基于图像不变量特征的自动目标识别技术研究
|
摘要
随着光电子、智能控制、模式识别和计算机视觉技术飞跃发展，自动目标识别技术(ATR)在现代武器系统中的作用日益突出。基于图像不变量的特征提取方法，一直是ATR的关键技术之一。本文在对目标识别、图像处理等理论研究的基础上，针对图像目标的不变量特征进行了总结和拓展。论文以飞机为研究对象，完成了从目标图像特征提取到分类的一系列ATR关键技术研究，为飞机成像自动识别技术提供了有价值的参考。论文主要贡献如下：
1、对飞机识别中用到的图像不变量，包括全局不变量和局部不变量，进行了系统的总结；
2、以往的飞机识别，大都基于已知目标是飞机的前提下，对飞机机型进行自动判别。实际应用中，目标的类型往往是未知的，成像自动目标识别系统无法事先自动获知传感器采集目标是否是飞机。因此，为解决在一系列目标中能够自动检测出飞机，提出了一种基于模糊C均值聚类的改进词袋模型算法；
3、提出了对飞机目标进行二级自动分类的识别框架：粗分类和精分类。粗分类采用上述的改进词袋模型算法，检测出飞机目标；精分类采用通用的不变量特征提取方法，结合智能型分类器：传统神经网络或支持向量机，进行飞机机型分类；
4、针对三种全局不变量：Hu矩，仿射矩，归一化傅里叶描述子，结合支持向量机分类器，进行识别效果对比。在此基础上，将三者进行特征级融合，形成一种新的组合不变量：矩-傅里叶描述子。同时，为解决特征分量之间取值范围较大的问题，研究了四种不同的特征量归一化方法，分别与传统神经网络和支持向量机结合后的分类效果，进而提出对图像不变量特征选用归一化方法的具体原则；
5、提出了一种新的局部不变量： SIFT顺序尺度。分析了SIFT顺序尺度的不变性。仿真实验验证了在清晰、加噪、遮挡条件下所提出的SIFT顺序尺度不变量，对比于仿射矩、多尺度自卷积的高识别率性能；
6、针对特征级融合时，特征向量维数较大，部分较差特征甚至还会降低识别系统识别率等问题，提出采用决策级融合方法进行机型判别：对同一幅飞机图像，选取不同类别的不变量，构造多个分类性能较优的单分类器，按照自适应权重投票法，进行多分类器融合判别，去实现较为通用的飞机图像自动识别系统；
本文虽然是以飞机目标为研究对象进行图像识别研究，但所提出的技术具有通用性，很容易推广到运动刚体目标的图像识别中，如卫星识别，导弹识别,舰船识别，地面车辆识别等。
With the rapid development of photonics, intelligent control, pattern recognitionand computer vision, Automatic Target Recognition (ATR) technology is more andmore important in modern weapon systems. In ATR field, the feature extractionmethod based on image invariants is one of the key technologies for achieving ATR.In this paper, on the basis of studying target recognition and image processing, theinvariant features are summarized and expanded. Moreover, taking aircraft as anobject of study, a series of key technologies on ATR from feature extraction to targetclassification are studied. So the research of this paper can provide some beneficialmethods for ATR technology. The main contributions are as follows:
1. The invariants, which include global invariants and local invariants in aircraftrecognition, are summarized;
2. For traditional aircraft recognition, the research works are mainly based onaircraft type recognition, and the collected image target has been thought as aircraftin advance. However, in practical applications, the collected image target isunknown in advance, so the image target recognition system can’t know that thecollected target is or not aircraft. For detecting the aircraft from a series of targetsautomatically, an automatic target recognition algorithm base on the improved bag ofword model, which is used by Fuzzy C-Mean (FCM) clustering, is proposed;
3. A two-stage classification framework on aircraft automatic recognition isproposed: Coarse classification and Fine classification. Coarse classification detectsaircraft from a series of targets by the above improved bag of word model. Fineclassification identifies the aircraft type from a series of aircraft targets by universalinvariants with Support Vector Machine (SVM) or traditional neural network.
4. The aircraft recognition performance is compared by the three kinds of globalinvariants: Hu moments, affine moments, normalized Fourier descriptors, with SVMclassifier. Then the above three kinds of invariants are combined as moment-fourierdescriptors. Moreover, for resolving the wide value range between feature vectors, the four normalization methods, which are combined with traditional neural networkor SVM separately, are studied and the choice principle of the normalizationmethods is proposed.
5. A new kind of local invariant features, which is called as SIFT SequenceScale (SIFT-SS), are proposed. The invariance of the SIFT-SS is analyzed. Moreover,the recognition performance of SIFT-SS invariants, affine moments, Multi-ScaleAutoconvolution (MSA) are compared in clear images, added noised images andocclusion images. Experiments are shown that the SIFT-SS invariants are the highestrecognition rate in the above three kind of invariants.
6. As feature fusion lie in some questions, such as the too large feature vectordimensions, some poor invariants can reduce the recognition rate of aircraftautomatic recognition system. So a new decision fusion method is proposed: first,for an aircraft image, different kinds of invariants are extracted and each kind ofinvariants is used to construct a SVM classifier. Second, many SVM classifiers arefused by the adaptive weights vote method and used for aircraft type recognition.
In this paper, although the research object is aircraft, the proposed methods areuniversal for all image targets. So the methods can be easy to expand the imagerecognition for many mobile rigid objects, such as satellite recognition, missilerecognition, ship recognition, vehicle recognition.
