高分辨距离像雷达自动目标识别研究
|
摘要
现代高分辨雷达的兴起为目标识别提供了新的途径。高分辨距离像反映了目标沿雷达径向的几何结构分布,较之于二维或三维成像,不仅获取要容易得多,而且避免了成像过程中复杂的运动补偿问题。因此,近年来高分辨雷达目标识别受到了业界的广泛关注。
本文在前人工作的基础上,着重对高分辨距离像雷达目标识别系统中特征提取与分类识别两个环节作了较深入的研究,并提出了一些创新的算法。这些算法在多组仿真与实测目标距离像数据的基础上进行了验证。归纳起来,本文的主要内容包括以下几个方面:
1.结合扰动法和零空间法,分别提出了基于QR分解的线性辨别分析和直接线性辨别分析雷达目标距离像识别方法,并利用核机器学习理论分别对其进行了非线性推广。实验结果表明,基于QR分解的辨别分析在实时性能上具有明显的优势,而直接辨别分析则具有良好的识别性能。
2.针对传统Gram-Schmidt正交化算法敏感于舍入误差的不足,首先提出了核修正Gram- Schmidt正交化算法,然后以此为基础发展了批处理式和类增量式两种核辨别分析雷达目标距离像识别方法。新方法充分利用了类内散布矩阵最具辨别力的零空间信息,具有良好的识别性能。尤其类增量式的核辨别分析在有新目标数据嵌入训练样本集时可以动态刷新特征矢量,有效地避免了将所有目标数据同时调入内存,造成计算负担过重的问题,具有明显的实时性能优势。
3.在模式识别理论中,特征提取的一般原则是希望所提取的目标特征之间统计相关性越小越好,最好是不相关的。依据这一理论,提出了一种基于核不相关辨别分析的雷达目标距离像识别框架,其不相关最优辨别矢量集可以通过联合对角化或广义奇异值分解方式求解。由于去除了模式样本特征之间的冗余信息,新方法体现了良好的识别性能。
4.针对经典辨别分析中可能存在的矩阵奇异问题,首先依据Fisher准则导出了距离像总散布矩阵的零空间中不含有有用辨别信息的结论。利用这一结论,可以对各散布矩阵进行预降维,以减小后续运算的计算复杂度。然后从全局角度出发,提出了一种双辨别子空间雷达目标距离像识别方法。该方法充分利用了类内散布矩阵零空间和非零空间中所包含的有用辨别信息,获得了良好的识别性能。
5.在经典最近特征线和最近特征平面分类器的基础上,利用核机器学习理论分别将其推广为核非线性分类器,使两者无需经过特征提取即可以直接对原始距离像样本进行分类。同时,针对这些分类器在大数据样本量与高维数时计算量大,且有可能失效的问题,基于局部最近邻准则提出了改进的分类方法,使其在保持较高识别率的同时,显著提高了分类的实时性能。
The increasing availability of high resolution range (HRR) radars provides a new way for radar target recognition. High resolution range profile (HRRP) shows the target's scatterers distribution along the radar line-of-sight, which contains potentially discriminative information about the target geometry. Furthermore, the HRRP can be easily captured and avoids the complex motion compensation processing, relative to two-dimensional or three-dimensional imagery. Therefore, HRR radar target recognition has received extensive attention from the radar technique community in recent years.
Based on the previous work, this dissertation is focused on the feature extraction and classification of a radar target recognition system using HRRP. Some new methods are presented, and all of them are evaluated on both simulated and measured data of aircrafts.
The main content is summarized as follows:
1. According to the perturbation theory and null-space method, two feature extraction methods for radar HRRP recognition are proposed respectively. One is QR decomposition based linear discriminant analysis (LDA), the other is direct LDA. Meanwhile, both methods are generalized to nonlinear versions via kernel trick. The experimental comparisons show that QR decomposition based methods have great advantage in terms of real-time performance, while another two achieve excellent recognition performance.
2. The classical Gram-Schmidt (GS) orthogonalization procedure is very sensitive to round-off-errors. Thereby, a modified GS orthogonalization procedure using kernel function operator (KMGS) is first proposed. Then two nonlinear algorithms, batch and class-incremental kernel discriminant analysis (KDA), are put forward for radar HRRP recognition. Compared with other kernel-based methods, batch KDA and class-incremental KDA both achieve good recognition performance for making use of the significant discriminative information in the null space of within-class scatter matrix. Moreover, class-incremental KDA introduces an incremental approach to update the discriminant vectors when new target data sets are inserted into the training set, which is very desirable for designing a dynamic recognition system. Therefore, it has apparent advantage in real-time performance.
3. In pattern analysis, the common principle of feature extraction is desirable to extract feature vectors with uncorrelated attributes. Motivated by this principle, a new formulation for KDA is proposed for radar HRRP recognition, which can solve the uncorrelated discriminant vectors by joint diagnonalization and GSVD respectively. The methods both achieve good recognition performance for removing the redundancy among feature vectors extracted.
4. It is well known that classical Fisher discriminant analysis algorithms suffer from singularity problem and lose some significant discriminative information. To address this problem, one conclusion that there exists no useful discriminative information in the null space of the population scatter matrix is first derived, which can be used to reduce the dimensionality of original scatter matrices as well as the computation complexity of the following operation. Then a double discriminant subspaces algorithm for radar HRRP recognition is proposed. The new method considers the separability from a global viewpoint to some extent, which can make full use of the discriminative information in both null space and non-null space of within-class scatter matrix. Therefore, it makes the new method a more powerful discriminator.
5. Kernel nonlinear classifiers from classical nearest feature line and nearest feature plane are proposed for radar HRRP classification, which can directly classify original range profiles and need no feature extraction beforehand. Meanwhile, these classifiers are modified based on locally nearest neighborhood rule. Compared with those original ones, the modified classifiers achieve competitive performance and take much lower computation cost, while the probability of failure is reduced to some extent.
