；
3.提出了基于假设检验的方法来确定饮食、生物钟等因素对脑电波信号的影响,同时通过实验证明,在个人身份识别的应用中,脑电波信号会受到其它因素(如饮食和生物钟等)的一些影响,可以通过训练样本的多样化,来获得较高的识别率；
4.实现了脑电信号和指纹的多模态身份识别的原型系统,对脑电信号能否与现有的生物特征互补,提供附加的识别信息,从而提高现有生物特征识别系统的精度和系统的安全性进行了评估。实验结果表明,融合脑电波和指纹的个人身份识别系统的性能比单独模态下有提高。
Electroencephalography (EEG) is the recording of electrical activity along the scalp produced by the firing of neurons within the brain. Several studies have been proposed using EEG signals from multiple electrodes as a biometric modality for personal identification. However, the conventional EEG recording systems for medical use are expensive and the recording process is complex and time-consuming. These restrictions hinder the applications of EEG-based personal identification system in practice. To evaluate the feasibility of using EEG as an independent biometric modality in personal identification and to performance to improve the security and privacy of the existing biometric systems, this paper studied several problems in the applications of EEG based identification based on the portable recording system.
The main tasks of this paper are as follows:
1. The Bayes model based automatic noise removing method is proposed for the single channel EEG. Experimental results show that our method can remove the Electromyography and Electrooculogram effectively while keeping the EEG signal characteristic furthest.
2. The Burg AR model parameters and Burg PSD are selected as features of EEG and the median identification accuracy is 96.9% on the database including 40 subjects. Experimental results show the feasibility of using EEG as an independent biometric modality in personal identification.
3. The statistical hypothesis test method is proposed to evaluate the effects of person's diet and circadian on the EEG-based personal identification system. Experimental results show that the EEG recording factors would decrease the accuracy of the performance to a certain extent. However, the identification performance can be improved through building more representative training sets.
4. To evaluate whether EEG can be a supplemental modality of other biometric modalities and the possibility to improve the security and accuracy of the biometric systems, this paper realized a prototype dual-biometric-modality identification system based on fingerprint and EEG. Experimental results show that the matching performance under the dual-modal biometric system is higher than the single-mode system.
引文
[1]A. K. Jain, P. Flynn, A. A. Ross, Handbook of Biometrics, Springer, 2007.
[2]H. Yuliang, T. Jie, L. Liang, et al., Fingerprint matching based on global comprehensive similarity, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.28(6), 2006, pp.850-862.
[3]J. Daugman, Statistical richness of visual phase information:update on recognizing persons by iris patterns, International Journal of Computer Vision, vol.45(1),2001,pp.25-38.
[4]L. Chengjun, Capitalize on dimensionality increasing techniques for improving face recognition grand challenge performance, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.28(5),2006, pp.725-737.
[5]G. Wen, C. Bo, S. Shiguang, et al., The CAS-PEAL large-scale Chinese face database and baseline evaluations, IEEE Transactions on System, Man, and Cybernetics, Part A, vol.38(1),2008, pp.149-161.
[6]A. K. Jain, A. A. Ross, S. Pankanti, A prototype hand geometry-based verification system, International Proceedings on Audio & Video-Based Biometric Person Identification, 1999, pp.166-171.
[7]Z. Korotkaya, Biometric person authentication: odor, http://www.it.lut.fi/kurssit/03-04/010970000/seminars/Korotkaya.pdf, 2003.
[8]A. K. Jain, Biometric system security, http://biometrics.cse.msu.edu, 2006.
[9]K. W. Bowyer, K. I. Chang, P. Yan, et al., Multi-modal biometrics:an overview, Second Workshop on Multi-Modal User Authentication, 2006.
[10]http://vast.uccs.edu/～tboult/#announce
[11]Researchers Hack Faces in Biometric Facial Authentication Systems, http://www.darkreading.com/security/vulnerabilities/213901113/index.html.
[12]S. J. Lee, K. R. Park, J. Kim, Robust fake iris detection based on variation of the reflectance ratio between the iris and the sclera, Biometric Consortium Conference, Baltimore, 2006.
[13]T. Matsumoto, Artificial fingers and irises:importance of vulnerability analysis, The 7th International Biometrics Conference, London, 2004.
[14]Z. Piotrowski, P. Gajewski, Voice spoofing as an impersonation attack and the way of protection, Journal of Information Assurance and Security, 2007(2), pp.223-225.
[15]R. V. Yampolskiy, Mimicry attack on strategy-based behavioral biometric, Fifth International Conference on Information Technology: New Generations, 2008, pp.916-921.
[16]S. Sanei, J. A. Chambers, EEG Signal Processing, John Wiley & Sons Ltd, England, 2007.
[17]J. Thorpe, P. C. van Oorschot, A. Somayaji, Passthoughts:authenticating with our minds, Proceedings of the 2005 workshop on New security paradigms, 2005, pp.45-56.