1、对飞机识别中用到的图像不变量，包括全局不变量和局部不变量，进行了系统的总结；
2、以往的飞机识别，大都基于已知目标是飞机的前提下，对飞机机型进行自动判别。实际应用中，目标的类型往往是未知的，成像自动目标识别系统无法事先自动获知传感器采集目标是否是飞机。因此，为解决在一系列目标中能够自动检测出飞机，提出了一种基于模糊C均值聚类的改进词袋模型算法；
3、提出了对飞机目标进行二级自动分类的识别框架：粗分类和精分类。粗分类采用上述的改进词袋模型算法，检测出飞机目标；精分类采用通用的不变量特征提取方法，结合智能型分类器：传统神经网络或支持向量机，进行飞机机型分类；
4、针对三种全局不变量：Hu矩，仿射矩，归一化傅里叶描述子，结合支持向量机分类器，进行识别效果对比。在此基础上，将三者进行特征级融合，形成一种新的组合不变量：矩-傅里叶描述子。同时，为解决特征分量之间取值范围较大的问题，研究了四种不同的特征量归一化方法，分别与传统神经网络和支持向量机结合后的分类效果，进而提出对图像不变量特征选用归一化方法的具体原则；
5、提出了一种新的局部不变量： SIFT顺序尺度。分析了SIFT顺序尺度的不变性。仿真实验验证了在清晰、加噪、遮挡条件下所提出的SIFT顺序尺度不变量，对比于仿射矩、多尺度自卷积的高识别率性能；
6、针对特征级融合时，特征向量维数较大，部分较差特征甚至还会降低识别系统识别率等问题，提出采用决策级融合方法进行机型判别：对同一幅飞机图像，选取不同类别的不变量，构造多个分类性能较优的单分类器，按照自适应权重投票法，进行多分类器融合判别，去实现较为通用的飞机图像自动识别系统；
本文虽然是以飞机目标为研究对象进行图像识别研究，但所提出的技术具有通用性，很容易推广到运动刚体目标的图像识别中，如卫星识别，导弹识别,舰船识别，地面车辆识别等。
With the rapid development of photonics, intelligent control, pattern recognitionand computer vision, Automatic Target Recognition (ATR) technology is more andmore important in modern weapon systems. In ATR field, the feature extractionmethod based on image invariants is one of the key technologies for achieving ATR.In this paper, on the basis of studying target recognition and image processing, theinvariant features are summarized and expanded. Moreover, taking aircraft as anobject of study, a series of key technologies on ATR from feature extraction to targetclassification are studied. So the research of this paper can provide some beneficialmethods for ATR technology. The main contributions are as follows:
1. The invariants, which include global invariants and local invariants in aircraftrecognition, are summarized;
2. For traditional aircraft recognition, the research works are mainly based onaircraft type recognition, and the collected image target has been thought as aircraftin advance. However, in practical applications, the collected image target isunknown in advance, so the image target recognition system can’t know that thecollected target is or not aircraft. For detecting the aircraft from a series of targetsautomatically, an automatic target recognition algorithm base on the improved bag ofword model, which is used by Fuzzy C-Mean (FCM) clustering, is proposed;
3. A two-stage classification framework on aircraft automatic recognition isproposed: Coarse classification and Fine classification. Coarse classification detectsaircraft from a series of targets by the above improved bag of word model. Fineclassification identifies the aircraft type from a series of aircraft targets by universalinvariants with Support Vector Machine (SVM) or traditional neural network.
4. The aircraft recognition performance is compared by the three kinds of globalinvariants: Hu moments, affine moments, normalized Fourier descriptors, with SVMclassifier. Then the above three kinds of invariants are combined as moment-fourierdescriptors. Moreover, for resolving the wide value range between feature vectors, the four normalization methods, which are combined with traditional neural networkor SVM separately, are studied and the choice principle of the normalizationmethods is proposed.
5. A new kind of local invariant features, which is called as SIFT SequenceScale (SIFT-SS), are proposed. The invariance of the SIFT-SS is analyzed. Moreover,the recognition performance of SIFT-SS invariants, affine moments, Multi-ScaleAutoconvolution (MSA) are compared in clear images, added noised images andocclusion images. Experiments are shown that the SIFT-SS invariants are the highestrecognition rate in the above three kind of invariants.
6. As feature fusion lie in some questions, such as the too large feature vectordimensions, some poor invariants can reduce the recognition rate of aircraftautomatic recognition system. So a new decision fusion method is proposed: first,for an aircraft image, different kinds of invariants are extracted and each kind ofinvariants is used to construct a SVM classifier. Second, many SVM classifiers arefused by the adaptive weights vote method and used for aircraft type recognition.
In this paper, although the research object is aircraft, the proposed methods areuniversal for all image targets. So the methods can be easy to expand the imagerecognition for many mobile rigid objects, such as satellite recognition, missilerecognition, ship recognition, vehicle recognition.
引文
[1] Kyung-Tae Kim, Dong-Kyu Seo, and Hyo-Tae Kim. Efficient Classification of ISARImages[J].IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION,2005,53(5):1611-1621
[2]李言俊，张科著.景象匹配与目标识别技术[M].西北工业大学出版社，2009：13-15
[3]刘宏鼎,秦世引.基于图像特征的运动目标识别与伺服跟踪[J].仪器仪表学报,2008,29(3):644-648