本文在前人工作的基础上,着重对高分辨距离像雷达目标识别系统中特征提取与分类识别两个环节作了较深入的研究,并提出了一些创新的算法。这些算法在多组仿真与实测目标距离像数据的基础上进行了验证。归纳起来,本文的主要内容包括以下几个方面:
1.结合扰动法和零空间法,分别提出了基于QR分解的线性辨别分析和直接线性辨别分析雷达目标距离像识别方法,并利用核机器学习理论分别对其进行了非线性推广。实验结果表明,基于QR分解的辨别分析在实时性能上具有明显的优势,而直接辨别分析则具有良好的识别性能。
2.针对传统Gram-Schmidt正交化算法敏感于舍入误差的不足,首先提出了核修正Gram- Schmidt正交化算法,然后以此为基础发展了批处理式和类增量式两种核辨别分析雷达目标距离像识别方法。新方法充分利用了类内散布矩阵最具辨别力的零空间信息,具有良好的识别性能。尤其类增量式的核辨别分析在有新目标数据嵌入训练样本集时可以动态刷新特征矢量,有效地避免了将所有目标数据同时调入内存,造成计算负担过重的问题,具有明显的实时性能优势。
3.在模式识别理论中,特征提取的一般原则是希望所提取的目标特征之间统计相关性越小越好,最好是不相关的。依据这一理论,提出了一种基于核不相关辨别分析的雷达目标距离像识别框架,其不相关最优辨别矢量集可以通过联合对角化或广义奇异值分解方式求解。由于去除了模式样本特征之间的冗余信息,新方法体现了良好的识别性能。
4.针对经典辨别分析中可能存在的矩阵奇异问题,首先依据Fisher准则导出了距离像总散布矩阵的零空间中不含有有用辨别信息的结论。利用这一结论,可以对各散布矩阵进行预降维,以减小后续运算的计算复杂度。然后从全局角度出发,提出了一种双辨别子空间雷达目标距离像识别方法。该方法充分利用了类内散布矩阵零空间和非零空间中所包含的有用辨别信息,获得了良好的识别性能。
5.在经典最近特征线和最近特征平面分类器的基础上,利用核机器学习理论分别将其推广为核非线性分类器,使两者无需经过特征提取即可以直接对原始距离像样本进行分类。同时,针对这些分类器在大数据样本量与高维数时计算量大,且有可能失效的问题,基于局部最近邻准则提出了改进的分类方法,使其在保持较高识别率的同时,显著提高了分类的实时性能。
The increasing availability of high resolution range (HRR) radars provides a new way for radar target recognition. High resolution range profile (HRRP) shows the target's scatterers distribution along the radar line-of-sight, which contains potentially discriminative information about the target geometry. Furthermore, the HRRP can be easily captured and avoids the complex motion compensation processing, relative to two-dimensional or three-dimensional imagery. Therefore, HRR radar target recognition has received extensive attention from the radar technique community in recent years.
Based on the previous work, this dissertation is focused on the feature extraction and classification of a radar target recognition system using HRRP. Some new methods are presented, and all of them are evaluated on both simulated and measured data of aircrafts.
The main content is summarized as follows:
1. According to the perturbation theory and null-space method, two feature extraction methods for radar HRRP recognition are proposed respectively. One is QR decomposition based linear discriminant analysis (LDA), the other is direct LDA. Meanwhile, both methods are generalized to nonlinear versions via kernel trick. The experimental comparisons show that QR decomposition based methods have great advantage in terms of real-time performance, while another two achieve excellent recognition performance.
2. The classical Gram-Schmidt (GS) orthogonalization procedure is very sensitive to round-off-errors. Thereby, a modified GS orthogonalization procedure using kernel function operator (KMGS) is first proposed. Then two nonlinear algorithms, batch and class-incremental kernel discriminant analysis (KDA), are put forward for radar HRRP recognition. Compared with other kernel-based methods, batch KDA and class-incremental KDA both achieve good recognition performance for making use of the significant discriminative information in the null space of within-class scatter matrix. Moreover, class-incremental KDA introduces an incremental approach to update the discriminant vectors when new target data sets are inserted into the training set, which is very desirable for designing a dynamic recognition system. Therefore, it has apparent advantage in real-time performance.
3. In pattern analysis, the common principle of feature extraction is desirable to extract feature vectors with uncorrelated attributes. Motivated by this principle, a new formulation for KDA is proposed for radar HRRP recognition, which can solve the uncorrelated discriminant vectors by joint diagnonalization and GSVD respectively. The methods both achieve good recognition performance for removing the redundancy among feature vectors extracted.
4. It is well known that classical Fisher discriminant analysis algorithms suffer from singularity problem and lose some significant discriminative information. To address this problem, one conclusion that there exists no useful discriminative information in the null space of the population scatter matrix is first derived, which can be used to reduce the dimensionality of original scatter matrices as well as the computation complexity of the following operation. Then a double discriminant subspaces algorithm for radar HRRP recognition is proposed. The new method considers the separability from a global viewpoint to some extent, which can make full use of the discriminative information in both null space and non-null space of within-class scatter matrix. Therefore, it makes the new method a more powerful discriminator.
5. Kernel nonlinear classifiers from classical nearest feature line and nearest feature plane are proposed for radar HRRP classification, which can directly classify original range profiles and need no feature extraction beforehand. Meanwhile, these classifiers are modified based on locally nearest neighborhood rule. Compared with those original ones, the modified classifiers achieve competitive performance and take much lower computation cost, while the probability of failure is reduced to some extent.
引文
[1]黄培康,殷红成,许小剑.雷达目标特性.北京:电子工业出版社,2005,229-278
[2]Bhanu B.Automatic target recognition:State of the art survey.IEEE Trans.on AES,1986,22(4):364-379
[3]刘宏伟,杜兰,袁莉,等.雷达高分辨距离像目标识别研究进展.电子与信息学报,2005,27(8):1328-1334
[4]Smith C R,Goggana P M.Radar target recognition.IEEE Antennas and Propagation Magazine,1993,35(2):27-38
[5]孙文峰.雷达目标识别技术评述.雷达与对抗,2001,3:1-8
[6]郭桂蓉,庄钊文,陈曾平.电磁特征抽取与目标识别.长沙:国防科技大学出版社,1996,1-2
[7]边肇祺,张学工,等.模式识别(第二版).北京:清华大学出版社,2000,9-303
[8]Turk M A,Pentland A P.Face recognition using eigenfaces.Proceedings International Conference on Pattern Recognition,1991:596-591