[18]M. Poulos, M. Rangoussi, N. Alexandris, et al., Person identification based on parametric processing of the EEG, IEEE Proceedings on Electronics, Circuits, and Systems, vol.1,1999, pp.283-286.
[19]M. Poulos, M. Rangoussi, N. Alexandris, Neural network based person identification using EEG features, IEEE International Conference on Acoustics, Speech, and Signal Processing, 1999(2), pp.1117-1120.
[20]R. B. Paranjape, J. Mahovsky, L. Benedicenti, et al., The electroencephalogram as a biometric, Proceedings of Canadian on Elect.& Comp. Eng., vol.2,2001, pp.1363-1366.
[21]C. R. Hema, M. P. Paulraj, K. Harkirenjit, Brain signatures:a modality for biometric authentication, International Conference on Electronic Design, 2008, pp.1-4.
[22]C Miyamoto, S Baba, I. Nakanishi, Biometric person authentication using new spectral features of electroencephalogram (EEG), International Symposium on Intelligent Signal Processing and Communication Systems,2008, pp.1-4.
[23]R. Palaniappan, Electroencephalogram signals from imagined activities:a novel biometric identifier for a small population, Intelligent Data Engineering and Automated Learning, Lecture Notes in Computer Science, vol.4224, 2006, pp.604-611.
[24]R. Palaniappan, Two-stage biometric authentication method using thought activity brain waves, International Journal of Neural Systems, vol.18(1),2008, pp.59-66.
[25]R. Palaniappan, D. P. Mandic, Biometrics from brain electrical activity: a machine learning approach, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.29(4), 2007, pp.738-742.
[26]S. Marcel, J. R. Millan, Person authentication using brainwaves (EEG) and maximum a posteriori modal adaptation, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.29(4), 2007, pp. 743-748.
[27]S. Shiliang, Multitask learning for EEG-based biometrics, 19th International Conference on Pattern Recognition, 2008, pp.1-4.
[28]H. Chen, L. Xudong, W. Jane, Hashing the mAR coefficients from EEG data for person authentication, IEEE International Conference on Acoustics, Speech and Signal Processing, 2009. pp.1445-1448.
[29]A. Yazdani, A. Roodaki, S. H. Rezatofighi, et al., Fisher linear discriminant based person identification using visual evoked potentials,9th International Conference on Signal Processing, 2008, pp.1677-1680.
[30]J. G. Snodgrass, M. Vanderwart, A standardized set of 260 pictures:norms for name agreement, image agreement, familarity, and visual complexity, J. Exp. Psychol. Hum. Learn, vol.6(2), 1980, pp.174-215.
[31]http://www.neurosky.com/
[32]http://en.wikipedia.org/wiki/Electroencephalography
[33]A. Hyvarinen, J. Karhunen, E. Oja, Independent Component Analysis, John Wiley & Sons Ltd, 2001.
[34]T. P. Jung, S. Makeig, C. Humphries, et al., Removing electroencephalographic artifacts by blind source separation, Psychophysiology, vol.37(2), 2000, pp.163-178.
[35]T. P. Jung, S. Makeig, M. Westerfield, et al., Removal of eye activity artifacts from visual event-related potentials in normal and clinical subjects, Clinical Neurophysiology, vol.111(10), 2000, pp.1745-1758.
[36]I. Nakanishi, S. Baba, C. Miyamoto, EEG Based Biometric Authentication Using New Spectral Features, International Symposium on Intelligent Signal Processing and Communication Systems, 2009, pp.651-654.
[37]L. J. Chung, T. S. Desney, Using a low-cost electroencephalograph for task classification in HCI research, Proceedings of the ACM symposium on User interface software and technology, 2006.
[38]S. Fei, X. Liwen, C. Anni, et al., EEG-based personal identification: from proof-of-concept to a practical system, 20th International Conference on Pattern Recognition, 2010, pp.3728-3731.
[39]边肇祺,张学工,等,模式识别,第二版,清华大学出版社,2000.
[40]R. O. Duda, P. E. Hart, D. G Stork,模式分类,第二版,机械工业出版社,中信出版社,2003,68-72页.
[41]V. Abootalebi, M. H. Moradi, M. A. Khalilzadeh, A new approach for EEG feature extraction in P300-based lie detection, Computer Methods and Programs in Biomedicine, vol.94(1),2009, pp.48-57.
[42]R. Palaniappan, Method of identifying individuals using VEP signals and neural network, IEE Proceedings-Science, Measurement and Technology, vol.151(1), 2004, pp.16-20.
[43]何子述,夏威,等,现代数字信号处理及其应用,清华大学出版社,2009,,68-94页.
[44]张贤达,现代信号处理,清华大学出版社,Springer,2002,65-112页.