[4] M. Y. Mashor, M. K. Osman and,M. R. Arshad.3D Object Recognition Using2DMoments and HMLP Network[C]. Proceedings of the International Conference onComputer Graphics, Imaging and Visualization (CGIV’04),2004:126-130
[5]Wenjing Li, George Bebis, Nikolaos G. Bourbakis.3-D Object Recognition Using2-D Views [J].IEEE TRANSACTIONS ON IMAGE PROCESSING,2008,17(11):2236-2254
[6]Dudani SA,Breeding KJ,Mcghee Robert B.Aircraft Identification by Momentlnvariants [J]．IEEE TRANSACTIONS ON COMPUTERS,1977,26(1)：39-46
[7]K.ARBTER,WESLEY.E,SNYDERd. Application of Affine-Invariant FourierDescriptors to Recognition of3-D Objects [J]. IEEE Transactions on patternanalysis and machine intelligence,1990,12(7):640-647
[8] Reeves AP, Prokop RJ, Andrews SE. Three-dimensional shape analysis usingmoments and Fourier descriptors [J].IEEE TRANSACTIONS ON PATTERN ANALYSIS ANDMACHINE INTELLIGENCE,1988,(10):937-943
[9] Kamgar-Parsi,Behrooz,Kamgar-Parsi,Behzad,Jain, Anil K. Automatic aircraftrecognition: Toward using human similarity measure in a recognition system [C].Proceedings of the1999IEEE Computer Society Conference on Computer Visionand Pattern Recognition (CVPR'99),1999:268-273
[10] Das.Subhodev,Bhanu.Bir,Wu.Xing,etal. System for aircraft recognition inperspective aerial images [C]. Proceedings of the2nd IEEE Workshop onApplications of Computer Vision.1994:168-175
[11]Das.Subhodev, Bhanu.Bir.A system for model-based object recognition inperspective aerial images[J]. Pattern Recognition,1998,31(4):465-491
[12]Saidi.M.N.,Daoudi.K,Khenchaf.A,etal. Automatic target recognition ofaircraft models based on ISAR images [C]. International Geoscience and RemoteSensing Symposium (IGARSS),2009,4:685-688
[13] Saidi.M.N, Toumi. A,Hoeltzener.B,etal. Aircraft Target Recognition: A novelapproach for features extraction from ISAR images[C]. Radar Conference-Surveillance for a Safer World,2009:1-5
[14] Hmam, Hatem; Kim, Jijoong. Automatic aircraft recognition [C]. Proceedingsof SPIE-The International Society for Optical Engineering.2002:229-238
[15] G.Y. Chen, T.D. Bui, A. Krzyzak. Invariant pattern recognition using radon,dual-tree complex wavelet and Fourier transforms [J].PatternRecognition.2009,42:2013-2019
[16]杜亚娟.基于不变矩理论的自动目标识别技术研究（博士学位论文）[D].西北工业大学,2000
[17]刘准钆,程咏梅,潘泉等。证据冲突下自适应融合目标识别算法[J].航空学报，2010，31(7)：1426-1432
[18]杜鸿英，郭雷，李晖晖，刘坤.基于不变矩与证据理论的飞机序列图像识别[J].计算机仿真，2010，27(2):92-95
[19]李科.自动识别遥感光学图像中飞机目标的研究[硕士学位论文][D].国防科学技术大学，2005
[20]陈涛.图像仿射不变特征提取方法研究[博士学位论文][D].国防科技大学，2006
[21]唐涛.图像仿射不变特征及其在遥感图像目标识别中的应用[硕士学位论文][D].国防科技大学，2007
[22]李迎春.航空图像中机场停泊飞行器的识别技术研究[博士学位论文][D].吉林大学，2004
[23]郑南.遥感图像中飞机目标的识别分类算法研究[硕士学位论文][D].吉林大学，2007
[24]吴巍,彭嘉雄.飞行器结构特征提取与识别[J].华中科技大学学报(自然科学版),2004,32(1):70-72
[25]Jin Liu, Tianxu Zhang. Recognition of the blurred image by complex momentinvariants [J]. Pattern Recognition Letters.2005,24:1128–1138
[26]Liu Jin.Zhang TianXu. Fast algorithm for generation of moment invariants[J].Pattern Recognition.2004,37(10):1745-1756
[27]张天序著.成像自动目标识别[M].湖北科学技术出版社，2003
[28]安国平.基于DAM6416P平台的目标图像识别技术研究.[硕士学位论文][D].南京航空航天大学，2008
[29]蔡梅艳.基于TMS320C642DSP的目标图像识别研究.[硕士学位论文][D].南京航空航天大学，2007
[30]王振旻.目标图像识别算法研究及其在DSP高速处理系统中的实现.[硕士学位论文]
[D].南京航空航天大学，2008
[31] Zhang Feng, Liu Shang-qian,Wang Da-bao, Guan Wei. Aircraft recognition ininfrared image using wavelet moment invariants[J]. Image and VisionComputing,2009,27:313-318
[32]崔艳鹏,胡建伟,杨绍全.利用尺度不变量特征的ISAR二维像自动识别技术[J].西安电子科技大学学报(自然科学版),2009,36（4）：725-728
[33]胡国平,张守宏.多传感器协同探测目标的分类识别研究[J].西安电子科技大学学报(自然科学版),2009，36(3):443-447
[34]张名成,吴秀清,王鹏伟.基于闭合轮廓提取和部分特征匹配的飞机识别[J].计算机仿真,2006，23(11):193-197
[35]刘莉,吴秀清,牛宗标.模糊图像中的飞机识别方法[J].计算机仿真,2006,23(3):164-166
[36]王鹏伟，吴秀清，余珊.基于角点特征和自适应核聚类算法的目标识别[J].计算机工程,2007,33(6):179-181
[37]熊英，马慧敏.3维物体SIFT特征的提取与应用[J].中国图像图形学报.2010,15（5）:814-819
[38]王志远.基于电视跟踪的三维目标识别[硕士学位论文][D].长春理工大学，2008
[39]陈小超.基于几何特性的飞机目标特征提取技术的研究[硕士学位论文][D].长春理工大学，2006
[40]M. K. OSMAN, M. Y. MASHOR, M. R. ARSHAD.3D Object Recognition Using MultipleViews, Affine Moment Invariants and Multilayered Perceptron Network[J]. WSEASTransactions on SYSTEMS.2004,10(3):3065-3070
[41]廖海斌,王宏勇.航空机型快速有效识别方法研究[J].计算机工程与用.2008,44(34):185-187
[42] Hu M K.Visual pattern recognition by moment invariants[J]. IRE Transactionson Information Theory,1962,8:179-187
[43]刘进,张天序.图像不变矩的推广[J].计算机学报,2004,27(5):668-674
[44]张洁玉,陈强,白小晶,孙权森,夏德深.一种新的局部仿射不变特征描述符[J].光电子激光.2009，20(11):1503-1506
[45]孙洁,马惠敏,李凤亭.基于仿射不变性特征的视点空间划分[J].清华大学学报(自然科学版),2009,49(1):53-56
[46]王凤国,冯象初,张小波.平稳小波变换在仿射不变性目标识别中的应用[J].计算机工程与应用,2007,43(21):239-241
[47]杨昕梅,吴钦章,周进.仿射不变的运动目标识别方法[J].光学精密工程.2007,15(7):1112-1116
[48] Janne Heikkil. Pattern matching with affine moment descriptors[J]. PatternRecognition.2004,37:1825-1834
[49] Hongping Cai,Lin Lei,Yi Su. An Affine Invariant Region Detector Using the4thDifferential Invariant[C].19th IEEE International Conference on Tools withArtificial Intelligence.2007:540-543