[9]Yoshida M,Kamio T,Asai H.Neuro-based human-face recognition with 2-dimensional discrete Walsh transform.Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks(IJCNN'2000),2000,3:315-319
[10]Zwicke P E,Imrekiss J R.A new implementation of the Mellin transform and its application to radar classification of ships.IEEE Trans.on Pattern Analysis and Machine Intelligence,1983,5(2):256-264
[11]Strattan R D.Target identification from radar signatures.1978 IEEE Conference ASSP,1978:223-227
[12]Zyweck A,Bogner R E.Radar target classification of commercial aircraft.IEEE Trans.on AES,1996,32(2):598-606
[13]Swets D,Weng J.Using discriminant eigenfeatures for image retrieval.IEEE Trans.on PAMI,1996,18(8):831-836
[14]Vapnik N.The nature of statistical learning theory.New York:Springer Verlag,1995,1-188
[15]Barton D K.Sputink Ⅱ as observed by C band radar.IRE Nat.Conf.Rec.,1959,7(5):67-73
[16]Hynes H,Gardner R E.Doppler spectra of S band and X band signals.IEEE Trans.on AES,1967,3(6):356-365
[17]Fliss G G,Mensa D L.Instrumentation for RCS measurements of modulation spectra of aircraft blades.IEEE National Radar Conference,1986:12-13
[18]Bell M R,Grubbs R A.JEM modeling and measurement for radar target identification.IEEE Trans.on AES,1993,29(1):73-87
[19]Baum C E.On the singularity expansion method for solution of electromagnetic interaction problems.Air Force Weapons Lab.Interaction Notes 88,1971:1-25
[20]Pearson L W,Blaricum M J,Mittra R.A new method for radar target recognition based upon the singularity expansion method.Rec.IEEE Int.Radar Conf.,Arlington,VA,1975:452-457
[21]Blaricum M J,Mittra R.A technique for extracting the poles and residues of a system directly form its transient response.IEEE Trans.on AP,1975,23:777-781
[22]Jain V K,Sarkar T K,Weiner D D.Rational modeling by pencil of function method.IEEE Trans.on Acoustics,Speech,Signal Processing,1993,31(3):564-573
[23]Hua Y B,Sarkar T K.Generalized pencil-of-function method for extracting poles of an EM system from transient response.IEEE Trans.on AP,1989,37(2):229-234
[24]Drachman B,Rothwell E.A continuation method for identification of the natural frequencies of an object using a measured response.IEEE Trans.on AP,1985,33:445-450
[25]Kennaugh E M.The K-pulse concept.IEEE Trans.on AP,1983,29(3):327-331
[26]Chen K M.Radar wave synthesis methods:a new radar detection scheme.IEEE Trans.on AP,1981,29(4):553-565
[27]Chen K M.Ultra-wideband/Short-pulse radar for target identification and detection:laboratory study.Proceedings of IEEE 1995 Radar Conference,1995:450-455
[28]Rothwell E J,Nyquist K M,Chen K M.Radar target discrimination using the Extinctionpulse technique.IEEE Trans.on AP,1985,33(9):929-936
[29]Ilavarasan P.Performance of an automated radar target discrimination scheme using E pulses and S pulses.IEEE Trans.on AP,1993,41(5):582-588
[30]Rath M W.Survey of neural network technology for automatic target recognition.IEEE Trans.on NN,1990,1(1):28-43
[31]Giuli D.Polarization diversity in radars.Proceedings of IEEE,1986,74(2):245-269
[32]Zebker H A,Vanzyl J J.Imaging radar polarimetry:a review.Proceedings of IEEE,1991,79(11):1583-1606
[33]王晓丹,王积勤.雷达目标识别技术综述.现代雷达,2003,25(5):22-26
[34]Cameron W.Feature motivated polarization scattering matrix decomposition.IEEE Int.Radar Conf.,1990:549-557
[35]Chamberlain N F,Walton E K,Garber F D.Radar target identification of aircraft using polarization-diverse features.IEEE Trans.on AES,1991,27(1):58-66
[36]Steedly W M,Moses R L.High resolution exponential modeling of fully polarized radar returns.IEEE Trans.on AES,1991,27(3):459-468
[37]肖顺平,王雪松,郭桂蓉.基于极化谱的飞机目标识别.电子学报,1997,25(12):60-64
[38]王雪松,肖顺平,庄钊文.基于改进退火法按拟合参数估计的极化雷达目标识别.现代雷达,1997,19(2):6-11
[39]Tenoux T,Delisle G Y,Fournet P,et al.Analysis and interpretation of high resolution polarimetric SAR images.4e Colloque International sur le Radar,1994:358-363
[40]Meric S,Chassay G,Tenoux T,et al.Propagation prediction calculation used for SAR imaging urban area.Electronics Letters,1998,34(11):1147-1149
[41]刘晓峰.无线电摄像机目标识别研究[硕士学位论文].成都:电子科技大学,1996,1-6
[42]郭飚,陈曾平,庄钊文,等.基于高分辨率二维雷达图像的特征提取与目标识别.航天电子对抗,1998,2:19-25
[43]Novak L M,Owirka G J,Netishen C M.Radar target identification using spatial matched filters.Pattern Recognition,1994,27(4):607-617
[44]Novak L M,Owirka G J.Radar target identification using an eigen-image approach.IEEE Nat.Radar Conf,Atlanta,1994:129-131
[45]Martin N S.SAR systems resolution reviewed for target classification in knowledge-based environment.Proceedings of IEEE Electronic Technology Directions to the Year 2000,1995,5:177-183
[46]Pierce L E,Sarabandi I,Ulaby F T,et al.Knowledge-based classification of SAR images.IEEE IGARSS'93,1993,4:1611-1613
[47]Farhat N H.Microwave diversity imaging and automated target identification based models of neural networks.Proceedings of IEEE,1989,77(5):670-680
[48]Osman H,Blostein S D.SAR image processing using probabilistie winner-take-all learning and artificial neural networks.Proceedings of IEEE Int.Conf.on IP,1996,2:613-616
[49]Liao X J,Bao Z,Xing M D.On the sensitivity of high resolution range profiles and its reduction methods.IEEE International Radar Conf.,2000:310-315
[50]Smith C R,et al.Radar target identification.IEEE Antennas and Propagation Magazine,1993,35(2):27-38
[51]Wehner D R.High-resolution radar(2nd).685 Canton Street,Norwood,MA 02062,Artech House,INC.,1995,1-197
[52]Xing M D,Bao Z.The properties of range profile of aircraft.CIE International Conference on Radar Proceedings,Beijing,2001:1050-1054
[53]李廷军,姜文利,等.发展中的雷达目标识别.现代雷达,2000,22(6):1-5
[54] Seybold J S,Bishop S J.Three-dimensional ISAR imaging using a conventional high-range resolution radar.Proceedings of IEEE Nat.Radar Conf.,1996:309-314