[45]H. Monson, Statistical Digital Signal Processing and Modeling, John Wiley & Sons Ltd,1996.
[46]S. M. Kay, Modern Spectral Estimation: Theory and Application, Englewood Cliffs, NJ:Prentice Hall, 1988, pp.228-230.
[47]P. D. Welch, The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short modified periodograms, IEEE Trans. Audio Electroacoustics, vol.15(6),1967, pp.70-73.
[48]A. Subasi, M. I. Gursoy, EEG signal classification using PCA, ICA, LDA and support vector machines, Expert Systems with Applications, 2010, doi:10.1016/j.eswa.2010.06.065.
[49]H. Chen, W. Jane, An independent component analysis (ICA) based approach for EEG person authentication, 3rd International Conference on Bioinformatics and Biomedical Engineering, 2009, pp.1-4.
[50]http://en.wikipedia.org/wiki/Statistical_hypothesis_testing
[51]http://en.wikipedia.org/wiki/Student's_t-test.
[52]赵德群,指纹图像特征提取及匹配算法研究,北京邮电大学博士论文,2007.
[53]李弼程,信息融合技术及其应用,国防工业出版社,2010.
[2]H. Yuliang, T. Jie, L. Liang, et al., Fingerprint matching based on global comprehensive similarity, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.28(6), 2006, pp.850-862.
[3]J. Daugman, Statistical richness of visual phase information:update on recognizing persons by iris patterns, International Journal of Computer Vision, vol.45(1),2001,pp.25-38.
[4]L. Chengjun, Capitalize on dimensionality increasing techniques for improving face recognition grand challenge performance, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.28(5),2006, pp.725-737.
[5]G. Wen, C. Bo, S. Shiguang, et al., The CAS-PEAL large-scale Chinese face database and baseline evaluations, IEEE Transactions on System, Man, and Cybernetics, Part A, vol.38(1),2008, pp.149-161.
[6]A. K. Jain, A. A. Ross, S. Pankanti, A prototype hand geometry-based verification system, International Proceedings on Audio & Video-Based Biometric Person Identification, 1999, pp.166-171.
[7]Z. Korotkaya, Biometric person authentication: odor, http://www.it.lut.fi/kurssit/03-04/010970000/seminars/Korotkaya.pdf, 2003.
[8]A. K. Jain, Biometric system security, http://biometrics.cse.msu.edu, 2006.
[9]K. W. Bowyer, K. I. Chang, P. Yan, et al., Multi-modal biometrics:an overview, Second Workshop on Multi-Modal User Authentication, 2006.
[10]http://vast.uccs.edu/～tboult/#announce
[11]Researchers Hack Faces in Biometric Facial Authentication Systems, http://www.darkreading.com/security/vulnerabilities/213901113/index.html.
[12]S. J. Lee, K. R. Park, J. Kim, Robust fake iris detection based on variation of the reflectance ratio between the iris and the sclera, Biometric Consortium Conference, Baltimore, 2006.
[13]T. Matsumoto, Artificial fingers and irises:importance of vulnerability analysis, The 7th International Biometrics Conference, London, 2004.
[14]Z. Piotrowski, P. Gajewski, Voice spoofing as an impersonation attack and the way of protection, Journal of Information Assurance and Security, 2007(2), pp.223-225.
[15]R. V. Yampolskiy, Mimicry attack on strategy-based behavioral biometric, Fifth International Conference on Information Technology: New Generations, 2008, pp.916-921.
[16]S. Sanei, J. A. Chambers, EEG Signal Processing, John Wiley & Sons Ltd, England, 2007.
[17]J. Thorpe, P. C. van Oorschot, A. Somayaji, Passthoughts:authenticating with our minds, Proceedings of the 2005 workshop on New security paradigms, 2005, pp.45-56.
[18]M. Poulos, M. Rangoussi, N. Alexandris, et al., Person identification based on parametric processing of the EEG, IEEE Proceedings on Electronics, Circuits, and Systems, vol.1,1999, pp.283-286.
[19]M. Poulos, M. Rangoussi, N. Alexandris, Neural network based person identification using EEG features, IEEE International Conference on Acoustics, Speech, and Signal Processing, 1999(2), pp.1117-1120.
[20]R. B. Paranjape, J. Mahovsky, L. Benedicenti, et al., The electroencephalogram as a biometric, Proceedings of Canadian on Elect.& Comp. Eng., vol.2,2001, pp.1363-1366.
[21]C. R. Hema, M. P. Paulraj, K. Harkirenjit, Brain signatures:a modality for biometric authentication, International Conference on Electronic Design, 2008, pp.1-4.
[22]C Miyamoto, S Baba, I. Nakanishi, Biometric person authentication using new spectral features of electroencephalogram (EEG), International Symposium on Intelligent Signal Processing and Communication Systems,2008, pp.1-4.