[50]李兴唐,曹立华,王思雯.仿射变换的飞行器识别[J].光学精密工程.2009,17(2):402-408
[51] Jan Flusser and Tomas Suk. pattern recognition by affine moment invariants[J].pattern recognition,1993，26(1):167-174
[52]李迎春,陈贺新,赵铭,顼鹏飞;基于飞机目标的仿射不变矩研究[J].吉林大学学报，2003，21(5):84-88
[53]吴高洁，李超，熊璋.一种目标识别中基于关键点的仿射不变矩[J].北京航空航天大学学报,2009,35(9):1044-1047
[54] D.Shen,H.S.Ip Horace. Discriminative wavelet shape descriptors forrecognition of2-D patterns[J]. Pattern Recognition.1999,32(2):151–165
[55] Chong-Yaw Wee,Raveendran Paramesran,R. Mukundan. Fast computation of geometricmoments using a symmetric kernel[J]. Pattern Recognition,2008,41:2369–2380
[56] Dong Xu, Hua Li. Geometric moment invariants[J]. Pattern Recognition,2008,41:240–249
[57] T.P.Wallace,P.A.Wintz.An efficient three-dimensional aircraftrecognition algorithm using normalized Fourier descriptors[J].Comput.Graphics Image Processing,1980,13：99-126
[58]Zen Chen, Shinn-Ying Ho. Computer vision for robust3D aircraft recognitionwith fast library search[J]. Pattern Recognition,1991,24(5):375-390
[59] Esa Rahtu,Mikko Salo and Janne Heikkila. Affine Invariant Pattern RecognitionUsing Multi-scale Autoconvoltion[J]. IEEE Trans on Pattern Anlysis andMachine Intelligence,2005:908-918
[60]徐学强,汪渤,于家城等.一种新型不变矩在图像识别中的应用[J].光学术,2007,33(4):580-583
[61]黄波，赵继印，郑蕊蕊，李敏.基于多尺度自卷积归一化直方图的仿射不变量模式识别[J].电子学报,2011,39(1):64-69
[62] J. Flusser, T. Suk, and S. Saic, Recognition of blurred images by the methodof moments[J]. IEEE Trans.Image Process.,1996，5(3):533–538
[63] Hui Zhang, Huazhong Shu, Guoniu N. Han, Gouenou Coatrieux, Limin Luo, JeanLouis Coatrieux. Blurred Image Recognition by Legendre MomentInvariants[J].IEEE TRANSACTIONS ON IMAGE PROCESSING.2010.19(3):596-611
[64] ALIREZA KHOTANZAD AND YAW HUA HONG. Invariant Image Recognition byZernike Moments[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINEINTELLIGENCE.1990,12(5):489-497
[65]赵恒卓,杨春旭,胡正仪,王延平.基于线矩特征的破损目标识别[J].武汉大学学报(自然科学版),1997,43(5):650-654
[66]卢汉青,彭家雄，万发贯.角点在目标分类识别中的应用[J].数据和采集.1992，7(3):183-186
[67]曾刚,廖原,尹亮,胡正仪,王延平.拐点特征的提取和物体破损图象的识别[J].中国图像图形学报,1998,3(3):217-220
[68]曹健,高春晓,刘琼昕,贺跃.基于角点特征的目标识别方法[J].华中科技大学学报(自然科学版),2010,38(6):84-87
[69]季战领,冯晓毅,阎昆.一种ISAR图像中飞机目标识别的新特征[J].计算机工程,2010,36(23):192-196
[70]Georgios Kordelas, Petros Daras. Viewpoint independent object recognition incluttered scenes exploiting ray-triangle intersection and SIFT algorithms [J].Pattern Recognition43(2010)3833–3845
[71] D.G.Lowe. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2)：91-110
[72] Filip Krolupper, Jan Flusser. Polygonal shape description for recognition ofpartially occluded objects[J]. Pattern Recognition Letters,2007,28:1002-1011
[73] Chao Kan, Mandyam D. Srinath. Invariant character recognition with Zernikeand orthogonal Fourier-Mellin moments[J]. PatternRecognition,2002,35:143-144
[74] Tomas Suk, Jan Flusser. Combined blur and affine moment invariants and theiruse in pattern recognition[J]. Pattern Recognition,2003,36:2895–2907
[75]敬忠良，肖刚，李振华.图像融合--理论与应用[M].高等教育出版社，2007：105-107
[76]廖闻剑,成瑜.三维飞机自动识别的一种有效方法.[J].航空学报，1998，19（6）：730-735
[77] K.S.Fu. Syntactic Pattern Recognition and Applications [M]. Prentice Hall,1982
[78] Robert A. McLaughlin and Michael D.Alder. Recognition of Infra Red Imagesof Aircraft Rotated in Three Dimensions [R]. University of Western AustraliaTechnical Report，1995:95-104
[79] Shen-Chi Tien, Tsorng-Lin Chia，Yibin Lu. Using cross-ratios to model curvedata for aircraft recognition[J]，Pattern Recognition Letters.2003,24：2047–2060
[80] Wei Zhang, Bing Yu, Gregory J. Zelinsky, Dimitris Samaras。Object ClassRecognition Using Multiple Layer Boosting with Heterogeneous Features[C].IEEEComputer Society Conference on Computer Vision and Pattern Recognition(CVPR'05),2005，2：323-330
[81] J.-W. Hsieh, J.-M. Chen, C.-H. Chuang and K.-C. Fan，Aircraft type recognitionin satellite images[J]. IEEE Proc.-Vis. Image Signal Process.2005,152(3):307-315
[82] XU sheng, PENG Qicong.3D Object Recognition Using Multiple Features and NeuralNetwork [C].CIS2008:434-439
[83]侯一民,伦向敏.基于矩与角点特征的飞机目标识别[J].计算机工程与应用.2008,44(16):179-181
[84]曾万梅，吴庆宪，姜长生.基于组合不变矩特征的空中目标识别方法[J].电光与控制,2009,16(7):21-24
[85]苗常青,汪渤,付梦印等.电视图像目标实时分割与识别算法[J].北京理工大学学报,2005,25(9):786-790
[86]赵芹,周涛,舒勤.飞机红外图像的目标识别及姿态判断[J].红外技术,2007,29(3):167-169
[87]肖家庆,卢凌,李晟,聂明新.基于矩不变量的图像目标识别[J].武汉理工大学学报.2006,30(4):696-699
[88]马迎军.基于粗糙集与支持向量机的军用飞机识别算法[硕士论文][D].西北工业大学，2007:71-72
[89] Donghe Wang，Xin He，Wei Zhonghui， Huilong Yu. A Method of Aircraft ImageTarget Recognition Based on Modified PCA Features and SVM[C].The NinthInternational Conference on Electronic Measurement&Instruments,2009，4:117-881
[90] Soo Beom Park, Jae Won Lee, Sang Kyoon Kim.Content-based image classificationusing a neural network[J].Pattern Recognition Letters.2004，25:287–300