[55]Bryant M L,Gostin L L,Soumekh M.Three-dimensional E-CSAR imaging of a T-72 tank and synthesis of its spotlight,stripmap and interferometric SAR reconstructions.Proceedings of IEEE Int.Conf.on IP,2001,3:628-631
[56]Yang R H,Pan Q,Cheng Y M.A new method for identify 3D aircraft targets.Computer Simulation,2006,23(6):82-84
[57]Li H J,Yang S H.Using range profiles as feature vectors to identify aerospace objects.IEEE Trans.on AP,1993,41(3):261-268
[58]Hudson S,Psaltis D.Correlation filters for aircraft identification from radar range profile.IEEE Trans.on AES,1993,29(3):741-746
[59]Rothwell E J,Chen K M,Nyquist D P,et al.A radar target discrimination scheme using the discrete wavelet transform for reduced data storage.IEEE Trans.on AP,1994,42(7):1033-1037
[60]Li Q,Rothwell E J,Chen K M,et al.Radar target discrmination shcemes using time-domain and frequency-domain methods for reduced data storage.IEEE Trans.on AP,1997,45(6):995-1000
[61]袁莉,刘宏伟,保铮.基于中心矩特征的雷达HRRP自动目标识别.电子学报,2004,32(12):2078-2081
[62]Zwicke P E.Ship classification using recursive structure identification and the Mellin transform.United Technology Res.CENT.,Rep.80,1981:192109
[63]郭桂蓉,郁文贤,胡步法.一种有效的舰船目标识别方法.系统工程与电子技术,1990,12(6):1-7
[64]郁文贤,郭桂蓉.ATR技术的研究现状和发展趋势.系统工程与电子技术,1994,16(6):25-30
[65]肖顺平,郭桂蓉,庄钊文,等.基于散射中心的目标建模与识别.系统工程与电子技术,1994,16(6):55-61
[66]He G H,Shah X M,Fen Z M,et al.Study of two methods in radar target recognition.Proceedings of IEEE Int.Radar Conf.,1996:674-678
[67]廖学军.基于高分辨距离像的雷达目标识别[博士学位论文].西安:西安电子科技大学,1999,1-6
[68]Jouny I,Garber F D,Moses R L.Radar target identification using the bispectrum:a comparative study.IEEE Trans.on AES,1995,31(1):69-77
[69]Chandran V,Elgar S L.Pattern recognition using invariants defined from higher order spectra one-dimensional inputs.IEEE Trans.on SP,1993,41(1):205-212
[70]Tugnait J K.Detection of non-Gaussian signals using integrated polyspectrum.IEEE Trans.on SP,1994,42(11):3137-3149
[71]Liao X J,Bao Z.Circularly integrated bispectra:novel shift invariant feature for highresolution radar target recognition.IEE Electronics Letters,1999,34(19):1879-1880
[72]Zhang X D,Shi Y,Bao Z.A new feature vector using selected bispectra for signal classification with application in radar target recognition.IEEE Trans.on SP,2001,49(9):1875-1885
[73]Kim K T,Seo D K,Kim H T.Efficient radar target recognition using the Music algorithm and invariant features.IEEE Trans.on AP,2002,50(3):325-337
[74]Carriere R,Moses R L.High resolution radar target modeling using a modified Prony estimator.IEEE Trans.on AP,1992,40(1):13-18
[75]Li J,Stoica P.Efficient mixed-spectrum estimation with application to feature extraction.IEEE Trans.on SP,1996,42(2):281-295
[76]李建平,严中洪,张万萍.基于小波分析的模式识别的几个问题.计算机科学,2001,28(5):110-112
[77]朱海,马颖.利用小波包提取雷达信号特征的方法研究.电子对抗,2002,5:33-36
[78]张静远,张冰,等.基于小波变换的特征提取方法分析.信号处理,2000,6:156-162
[79]田野,雷英杰,李军.基于小波变换的雷达信号特征提取方法.空军工程大学学报.2006,7(5):22-24
[80]马建华,刘宏伟,保铮.基于小波变换的雷达高分辨距离像识别.西安电子科技大学学报,2005,32(6):895-900
[81]Rothwell E J,Nyquist D P,Chen K M,et al.A radar target discrimination shceme using the discrete wavelet transform for reduced data storage.IEEE Trans.on AP,1994,42(7):1033-1037
[82]郭桂蓉.模糊模式识别理论及应用研究.中国科学基金,1991,3:15-18
[83]高新波,谢维信.模糊聚类理论发展及应用的研究进展.科学通报,1999,44(21):2241-2251
[84]肖怀铁,郭雷,付强,等.宽带多极化雷达目标模糊匹配识别方法.系统工程与电子技术,2005,27(5):770-773
[85]Liang M,Sun Z K,Liu J C.The second-order neural network for radar ship target recognition.Proceedings of IEEE Nat.AE Conf.,1992,1:270-274
[86]Kouba E T,Rogers S K,Ruck D W,et al.Recurrent neural networks for radar target identification.Proceedings of SPIE,1993,1965:256-265
[87]Stewart C,Lu Y C,Larson V.A neural clustering approach for high resolution radar target classification.Pattern Recognition,1994,27(4):503-513
[88]Lu Y C,Chang K C.A neural network approach for high resolution target classification.Proceedings of SPIE,1995,2484:558-566
[89]Zhao Q,Bao Z.Radar target recognition using a radial basis function neural network.Neural Networks,1996,9(4):709-720
[90]肖怀铁,付强,庄钊文,等.宽带毫米波雷达目标时延神经网络识别新方法.红外与毫米波学报,2001,20(6):459-463
[91]陈大庆,保铮.基于多层前向网络的雷达目标一维距离像识别.西安电子科技大学学报,1997,24(1):1-6
[92]Botha E C,et al.Feature based classification of aerospace radar targets using neural networks.Neural Networks,1996,9(1):129-142
[93]Shaw A K,Bhatngar V.Automatic target recognition using eigen-template.Proceedings of SPIE,1998,3370:448-459
[94]Shaw A K,Vashist R,et al.HRR-ATR using eigen-template with noisy observation in unknown target scenario.Proceedings of SPIE,2000:467-478
[95]刘本永.子空间法雷达目标一维距离像识别研究[博士学位论文].成都:电子科技大学,1999,1-95
[96]周代英.雷达目标一维距离像识别研究[博士学位论文].成都:电子科技大学,2001,1-92
[97]孟继成.雷达目标距离像识别研究[博士学位论文].成都:电子科技大学,2005,1-106
[98]Pei B N,Bao Z.Multi-aspect radar target recognition method based on scattering centers and HMMs Classifiers.IEEE Trans.on AES,2005,41(3):1067-1074
[99]Rabiner L R.A tutorial on hidden Markov models and selected application in speech recognition.Proceedings of IEEE,1989,77(2):257-286
[100]周德全.基于一维距离像的雷达目标识别研究[博士学位论文].南京:南京理工大学,1998,1-90
[101]陈江峰,裴炳南.一种基于HMM的雷达目标识别方法.郑州大学学报,2003,35(1):52-56
[102]Freidman N.Bayesian network classifiers.Machine Learning,1997,29(2-3):131-163
[103]Heckerman D.Bayesian networks for data mining.Data mining and knowledge discovery,1997,1:79-119
[104]Cortes C,Vapnik V.Support-vector networks.Machine Learning,1995,20(3):273-297
[105]毛京红,许小剑.高分辨力雷达目标识别研究.系统工程与电子技术,1994,16(10):11-16
[106]Serretta H,Inggs M R.Ship target recognition with the Mellin transform aided by neural networks.Proceedings of COMSIG,1998:203-208
[107]Mieras H.Optimal polarization of simple compound targets.IEEE Trans.on AP,1983,31(6):996-998