[23]R. Palaniappan, Electroencephalogram signals from imagined activities:a novel biometric identifier for a small population, Intelligent Data Engineering and Automated Learning, Lecture Notes in Computer Science, vol.4224, 2006, pp.604-611.
[24]R. Palaniappan, Two-stage biometric authentication method using thought activity brain waves, International Journal of Neural Systems, vol.18(1),2008, pp.59-66.
[25]R. Palaniappan, D. P. Mandic, Biometrics from brain electrical activity: a machine learning approach, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.29(4), 2007, pp.738-742.
[26]S. Marcel, J. R. Millan, Person authentication using brainwaves (EEG) and maximum a posteriori modal adaptation, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.29(4), 2007, pp. 743-748.
[27]S. Shiliang, Multitask learning for EEG-based biometrics, 19th International Conference on Pattern Recognition, 2008, pp.1-4.
[28]H. Chen, L. Xudong, W. Jane, Hashing the mAR coefficients from EEG data for person authentication, IEEE International Conference on Acoustics, Speech and Signal Processing, 2009. pp.1445-1448.
[29]A. Yazdani, A. Roodaki, S. H. Rezatofighi, et al., Fisher linear discriminant based person identification using visual evoked potentials,9th International Conference on Signal Processing, 2008, pp.1677-1680.
[30]J. G. Snodgrass, M. Vanderwart, A standardized set of 260 pictures:norms for name agreement, image agreement, familarity, and visual complexity, J. Exp. Psychol. Hum. Learn, vol.6(2), 1980, pp.174-215.
[31]http://www.neurosky.com/
[32]http://en.wikipedia.org/wiki/Electroencephalography
[33]A. Hyvarinen, J. Karhunen, E. Oja, Independent Component Analysis, John Wiley & Sons Ltd, 2001.
[34]T. P. Jung, S. Makeig, C. Humphries, et al., Removing electroencephalographic artifacts by blind source separation, Psychophysiology, vol.37(2), 2000, pp.163-178.
[35]T. P. Jung, S. Makeig, M. Westerfield, et al., Removal of eye activity artifacts from visual event-related potentials in normal and clinical subjects, Clinical Neurophysiology, vol.111(10), 2000, pp.1745-1758.
[36]I. Nakanishi, S. Baba, C. Miyamoto, EEG Based Biometric Authentication Using New Spectral Features, International Symposium on Intelligent Signal Processing and Communication Systems, 2009, pp.651-654.
[37]L. J. Chung, T. S. Desney, Using a low-cost electroencephalograph for task classification in HCI research, Proceedings of the ACM symposium on User interface software and technology, 2006.
[38]S. Fei, X. Liwen, C. Anni, et al., EEG-based personal identification: from proof-of-concept to a practical system, 20th International Conference on Pattern Recognition, 2010, pp.3728-3731.
[39]边肇祺,张学工,等,模式识别,第二版,清华大学出版社,2000.
[40]R. O. Duda, P. E. Hart, D. G Stork,模式分类,第二版,机械工业出版社,中信出版社,2003,68-72页.
[41]V. Abootalebi, M. H. Moradi, M. A. Khalilzadeh, A new approach for EEG feature extraction in P300-based lie detection, Computer Methods and Programs in Biomedicine, vol.94(1),2009, pp.48-57.
[42]R. Palaniappan, Method of identifying individuals using VEP signals and neural network, IEE Proceedings-Science, Measurement and Technology, vol.151(1), 2004, pp.16-20.
[43]何子述,夏威,等,现代数字信号处理及其应用,清华大学出版社,2009,,68-94页.
[44]张贤达,现代信号处理,清华大学出版社,Springer,2002,65-112页.
[45]H. Monson, Statistical Digital Signal Processing and Modeling, John Wiley & Sons Ltd,1996.
[46]S. M. Kay, Modern Spectral Estimation: Theory and Application, Englewood Cliffs, NJ:Prentice Hall, 1988, pp.228-230.
[47]P. D. Welch, The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short modified periodograms, IEEE Trans. Audio Electroacoustics, vol.15(6),1967, pp.70-73.
[48]A. Subasi, M. I. Gursoy, EEG signal classification using PCA, ICA, LDA and support vector machines, Expert Systems with Applications, 2010, doi:10.1016/j.eswa.2010.06.065.
[49]H. Chen, W. Jane, An independent component analysis (ICA) based approach for EEG person authentication, 3rd International Conference on Bioinformatics and Biomedical Engineering, 2009, pp.1-4.
[50]http://en.wikipedia.org/wiki/Statistical_hypothesis_testing
[51]http://en.wikipedia.org/wiki/Student's_t-test.
[52]赵德群,指纹图像特征提取及匹配算法研究,北京邮电大学博士论文,2007.
[53]李弼程,信息融合技术及其应用,国防工业出版社,2010.