[91]梁明，孙仲康.人工神经网络的一种改进的B-P学习算法及其应用[C].中国神经网络首届学术大会论文集.1990：441-444
[92]A.A.Somaie,A.Badr and T.Salah. Aircraft Image Recognition UsingBack-Propagation.Radar[C]. CIE International Conference on, Proceedings，2001：498–501
[93] Shuangzi Sun，Lihong YuanYong Yang Xiaochao Chen. The Features Vector Researchon Target Recognition of Airplane[C].Proceedings of the11th Joint Conferenceon Information Sciences，2008:1-5
[94]张艳宁，郑江滨，侯云舒，赵荣椿.基于SOM和SVM的遥感图像目标识别[J].系统工程与电子技术,2002,24(7):9-11
[95]唐克,魏琪,杜涛.基于支持向量机的高空无人机侦察目标识别[J].火力与指挥控制.2010,35(3):82-85
[96]杨利英，覃征，王向华.多分类器融合实现机型识别[J].计算机工程与应用，2004：10-12
[97] J. Kittler and F.M. Alkoot.Sum versus Vote Fusion in Multiple ClassifierSystems [J].IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2003,25(1):110-115
[98]Bor-Chen Kuo,Chih-Sheng Huang,Hsiang-Chuan Liu,Chih-Cheng Hung.A fuzzy fusionalgorithm to combine multiple classifiers [C].IGARSS2009,3:685-688
[99]Dymitr Ruta,Bogdan Gabrys.An Overview of Classifier Fusion Methods[J].Computing and Information Systems,2000,7:1-10
[100] Dymitr Ruta,Bogdan Gabrys. A theoretical analysis of the limits of majorityvoting errors for multiple classifier systems[J].Pattern Analysis andApplications.2002,5(4):333-350
[101]韩建峰,杨哲海.组合分类器及其在高光谱影像分类中的应用[J].测绘科学技术学报.2007，24（3）:231-234
[102] Ahmed Al-Ani,Mohamed Deriche. A New Technique for Combining MultipleClassifiers using The Dempster-Shafer Theory of Evidence[J].Journal ofArtificial Intelligence Research2002,17:333-361
[103]蒋宏,田野.雷达专家系统目标识别和红外图像目标识别的D-S融合[J].航空科学技术.2010,2:30-33
[104]刘明,袁保宗,苗振江,唐晓芳.基于模糊规则的多分类器融合[J],电子与信息学报,2007,29(7):1707-1712
[105]马颂德.计算机视觉（计算理论与算法基础）[M]，科学出版社，1998:52-53
[106]章毓晋编著.图像工程(第2版)[M].清华大学出版社，2006:47-52
[107]郑南宁.计算机视觉与模式识别[M].国防工业出版社，1998:14-20
[108]（美）桑卡等著，艾海舟等译.图像处理、分析与机器视觉（第二版）[M].人民邮电出版社,2003:393-395
[109]陈柘，赵荣椿.几何不变性及其在3D物体识别中的应用[J].中国图像图形学报,2003,8(9):993-1000
[110]李玉山.数字视觉视频技术[M].西安：西安电子科技大学出版社，2006:128-129
[111]孙既祥.模式识别中的特征提取与计算机视觉不变量[M].国防工业出版社.2001:238-240
[112]李科,王润生,王程.一种用于飞机型号识别的树分类器方法[J].计算机工程与科学,2006,28(11):136-139
[113]夏良正，李久贤编著.数字图像处理(第2版)[M].东南大学出版社，2005:253-254
[114] Mark Nixon, Alberto Aguado. Feature Extraction and Image Processing(secondEdition)[M]，2008：311-314
[115] Gabriel Taubin,David B. Cooper.Object Recognition Based on Moment (orAlgebraic) Invariants[J]. Geometric Invariance in Computer Vision.1992:375-397
[116] Jan Flusser. Moment Invariants in Image Analysis[C]. Proceeding of worldacademy of science,engineering and technology,2006,11：196-201
[117] D. Shen, H.S.Ip. Horace, Discriminative wavelet shapedescriptors for recognition of2-D patterns[J]. Pattern Recognition.1999,32(2):151–165.
[118] Arbter K, Snyder WE,Burkhant H,etal. Application of affine-invariant fourierdescriptors to recognition of3D objects[J]. IEEE TransPAMI,1990,12(7):640-647
[119] Richard J. Prokop Anthony P. Reeves. A Survey of Moment-Based Techniques ForUnoccluded Object Representation and Recognition[J]. CVGIP: GraphicalModels and Image Processing,1992,54(5):438-460
[120]姚军，蒋晓瑜，黄应清.目标识别中Hu矩、Zernike矩和小波矩的比较[J].装甲兵工程学院学报.2006,20(3):34-36
[121]郭宇晨,马惠敏,廖庆敏.基于二维成像的三维物体形状特征分析[J].清华大学学报(自然科学版),2009,49(10):73-77
[122]卢汉清,彭嘉,万发贯.角点在目标识别分类中的应用[J].数据采集与处理,1992,7(3):182-186
[123] Krystian Mikolajczyk，Cordelia Schmid. A performance evaluation of localdescriptors[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.2005,27(10):1615-1630.
[124] Krystian Mikolajczyk, Bastian Leibe, Bernt Schiele.Local Features for ObjectClass Recognition[C]. IEEE International Conference on Computer Vision(ICCV'05).2005,2:1792-1799,
[125]张天序著.成像自动目标识别[M].湖北科学技术出版社，2005：263-269
[126]孙即祥.现代模式识别[M].高等教育出版社，2008：637-640
[127]边肇祺，张学工等编著.模式识别（第二版）[M].清华大学出版社，2000:296-303
[128] Vladimir Cherkassky and Yunqian Ma. Practical selection of SVM parametersand noise estimation for SVM regression [J]. Neural Networks,2004,17:113-126.
[129]王树国，黄勇杰，张生.可见光图像中飞机目标的特征选择及提取[J].哈尔滨工业大学学报,2010,42(7):1056-1059
[130]黄洁,张海.利用支持向量机的飞机目标检测[J].电光与控制,2008,15(9):6-9
[131]周静，黄心汉，彭刚.基于多特征融合的飞机目标识别[J].华中科技大学学报(自然科学版),2009,37(1):38-41
[132]王彦杰,基于显著局部特征的视觉物体表示方法[博士学位论文][D].北京理工大学，2010
[133] L.Fei-Fei and P. Perona. A Bayesian hierarchical model for learning naturalscene categories[C]. CVPR2005,2:524-531
[134] Roberto Toldo,Umberto Castellani, Andrea Fusiello. A Bag of Words Approachfor3D Object Categorization[C].MIRAGE2009, LNCS5496:116-127
[135] Roberto Toldo, Umberto Castellani, Andrea Fusiello.The bag of words approachfor retrieval and categorization of3D objects [J]. The Visual Computer:International Journal of Computer Graphics-Special Issue on3D ObjectRetrieval,26(10),2010:1257-1268
[136] Diane Larlus,Jakob Verbeek,Frédéric Jurie. Category Level ObjectSegmentation by Combining Bag-of-Words Models with Dirichlet Processes andRandom Fields[J]. International Journal of Computer Vision,2009,88(2):238-253