[108]Giuli D,Gheradelli M,Fossi M.Using polarization discriminants for target classification and identification.Proceedings of 1986 Inter.Conf.on Radar(CICR'86),China,1986:889-898
[109]Quach T,Farooq M.Investigation of a multiple passive sensor tracking algorithm.Proceedings of the 37~(th) Midwest Symposium on Circuits and Systems,1994,1:195-198
[110]Li H J,Lane R Y.Utilization of multiple polarization data for aerospace target identification.IEEE Trans.on AP,1995,43(12):1436-1440
[111]Jouny I,Kanapathipillai M.Neural network adaptive wavelet classification of radar targets.IEEE IGARSS'94,1994,4:1889-1891
[112]张小英,王宝发,刘铁军.基于PCA-LVQ的雷达目标一维距离像识别.系统工程与电子技术,2005,27(8):1373-1375
[113]何松华,郭桂蓉,庄钊文.雷达目标高分辨距离-极化结构成像方法研究.电子学报,1994,22(7):1-8
[114]Parmar N C,Codex M,Kokar M M.Target detection in fused X-band radar and IR images using the functional minimization approach to data association.Proceedings of IEEE Int.Symp.on Intelligent Control,1994:51-56
[115]姜文利,唐白玉,徐可斌,等.高频区雷达目标散射模型及其参数估计.电子学报,1998,26(3):70-74
[116]Altes R A.Sonar for generalized target description and its similarity to animal echolocation system.Journal of Acoustic.Soc.A.,1976,59:97-105
[117]Sch(o|¨)lkopf B,Smola A,M(u|¨)ller K R.Nolinear component analysis as a kernel eigenvalue problem.Neural Computation,1998,10(5):1299-1319
[118]Mika S,R(a|¨)tsch G,Weston J,et al.Fisher discriminant analysis with kernels.Proceedings of the IEEE International Workshop on Neural Networks for Signal Processing,USA,1999:41-48
[119]Baudat G,Anouar F.Generalized discriminant analysis using a kernel approach.Neural Computation,2000,12(10):2385-2404
[120]Raudys S,Duin R P W.On expected classification error of the fisher linear classifier with pseudo-inverse convariance matrix.Pattern Recognition Letters,1998,19(5-6):385-392
[121]Belhumeur P N,Hespanha J P,Kriegman D J.Eigenfaces vs.fisherfaces:recognition using class specific linear projection.PAMI,1999,19:711-720
[122]Hong Z Q,Yang J Y,et al.Optimal discriminant plane for a small number of samples and design method of classifier on the plane.Pattern Recognition,1991,24(4):317-324
[123]Chen L F,Mark Liao H Y,Lin J C,et al.A new LDA-based face recognition system which can solve the small sample size problem.Patter Recognition,2000,33:1713-1726
[124]Yu H,Yang J.A direct LDA algorithm for high-dimensional data with application to face recognition.Pattern Recognition,2001,34:2067-2070
[125]Lu J W,Plataniotis K N,Venetsanopoulos A N.Face recognition using kernel direct discriminant analysis algorithms.IEEE Trans.on Neural Networks,2003,14(1):117-126
[126]Zheng W M,Zou C R,Zhao L.Real-time face recognition using Gram-Schmidt orthogonalization for LDA.Proceedings of the 17~(th) International Conference on Pattern Recognition(ICPR'04),Cambridge UK,2004:403-406
[127]Fukunaga,K.Introduction to statistical pattern recognition.Orlando,FL:Academic Press,1990,1-592
[128]张贤达.矩阵分析与应用.北京:清华大学出版社,2004,47-52,229-244,367-380
[129]Wolf L,Shashua A.Learning over sets using kernel principal angles.Journal of Machine Learning Research,2003,4:913-931
[130]Rice J R.Experiments on Gram-Schmidt orthogonalization.Mathematics Computation,1966,20:325-328
[131]Bj(o|¨)rck A.Solving linear least squares problems using Gram-Schmidt orthogonalization.BIT,1967,7:1-21
[132]Jin Z,Yang J Y,Hu Z S,et al.Face recognition based on uncorrelated discriminant transformation.Pattern Recognition,2001,34(7):1405-1416
[133]Jin Z,yang J y,Tang Z M,et al.A theorem on uncorrelated optimal discriminant vectors.Pattern Recognition,2001,34(10):2041-2047
[134]金忠,杨静宇,陆建峰.一种具有统计不相关性的最优辨别矢量集.计算机学报,1999,22(10):1105-1108
[135]金忠,胡钟山,杨静宇,等.手写体数字有效鉴别特征的抽取和识别.计算机研究与发展,1999,36(12):1484-1489
[136]金忠.人脸图像特征制取与维数研究[博士学位论文].南京:南京理工大学,1999,1-85
[137]Ye J P,Janardan R,Li Q,et al.Feature extraction via generalized uncorrelated linear discriminant analysis.IEEE Trans.on Knowledge and Data Engineering,2006,18(10):1312-1322
[138]Howland P,Park H.Generalized discriminant analysis using the generalized singular value decomposition.IEEE Trans.on Pattern Analysis and Machine Intelligence,2004,26(8):995-1006
[139]Yang M H.Kernel eigenfaces vs.kernel fisherfaces:face recognition using kernel methods.Proceedings of the Fifth International Conference on Automatic Face and Gesture Recognition(FG 2002),Washington D.C.,2002:215-220
[140]Liu K,Yang J Y,et al.An efficient algorithm for Foley-Sammon optimal set of discriminant vectors by algebraic method.International Journal of Pattern Recognition and Artificial Intelligence,1992,6(5):817-829
[141]Kreyszig E.Introductory functional analysis with application.John Wiley & Sons,1978,1-704
[142]Cover T M,Hart P E.Nearest neighbor patter classification.IEEE Trans.on Information Theory,1967,13:21-27
[143]Li S Z,Lu J W.Face recognition using the nearest feature line method.IEEE Trans.on Neural Networks,1999,10(2):439-443
[144] Chien J T, Wu C C. Discriminant waveletfaces and nearest feature classifiers for face recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence,2002,24(12):1644- 1649
[145] Zheng W M, Zhao L, Zou C R. Locally nearest neighbor classifiers for pattern recognition. Pattern Recognition,2004,37(6): 1307-1309
[146] R Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding. Science,2000,290:2323-2326
[147] Liang Z Z, Shi P F. Uncorrelated discriminant analysis using a kernel method. Pattern Recognition,2005,38(2):307-310
[2]Bhanu B.Automatic target recognition:State of the art survey.IEEE Trans.on AES,1986,22(4):364-379
[3]刘宏伟,杜兰,袁莉,等.雷达高分辨距离像目标识别研究进展.电子与信息学报,2005,27(8):1328-1334
[4]Smith C R,Goggana P M.Radar target recognition.IEEE Antennas and Propagation Magazine,1993,35(2):27-38
[5]孙文峰.雷达目标识别技术评述.雷达与对抗,2001,3:1-8