[137]贾世杰，孔祥维，付海燕，金光.基于互补特征和类描述的商品图像自动分类[J].电子与信息学报,2010,32(10):2294-2300
[138]张子明，刘金刚.图片分类特征增强的统计方法.计算机工程与应用，2009,45(5):177-179
[139] C. Schmid. Beyond bags of features: Spatial pyramid matching for recognizingnatural scene categories [C]. in CVPR,2006:2169–2178
[140] J. Wu and J. M. Rehg. Beyond the euclidean distance: Creating effectivevisual codebooks using the histogram intersection kernel [C]. in ICCV,2009:630-637
[141] L. Yang, R. Jin, and R. Sukthankar. Unifying discriminative visual codebookgeneration with classifier training for object category reorganization[C].CVPR2008:1-8
[142]刘硕研,须德,冯松鹤,刘镝,裘正定.一种基于上下文语义信息的图像块视觉单词生成算法[J].电子学报,2010,38(5):1156-1161
[143]刘萍萍，赵宏伟，臧雪柏，戴金波.一种快速局部特征描述算法[J].自动化学报,2010,36(1):40-45
[144] J. Winn, A. Criminisi and T. Minka.Object categorization by learned universalvisual dictionary[C]. ICCV2005,2:1800-1807
[145] Frederic Jurie,Bill Triggs. Creating Effcient Codebooks for VisualRecognition[C].ICCV2005,1:604-610
[146] Xue Bai and Siwei Luo. Combining Bag of Words Model and Information TheoreticMethod for Image Clustering [J]. Advances in Neural Network Research andApplications,2010,67(5):423-430
[147]Coleman G B．Anrews H C．Image segmentation by clustering[J]．Proceeding ofthe IEEE，1979，67,5：773-785．
[148]Bezdek Je. Pattern Recognition with Fuzzy Objective FunctionAlgorithms[M]．Plenum Press，NewYork，1981
[149]彭丽.数据挖掘中几种划分聚类算法的比较及改进[硕士学位论文][D].大连理工大学，2008:25-26
[150]冯晓蒲，张铁峰.四种聚类方法之比较[J].微型机与应用.2010,29(16):1-3
[151]Yong Rui, Thomas S. Huang, Michael Ortega,etal. Relevance Feedback: A PowerTool for Interactive Content-Based Image Retrieval [J]. IEEE TRANSACTIONS ONCIRCUITS AND VIDEO TECHNOLOGY,2002:1-13
[152]周斌.多生物特征融合理论的研究与实验[博士学位论文][D]，清华大学,2007
[153]张铁柱，蒋宏.机载雷达和红外数据融合的智能目标识别[J].红外与激光工程,2010,39(4):756-760
[154]Jordi Inglada. Automatic recognition of man-made objects in high resolutionoptical remote sensing images by SVM classification of geometric imagefeatures[J]. ISPRS Journal of Photogrammetry&Remote Sensing,2007,62:236–248
[155]朱树先，张仁杰. BP和RBF神经网络在人脸识别中的比较[J].仪器仪表学报,2007,28(2):375-379
[156]谭琨,杜培军.基于支持向量机的高光谱遥感图像分类[J].红外与毫米波学报,2008,27(2):123-128
[157]林传力.基于内容的图像检索和Sift算法的应用[硕士论文][D].上海交通大学，2008.
[158]Craig Belcher,Yingzi Du. Region-based SIFT approach to irisrecognition[J].Optics and Lasers in Engineering.2009,47:139–147
[159] Yan Ke, Rahul Sukthankar.PCA-SIFT: A More Distinctive Representation forLocal Image Descriptors[C]. CVPR2004，2：506-513
[160]Luo Juan, Oubong Gwun. A Comparison of SIFT, PCA-SIFT and SURF[J].International Journal of Image Processing (IJIP).2010,3(4):143-152
[161]路小波,凌小静,刘斌.基于组合特征的车牌字符识别[J].仪器仪表学报,2006,27(7):698-701
[162]程咏梅,潘泉,张洪才,王刚.信息融合图像识别算法及其在三维飞机图像识别中的应用研究[J].航空学报.2004,25(2):176-179
[163]彭晓明，丁明跃，周成平，马茜.信息融合的飞机识别方法[J].光电工程，2003，30(6)：50-54
[164] R.Muralidharan, C.Chandrasekar.Object Recognition using SVM-KNN based onGeometric Moment Invariant [J]. International Journal of Computer Trends andTechnology,2011,1(1):215-220
[165]邹小波,赵杰文.基于小波去噪和支持向量机的苹果品种识别法[J].仪器仪表学报,2007,28(3):534-538
[166] C.De Stefano,A.Della Cioppa, A.Marcelli. An Adaptive Weighted Majority VoteRule for Combining Multiple Classifiers[C]. Proceedings16th InternationalConference on Pattern Recognition.2002,2:192-195
[2]李言俊，张科著.景象匹配与目标识别技术[M].西北工业大学出版社，2009：13-15
[3]刘宏鼎,秦世引.基于图像特征的运动目标识别与伺服跟踪[J].仪器仪表学报,2008,29(3):644-648
[4] M. Y. Mashor, M. K. Osman and,M. R. Arshad.3D Object Recognition Using2DMoments and HMLP Network[C]. Proceedings of the International Conference onComputer Graphics, Imaging and Visualization (CGIV’04),2004:126-130
[5]Wenjing Li, George Bebis, Nikolaos G. Bourbakis.3-D Object Recognition Using2-D Views [J].IEEE TRANSACTIONS ON IMAGE PROCESSING,2008,17(11):2236-2254
[6]Dudani SA,Breeding KJ,Mcghee Robert B.Aircraft Identification by Momentlnvariants [J]．IEEE TRANSACTIONS ON COMPUTERS,1977,26(1)：39-46
[7]K.ARBTER,WESLEY.E,SNYDERd. Application of Affine-Invariant FourierDescriptors to Recognition of3-D Objects [J]. IEEE Transactions on patternanalysis and machine intelligence,1990,12(7):640-647
[8] Reeves AP, Prokop RJ, Andrews SE. Three-dimensional shape analysis usingmoments and Fourier descriptors [J].IEEE TRANSACTIONS ON PATTERN ANALYSIS ANDMACHINE INTELLIGENCE,1988,(10):937-943
[9] Kamgar-Parsi,Behrooz,Kamgar-Parsi,Behzad,Jain, Anil K. Automatic aircraftrecognition: Toward using human similarity measure in a recognition system [C].Proceedings of the1999IEEE Computer Society Conference on Computer Visionand Pattern Recognition (CVPR'99),1999:268-273
[10] Das.Subhodev,Bhanu.Bir,Wu.Xing,etal. System for aircraft recognition inperspective aerial images [C]. Proceedings of the2nd IEEE Workshop onApplications of Computer Vision.1994:168-175