[6]郭桂蓉,庄钊文,陈曾平.电磁特征抽取与目标识别.长沙:国防科技大学出版社,1996,1-2
[7]边肇祺,张学工,等.模式识别(第二版).北京:清华大学出版社,2000,9-303
[8]Turk M A,Pentland A P.Face recognition using eigenfaces.Proceedings International Conference on Pattern Recognition,1991:596-591
[9]Yoshida M,Kamio T,Asai H.Neuro-based human-face recognition with 2-dimensional discrete Walsh transform.Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks(IJCNN'2000),2000,3:315-319
[10]Zwicke P E,Imrekiss J R.A new implementation of the Mellin transform and its application to radar classification of ships.IEEE Trans.on Pattern Analysis and Machine Intelligence,1983,5(2):256-264
[11]Strattan R D.Target identification from radar signatures.1978 IEEE Conference ASSP,1978:223-227
[12]Zyweck A,Bogner R E.Radar target classification of commercial aircraft.IEEE Trans.on AES,1996,32(2):598-606
[13]Swets D,Weng J.Using discriminant eigenfeatures for image retrieval.IEEE Trans.on PAMI,1996,18(8):831-836
[14]Vapnik N.The nature of statistical learning theory.New York:Springer Verlag,1995,1-188
[15]Barton D K.Sputink Ⅱ as observed by C band radar.IRE Nat.Conf.Rec.,1959,7(5):67-73
[16]Hynes H,Gardner R E.Doppler spectra of S band and X band signals.IEEE Trans.on AES,1967,3(6):356-365
[17]Fliss G G,Mensa D L.Instrumentation for RCS measurements of modulation spectra of aircraft blades.IEEE National Radar Conference,1986:12-13
[18]Bell M R,Grubbs R A.JEM modeling and measurement for radar target identification.IEEE Trans.on AES,1993,29(1):73-87
[19]Baum C E.On the singularity expansion method for solution of electromagnetic interaction problems.Air Force Weapons Lab.Interaction Notes 88,1971:1-25
[20]Pearson L W,Blaricum M J,Mittra R.A new method for radar target recognition based upon the singularity expansion method.Rec.IEEE Int.Radar Conf.,Arlington,VA,1975:452-457
[21]Blaricum M J,Mittra R.A technique for extracting the poles and residues of a system directly form its transient response.IEEE Trans.on AP,1975,23:777-781
[22]Jain V K,Sarkar T K,Weiner D D.Rational modeling by pencil of function method.IEEE Trans.on Acoustics,Speech,Signal Processing,1993,31(3):564-573
[23]Hua Y B,Sarkar T K.Generalized pencil-of-function method for extracting poles of an EM system from transient response.IEEE Trans.on AP,1989,37(2):229-234
[24]Drachman B,Rothwell E.A continuation method for identification of the natural frequencies of an object using a measured response.IEEE Trans.on AP,1985,33:445-450
[25]Kennaugh E M.The K-pulse concept.IEEE Trans.on AP,1983,29(3):327-331
[26]Chen K M.Radar wave synthesis methods:a new radar detection scheme.IEEE Trans.on AP,1981,29(4):553-565
[27]Chen K M.Ultra-wideband/Short-pulse radar for target identification and detection:laboratory study.Proceedings of IEEE 1995 Radar Conference,1995:450-455
[28]Rothwell E J,Nyquist K M,Chen K M.Radar target discrimination using the Extinctionpulse technique.IEEE Trans.on AP,1985,33(9):929-936
[29]Ilavarasan P.Performance of an automated radar target discrimination scheme using E pulses and S pulses.IEEE Trans.on AP,1993,41(5):582-588
[30]Rath M W.Survey of neural network technology for automatic target recognition.IEEE Trans.on NN,1990,1(1):28-43
[31]Giuli D.Polarization diversity in radars.Proceedings of IEEE,1986,74(2):245-269
[32]Zebker H A,Vanzyl J J.Imaging radar polarimetry:a review.Proceedings of IEEE,1991,79(11):1583-1606
[33]王晓丹,王积勤.雷达目标识别技术综述.现代雷达,2003,25(5):22-26
[34]Cameron W.Feature motivated polarization scattering matrix decomposition.IEEE Int.Radar Conf.,1990:549-557
[35]Chamberlain N F,Walton E K,Garber F D.Radar target identification of aircraft using polarization-diverse features.IEEE Trans.on AES,1991,27(1):58-66
[36]Steedly W M,Moses R L.High resolution exponential modeling of fully polarized radar returns.IEEE Trans.on AES,1991,27(3):459-468
[37]肖顺平,王雪松,郭桂蓉.基于极化谱的飞机目标识别.电子学报,1997,25(12):60-64
[38]王雪松,肖顺平,庄钊文.基于改进退火法按拟合参数估计的极化雷达目标识别.现代雷达,1997,19(2):6-11
[39]Tenoux T,Delisle G Y,Fournet P,et al.Analysis and interpretation of high resolution polarimetric SAR images.4e Colloque International sur le Radar,1994:358-363
[40]Meric S,Chassay G,Tenoux T,et al.Propagation prediction calculation used for SAR imaging urban area.Electronics Letters,1998,34(11):1147-1149
[41]刘晓峰.无线电摄像机目标识别研究[硕士学位论文].成都:电子科技大学,1996,1-6
[42]郭飚,陈曾平,庄钊文,等.基于高分辨率二维雷达图像的特征提取与目标识别.航天电子对抗,1998,2:19-25
[43]Novak L M,Owirka G J,Netishen C M.Radar target identification using spatial matched filters.Pattern Recognition,1994,27(4):607-617
[44]Novak L M,Owirka G J.Radar target identification using an eigen-image approach.IEEE Nat.Radar Conf,Atlanta,1994:129-131
[45]Martin N S.SAR systems resolution reviewed for target classification in knowledge-based environment.Proceedings of IEEE Electronic Technology Directions to the Year 2000,1995,5:177-183
[46]Pierce L E,Sarabandi I,Ulaby F T,et al.Knowledge-based classification of SAR images.IEEE IGARSS'93,1993,4:1611-1613
[47]Farhat N H.Microwave diversity imaging and automated target identification based models of neural networks.Proceedings of IEEE,1989,77(5):670-680
[48]Osman H,Blostein S D.SAR image processing using probabilistie winner-take-all learning and artificial neural networks.Proceedings of IEEE Int.Conf.on IP,1996,2:613-616
[49]Liao X J,Bao Z,Xing M D.On the sensitivity of high resolution range profiles and its reduction methods.IEEE International Radar Conf.,2000:310-315
[50]Smith C R,et al.Radar target identification.IEEE Antennas and Propagation Magazine,1993,35(2):27-38
[51]Wehner D R.High-resolution radar(2nd).685 Canton Street,Norwood,MA 02062,Artech House,INC.,1995,1-197
[52]Xing M D,Bao Z.The properties of range profile of aircraft.CIE International Conference on Radar Proceedings,Beijing,2001:1050-1054
[53]李廷军,姜文利,等.发展中的雷达目标识别.现代雷达,2000,22(6):1-5
[54] Seybold J S,Bishop S J.Three-dimensional ISAR imaging using a conventional high-range resolution radar.Proceedings of IEEE Nat.Radar Conf.,1996:309-314
[55]Bryant M L,Gostin L L,Soumekh M.Three-dimensional E-CSAR imaging of a T-72 tank and synthesis of its spotlight,stripmap and interferometric SAR reconstructions.Proceedings of IEEE Int.Conf.on IP,2001,3:628-631
[56]Yang R H,Pan Q,Cheng Y M.A new method for identify 3D aircraft targets.Computer Simulation,2006,23(6):82-84
[57]Li H J,Yang S H.Using range profiles as feature vectors to identify aerospace objects.IEEE Trans.on AP,1993,41(3):261-268
[58]Hudson S,Psaltis D.Correlation filters for aircraft identification from radar range profile.IEEE Trans.on AES,1993,29(3):741-746
[59]Rothwell E J,Chen K M,Nyquist D P,et al.A radar target discrimination scheme using the discrete wavelet transform for reduced data storage.IEEE Trans.on AP,1994,42(7):1033-1037
[60]Li Q,Rothwell E J,Chen K M,et al.Radar target discrmination shcemes using time-domain and frequency-domain methods for reduced data storage.IEEE Trans.on AP,1997,45(6):995-1000
[61]袁莉,刘宏伟,保铮.基于中心矩特征的雷达HRRP自动目标识别.电子学报,2004,32(12):2078-2081
[62]Zwicke P E.Ship classification using recursive structure identification and the Mellin transform.United Technology Res.CENT.,Rep.80,1981:192109
[63]郭桂蓉,郁文贤,胡步法.一种有效的舰船目标识别方法.系统工程与电子技术,1990,12(6):1-7
[64]郁文贤,郭桂蓉.ATR技术的研究现状和发展趋势.系统工程与电子技术,1994,16(6):25-30
[65]肖顺平,郭桂蓉,庄钊文,等.基于散射中心的目标建模与识别.系统工程与电子技术,1994,16(6):55-61
[66]He G H,Shah X M,Fen Z M,et al.Study of two methods in radar target recognition.Proceedings of IEEE Int.Radar Conf.,1996:674-678
[67]廖学军.基于高分辨距离像的雷达目标识别[博士学位论文].西安:西安电子科技大学,1999,1-6
[68]Jouny I,Garber F D,Moses R L.Radar target identification using the bispectrum:a comparative study.IEEE Trans.on AES,1995,31(1):69-77
[69]Chandran V,Elgar S L.Pattern recognition using invariants defined from higher order spectra one-dimensional inputs.IEEE Trans.on SP,1993,41(1):205-212
[70]Tugnait J K.Detection of non-Gaussian signals using integrated polyspectrum.IEEE Trans.on SP,1994,42(11):3137-3149
[71]Liao X J,Bao Z.Circularly integrated bispectra:novel shift invariant feature for highresolution radar target recognition.IEE Electronics Letters,1999,34(19):1879-1880
[72]Zhang X D,Shi Y,Bao Z.A new feature vector using selected bispectra for signal classification with application in radar target recognition.IEEE Trans.on SP,2001,49(9):1875-1885
[73]Kim K T,Seo D K,Kim H T.Efficient radar target recognition using the Music algorithm and invariant features.IEEE Trans.on AP,2002,50(3):325-337
[74]Carriere R,Moses R L.High resolution radar target modeling using a modified Prony estimator.IEEE Trans.on AP,1992,40(1):13-18
[75]Li J,Stoica P.Efficient mixed-spectrum estimation with application to feature extraction.IEEE Trans.on SP,1996,42(2):281-295
[76]李建平,严中洪,张万萍.基于小波分析的模式识别的几个问题.计算机科学,2001,28(5):110-112
[77]朱海,马颖.利用小波包提取雷达信号特征的方法研究.电子对抗,2002,5:33-36
[78]张静远,张冰,等.基于小波变换的特征提取方法分析.信号处理,2000,6:156-162
[79]田野,雷英杰,李军.基于小波变换的雷达信号特征提取方法.空军工程大学学报.2006,7(5):22-24
[80]马建华,刘宏伟,保铮.基于小波变换的雷达高分辨距离像识别.西安电子科技大学学报,2005,32(6):895-900
[81]Rothwell E J,Nyquist D P,Chen K M,et al.A radar target discrimination shceme using the discrete wavelet transform for reduced data storage.IEEE Trans.on AP,1994,42(7):1033-1037
[82]郭桂蓉.模糊模式识别理论及应用研究.中国科学基金,1991,3:15-18
[83]高新波,谢维信.模糊聚类理论发展及应用的研究进展.科学通报,1999,44(21):2241-2251
[84]肖怀铁,郭雷,付强,等.宽带多极化雷达目标模糊匹配识别方法.系统工程与电子技术,2005,27(5):770-773
[85]Liang M,Sun Z K,Liu J C.The second-order neural network for radar ship target recognition.Proceedings of IEEE Nat.AE Conf.,1992,1:270-274
[86]Kouba E T,Rogers S K,Ruck D W,et al.Recurrent neural networks for radar target identification.Proceedings of SPIE,1993,1965:256-265
[87]Stewart C,Lu Y C,Larson V.A neural clustering approach for high resolution radar target classification.Pattern Recognition,1994,27(4):503-513
[88]Lu Y C,Chang K C.A neural network approach for high resolution target classification.Proceedings of SPIE,1995,2484:558-566
[89]Zhao Q,Bao Z.Radar target recognition using a radial basis function neural network.Neural Networks,1996,9(4):709-720
[90]肖怀铁,付强,庄钊文,等.宽带毫米波雷达目标时延神经网络识别新方法.红外与毫米波学报,2001,20(6):459-463
[91]陈大庆,保铮.基于多层前向网络的雷达目标一维距离像识别.西安电子科技大学学报,1997,24(1):1-6
[92]Botha E C,et al.Feature based classification of aerospace radar targets using neural networks.Neural Networks,1996,9(1):129-142
[93]Shaw A K,Bhatngar V.Automatic target recognition using eigen-template.Proceedings of SPIE,1998,3370:448-459
[94]Shaw A K,Vashist R,et al.HRR-ATR using eigen-template with noisy observation in unknown target scenario.Proceedings of SPIE,2000:467-478
[95]刘本永.子空间法雷达目标一维距离像识别研究[博士学位论文].成都:电子科技大学,1999,1-95
[96]周代英.雷达目标一维距离像识别研究[博士学位论文].成都:电子科技大学,2001,1-92
[97]孟继成.雷达目标距离像识别研究[博士学位论文].成都:电子科技大学,2005,1-106
[98]Pei B N,Bao Z.Multi-aspect radar target recognition method based on scattering centers and HMMs Classifiers.IEEE Trans.on AES,2005,41(3):1067-1074
[99]Rabiner L R.A tutorial on hidden Markov models and selected application in speech recognition.Proceedings of IEEE,1989,77(2):257-286
[100]周德全.基于一维距离像的雷达目标识别研究[博士学位论文].南京:南京理工大学,1998,1-90
[101]陈江峰,裴炳南.一种基于HMM的雷达目标识别方法.郑州大学学报,2003,35(1):52-56
[102]Freidman N.Bayesian network classifiers.Machine Learning,1997,29(2-3):131-163
[103]Heckerman D.Bayesian networks for data mining.Data mining and knowledge discovery,1997,1:79-119
[104]Cortes C,Vapnik V.Support-vector networks.Machine Learning,1995,20(3):273-297
[105]毛京红,许小剑.高分辨力雷达目标识别研究.系统工程与电子技术,1994,16(10):11-16