[11]Das.Subhodev, Bhanu.Bir.A system for model-based object recognition inperspective aerial images[J]. Pattern Recognition,1998,31(4):465-491
[12]Saidi.M.N.,Daoudi.K,Khenchaf.A,etal. Automatic target recognition ofaircraft models based on ISAR images [C]. International Geoscience and RemoteSensing Symposium (IGARSS),2009,4:685-688
[13] Saidi.M.N, Toumi. A,Hoeltzener.B,etal. Aircraft Target Recognition: A novelapproach for features extraction from ISAR images[C]. Radar Conference-Surveillance for a Safer World,2009:1-5
[14] Hmam, Hatem; Kim, Jijoong. Automatic aircraft recognition [C]. Proceedingsof SPIE-The International Society for Optical Engineering.2002:229-238
[15] G.Y. Chen, T.D. Bui, A. Krzyzak. Invariant pattern recognition using radon,dual-tree complex wavelet and Fourier transforms [J].PatternRecognition.2009,42:2013-2019
[16]杜亚娟.基于不变矩理论的自动目标识别技术研究（博士学位论文）[D].西北工业大学,2000
[17]刘准钆,程咏梅,潘泉等。证据冲突下自适应融合目标识别算法[J].航空学报，2010，31(7)：1426-1432
[18]杜鸿英，郭雷，李晖晖，刘坤.基于不变矩与证据理论的飞机序列图像识别[J].计算机仿真，2010，27(2):92-95
[19]李科.自动识别遥感光学图像中飞机目标的研究[硕士学位论文][D].国防科学技术大学，2005
[20]陈涛.图像仿射不变特征提取方法研究[博士学位论文][D].国防科技大学，2006
[21]唐涛.图像仿射不变特征及其在遥感图像目标识别中的应用[硕士学位论文][D].国防科技大学，2007
[22]李迎春.航空图像中机场停泊飞行器的识别技术研究[博士学位论文][D].吉林大学，2004
[23]郑南.遥感图像中飞机目标的识别分类算法研究[硕士学位论文][D].吉林大学，2007
[24]吴巍,彭嘉雄.飞行器结构特征提取与识别[J].华中科技大学学报(自然科学版),2004,32(1):70-72
[25]Jin Liu, Tianxu Zhang. Recognition of the blurred image by complex momentinvariants [J]. Pattern Recognition Letters.2005,24:1128–1138
[26]Liu Jin.Zhang TianXu. Fast algorithm for generation of moment invariants[J].Pattern Recognition.2004,37(10):1745-1756
[27]张天序著.成像自动目标识别[M].湖北科学技术出版社，2003
[28]安国平.基于DAM6416P平台的目标图像识别技术研究.[硕士学位论文][D].南京航空航天大学，2008
[29]蔡梅艳.基于TMS320C642DSP的目标图像识别研究.[硕士学位论文][D].南京航空航天大学，2007
[30]王振旻.目标图像识别算法研究及其在DSP高速处理系统中的实现.[硕士学位论文]
[D].南京航空航天大学，2008
[31] Zhang Feng, Liu Shang-qian,Wang Da-bao, Guan Wei. Aircraft recognition ininfrared image using wavelet moment invariants[J]. Image and VisionComputing,2009,27:313-318
[32]崔艳鹏,胡建伟,杨绍全.利用尺度不变量特征的ISAR二维像自动识别技术[J].西安电子科技大学学报(自然科学版),2009,36（4）：725-728
[33]胡国平,张守宏.多传感器协同探测目标的分类识别研究[J].西安电子科技大学学报(自然科学版),2009，36(3):443-447
[34]张名成,吴秀清,王鹏伟.基于闭合轮廓提取和部分特征匹配的飞机识别[J].计算机仿真,2006，23(11):193-197
[35]刘莉,吴秀清,牛宗标.模糊图像中的飞机识别方法[J].计算机仿真,2006,23(3):164-166
[36]王鹏伟，吴秀清，余珊.基于角点特征和自适应核聚类算法的目标识别[J].计算机工程,2007,33(6):179-181
[37]熊英，马慧敏.3维物体SIFT特征的提取与应用[J].中国图像图形学报.2010,15（5）:814-819
[38]王志远.基于电视跟踪的三维目标识别[硕士学位论文][D].长春理工大学，2008
[39]陈小超.基于几何特性的飞机目标特征提取技术的研究[硕士学位论文][D].长春理工大学，2006
[40]M. K. OSMAN, M. Y. MASHOR, M. R. ARSHAD.3D Object Recognition Using MultipleViews, Affine Moment Invariants and Multilayered Perceptron Network[J]. WSEASTransactions on SYSTEMS.2004,10(3):3065-3070
[41]廖海斌,王宏勇.航空机型快速有效识别方法研究[J].计算机工程与用.2008,44(34):185-187
[42] Hu M K.Visual pattern recognition by moment invariants[J]. IRE Transactionson Information Theory,1962,8:179-187
[43]刘进,张天序.图像不变矩的推广[J].计算机学报,2004,27(5):668-674
[44]张洁玉,陈强,白小晶,孙权森,夏德深.一种新的局部仿射不变特征描述符[J].光电子激光.2009，20(11):1503-1506
[45]孙洁,马惠敏,李凤亭.基于仿射不变性特征的视点空间划分[J].清华大学学报(自然科学版),2009,49(1):53-56
[46]王凤国,冯象初,张小波.平稳小波变换在仿射不变性目标识别中的应用[J].计算机工程与应用,2007,43(21):239-241
[47]杨昕梅,吴钦章,周进.仿射不变的运动目标识别方法[J].光学精密工程.2007,15(7):1112-1116
[48] Janne Heikkil. Pattern matching with affine moment descriptors[J]. PatternRecognition.2004,37:1825-1834
[49] Hongping Cai,Lin Lei,Yi Su. An Affine Invariant Region Detector Using the4thDifferential Invariant[C].19th IEEE International Conference on Tools withArtificial Intelligence.2007:540-543
[50]李兴唐,曹立华,王思雯.仿射变换的飞行器识别[J].光学精密工程.2009,17(2):402-408
[51] Jan Flusser and Tomas Suk. pattern recognition by affine moment invariants[J].pattern recognition,1993，26(1):167-174
[52]李迎春,陈贺新,赵铭,顼鹏飞;基于飞机目标的仿射不变矩研究[J].吉林大学学报，2003，21(5):84-88
[53]吴高洁，李超，熊璋.一种目标识别中基于关键点的仿射不变矩[J].北京航空航天大学学报,2009,35(9):1044-1047
[54] D.Shen,H.S.Ip Horace. Discriminative wavelet shape descriptors forrecognition of2-D patterns[J]. Pattern Recognition.1999,32(2):151–165
[55] Chong-Yaw Wee,Raveendran Paramesran,R. Mukundan. Fast computation of geometricmoments using a symmetric kernel[J]. Pattern Recognition,2008,41:2369–2380
[56] Dong Xu, Hua Li. Geometric moment invariants[J]. Pattern Recognition,2008,41:240–249
[57] T.P.Wallace,P.A.Wintz.An efficient three-dimensional aircraftrecognition algorithm using normalized Fourier descriptors[J].Comput.Graphics Image Processing,1980,13：99-126
[58]Zen Chen, Shinn-Ying Ho. Computer vision for robust3D aircraft recognitionwith fast library search[J]. Pattern Recognition,1991,24(5):375-390
[59] Esa Rahtu,Mikko Salo and Janne Heikkila. Affine Invariant Pattern RecognitionUsing Multi-scale Autoconvoltion[J]. IEEE Trans on Pattern Anlysis andMachine Intelligence,2005:908-918