[106]Serretta H,Inggs M R.Ship target recognition with the Mellin transform aided by neural networks.Proceedings of COMSIG,1998:203-208
[107]Mieras H.Optimal polarization of simple compound targets.IEEE Trans.on AP,1983,31(6):996-998
[108]Giuli D,Gheradelli M,Fossi M.Using polarization discriminants for target classification and identification.Proceedings of 1986 Inter.Conf.on Radar(CICR'86),China,1986:889-898
[109]Quach T,Farooq M.Investigation of a multiple passive sensor tracking algorithm.Proceedings of the 37~(th) Midwest Symposium on Circuits and Systems,1994,1:195-198
[110]Li H J,Lane R Y.Utilization of multiple polarization data for aerospace target identification.IEEE Trans.on AP,1995,43(12):1436-1440
[111]Jouny I,Kanapathipillai M.Neural network adaptive wavelet classification of radar targets.IEEE IGARSS'94,1994,4:1889-1891
[112]张小英,王宝发,刘铁军.基于PCA-LVQ的雷达目标一维距离像识别.系统工程与电子技术,2005,27(8):1373-1375
[113]何松华,郭桂蓉,庄钊文.雷达目标高分辨距离-极化结构成像方法研究.电子学报,1994,22(7):1-8
[114]Parmar N C,Codex M,Kokar M M.Target detection in fused X-band radar and IR images using the functional minimization approach to data association.Proceedings of IEEE Int.Symp.on Intelligent Control,1994:51-56
[115]姜文利,唐白玉,徐可斌,等.高频区雷达目标散射模型及其参数估计.电子学报,1998,26(3):70-74
[116]Altes R A.Sonar for generalized target description and its similarity to animal echolocation system.Journal of Acoustic.Soc.A.,1976,59:97-105
[117]Sch(o|¨)lkopf B,Smola A,M(u|¨)ller K R.Nolinear component analysis as a kernel eigenvalue problem.Neural Computation,1998,10(5):1299-1319
[118]Mika S,R(a|¨)tsch G,Weston J,et al.Fisher discriminant analysis with kernels.Proceedings of the IEEE International Workshop on Neural Networks for Signal Processing,USA,1999:41-48
[119]Baudat G,Anouar F.Generalized discriminant analysis using a kernel approach.Neural Computation,2000,12(10):2385-2404
[120]Raudys S,Duin R P W.On expected classification error of the fisher linear classifier with pseudo-inverse convariance matrix.Pattern Recognition Letters,1998,19(5-6):385-392
[121]Belhumeur P N,Hespanha J P,Kriegman D J.Eigenfaces vs.fisherfaces:recognition using class specific linear projection.PAMI,1999,19:711-720
[122]Hong Z Q,Yang J Y,et al.Optimal discriminant plane for a small number of samples and design method of classifier on the plane.Pattern Recognition,1991,24(4):317-324
[123]Chen L F,Mark Liao H Y,Lin J C,et al.A new LDA-based face recognition system which can solve the small sample size problem.Patter Recognition,2000,33:1713-1726
[124]Yu H,Yang J.A direct LDA algorithm for high-dimensional data with application to face recognition.Pattern Recognition,2001,34:2067-2070
[125]Lu J W,Plataniotis K N,Venetsanopoulos A N.Face recognition using kernel direct discriminant analysis algorithms.IEEE Trans.on Neural Networks,2003,14(1):117-126
[126]Zheng W M,Zou C R,Zhao L.Real-time face recognition using Gram-Schmidt orthogonalization for LDA.Proceedings of the 17~(th) International Conference on Pattern Recognition(ICPR'04),Cambridge UK,2004:403-406
[127]Fukunaga,K.Introduction to statistical pattern recognition.Orlando,FL:Academic Press,1990,1-592
[128]张贤达.矩阵分析与应用.北京:清华大学出版社,2004,47-52,229-244,367-380
[129]Wolf L,Shashua A.Learning over sets using kernel principal angles.Journal of Machine Learning Research,2003,4:913-931
[130]Rice J R.Experiments on Gram-Schmidt orthogonalization.Mathematics Computation,1966,20:325-328
[131]Bj(o|¨)rck A.Solving linear least squares problems using Gram-Schmidt orthogonalization.BIT,1967,7:1-21
[132]Jin Z,Yang J Y,Hu Z S,et al.Face recognition based on uncorrelated discriminant transformation.Pattern Recognition,2001,34(7):1405-1416
[133]Jin Z,yang J y,Tang Z M,et al.A theorem on uncorrelated optimal discriminant vectors.Pattern Recognition,2001,34(10):2041-2047
[134]金忠,杨静宇,陆建峰.一种具有统计不相关性的最优辨别矢量集.计算机学报,1999,22(10):1105-1108
[135]金忠,胡钟山,杨静宇,等.手写体数字有效鉴别特征的抽取和识别.计算机研究与发展,1999,36(12):1484-1489
[136]金忠.人脸图像特征制取与维数研究[博士学位论文].南京:南京理工大学,1999,1-85
[137]Ye J P,Janardan R,Li Q,et al.Feature extraction via generalized uncorrelated linear discriminant analysis.IEEE Trans.on Knowledge and Data Engineering,2006,18(10):1312-1322
[138]Howland P,Park H.Generalized discriminant analysis using the generalized singular value decomposition.IEEE Trans.on Pattern Analysis and Machine Intelligence,2004,26(8):995-1006
[139]Yang M H.Kernel eigenfaces vs.kernel fisherfaces:face recognition using kernel methods.Proceedings of the Fifth International Conference on Automatic Face and Gesture Recognition(FG 2002),Washington D.C.,2002:215-220
[140]Liu K,Yang J Y,et al.An efficient algorithm for Foley-Sammon optimal set of discriminant vectors by algebraic method.International Journal of Pattern Recognition and Artificial Intelligence,1992,6(5):817-829
[141]Kreyszig E.Introductory functional analysis with application.John Wiley & Sons,1978,1-704
[142]Cover T M,Hart P E.Nearest neighbor patter classification.IEEE Trans.on Information Theory,1967,13:21-27
[143]Li S Z,Lu J W.Face recognition using the nearest feature line method.IEEE Trans.on Neural Networks,1999,10(2):439-443
[144] Chien J T, Wu C C. Discriminant waveletfaces and nearest feature classifiers for face recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence,2002,24(12):1644- 1649
[145] Zheng W M, Zhao L, Zou C R. Locally nearest neighbor classifiers for pattern recognition. Pattern Recognition,2004,37(6): 1307-1309
[146] R Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding. Science,2000,290:2323-2326
[147] Liang Z Z, Shi P F. Uncorrelated discriminant analysis using a kernel method. Pattern Recognition,2005,38(2):307-310
© 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 |