[60]徐学强,汪渤,于家城等.一种新型不变矩在图像识别中的应用[J].光学术,2007,33(4):580-583
[61]黄波，赵继印，郑蕊蕊，李敏.基于多尺度自卷积归一化直方图的仿射不变量模式识别[J].电子学报,2011,39(1):64-69
[62] J. Flusser, T. Suk, and S. Saic, Recognition of blurred images by the methodof moments[J]. IEEE Trans.Image Process.,1996，5(3):533–538
[63] Hui Zhang, Huazhong Shu, Guoniu N. Han, Gouenou Coatrieux, Limin Luo, JeanLouis Coatrieux. Blurred Image Recognition by Legendre MomentInvariants[J].IEEE TRANSACTIONS ON IMAGE PROCESSING.2010.19(3):596-611
[64] ALIREZA KHOTANZAD AND YAW HUA HONG. Invariant Image Recognition byZernike Moments[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINEINTELLIGENCE.1990,12(5):489-497
[65]赵恒卓,杨春旭,胡正仪,王延平.基于线矩特征的破损目标识别[J].武汉大学学报(自然科学版),1997,43(5):650-654
[66]卢汉青,彭家雄，万发贯.角点在目标分类识别中的应用[J].数据和采集.1992，7(3):183-186
[67]曾刚,廖原,尹亮,胡正仪,王延平.拐点特征的提取和物体破损图象的识别[J].中国图像图形学报,1998,3(3):217-220
[68]曹健,高春晓,刘琼昕,贺跃.基于角点特征的目标识别方法[J].华中科技大学学报(自然科学版),2010,38(6):84-87
[69]季战领,冯晓毅,阎昆.一种ISAR图像中飞机目标识别的新特征[J].计算机工程,2010,36(23):192-196
[70]Georgios Kordelas, Petros Daras. Viewpoint independent object recognition incluttered scenes exploiting ray-triangle intersection and SIFT algorithms [J].Pattern Recognition43(2010)3833–3845
[71] D.G.Lowe. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2)：91-110
[72] Filip Krolupper, Jan Flusser. Polygonal shape description for recognition ofpartially occluded objects[J]. Pattern Recognition Letters,2007,28:1002-1011
[73] Chao Kan, Mandyam D. Srinath. Invariant character recognition with Zernikeand orthogonal Fourier-Mellin moments[J]. PatternRecognition,2002,35:143-144
[74] Tomas Suk, Jan Flusser. Combined blur and affine moment invariants and theiruse in pattern recognition[J]. Pattern Recognition,2003,36:2895–2907
[75]敬忠良，肖刚，李振华.图像融合--理论与应用[M].高等教育出版社，2007：105-107
[76]廖闻剑,成瑜.三维飞机自动识别的一种有效方法.[J].航空学报，1998，19（6）：730-735
[77] K.S.Fu. Syntactic Pattern Recognition and Applications [M]. Prentice Hall,1982
[78] Robert A. McLaughlin and Michael D.Alder. Recognition of Infra Red Imagesof Aircraft Rotated in Three Dimensions [R]. University of Western AustraliaTechnical Report，1995:95-104
[79] Shen-Chi Tien, Tsorng-Lin Chia，Yibin Lu. Using cross-ratios to model curvedata for aircraft recognition[J]，Pattern Recognition Letters.2003,24：2047–2060
[80] Wei Zhang, Bing Yu, Gregory J. Zelinsky, Dimitris Samaras。Object ClassRecognition Using Multiple Layer Boosting with Heterogeneous Features[C].IEEEComputer Society Conference on Computer Vision and Pattern Recognition(CVPR'05),2005，2：323-330
[81] J.-W. Hsieh, J.-M. Chen, C.-H. Chuang and K.-C. Fan，Aircraft type recognitionin satellite images[J]. IEEE Proc.-Vis. Image Signal Process.2005,152(3):307-315
[82] XU sheng, PENG Qicong.3D Object Recognition Using Multiple Features and NeuralNetwork [C].CIS2008:434-439
[83]侯一民,伦向敏.基于矩与角点特征的飞机目标识别[J].计算机工程与应用.2008,44(16):179-181
[84]曾万梅，吴庆宪，姜长生.基于组合不变矩特征的空中目标识别方法[J].电光与控制,2009,16(7):21-24
[85]苗常青,汪渤,付梦印等.电视图像目标实时分割与识别算法[J].北京理工大学学报,2005,25(9):786-790
[86]赵芹,周涛,舒勤.飞机红外图像的目标识别及姿态判断[J].红外技术,2007,29(3):167-169
[87]肖家庆,卢凌,李晟,聂明新.基于矩不变量的图像目标识别[J].武汉理工大学学报.2006,30(4):696-699
[88]马迎军.基于粗糙集与支持向量机的军用飞机识别算法[硕士论文][D].西北工业大学，2007:71-72
[89] Donghe Wang，Xin He，Wei Zhonghui， Huilong Yu. A Method of Aircraft ImageTarget Recognition Based on Modified PCA Features and SVM[C].The NinthInternational Conference on Electronic Measurement&Instruments,2009，4:117-881
[90] Soo Beom Park, Jae Won Lee, Sang Kyoon Kim.Content-based image classificationusing a neural network[J].Pattern Recognition Letters.2004，25:287–300
[91]梁明，孙仲康.人工神经网络的一种改进的B-P学习算法及其应用[C].中国神经网络首届学术大会论文集.1990：441-444
[92]A.A.Somaie,A.Badr and T.Salah. Aircraft Image Recognition UsingBack-Propagation.Radar[C]. CIE International Conference on, Proceedings，2001：498–501
[93] Shuangzi Sun，Lihong YuanYong Yang Xiaochao Chen. The Features Vector Researchon Target Recognition of Airplane[C].Proceedings of the11th Joint Conferenceon Information Sciences，2008:1-5
[94]张艳宁，郑江滨，侯云舒，赵荣椿.基于SOM和SVM的遥感图像目标识别[J].系统工程与电子技术,2002,24(7):9-11
[95]唐克,魏琪,杜涛.基于支持向量机的高空无人机侦察目标识别[J].火力与指挥控制.2010,35(3):82-85
[96]杨利英，覃征，王向华.多分类器融合实现机型识别[J].计算机工程与应用，2004：10-12
[97] J. Kittler and F.M. Alkoot.Sum versus Vote Fusion in Multiple ClassifierSystems [J].IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2003,25(1):110-115
[98]Bor-Chen Kuo,Chih-Sheng Huang,Hsiang-Chuan Liu,Chih-Cheng Hung.A fuzzy fusionalgorithm to combine multiple classifiers [C].IGARSS2009,3:685-688
[99]Dymitr Ruta,Bogdan Gabrys.An Overview of Classifier Fusion Methods[J].Computing and Information Systems,2000,7:1-10
[100] Dymitr Ruta,Bogdan Gabrys. A theoretical analysis of the limits of majorityvoting errors for multiple classifier systems[J].Pattern Analysis andApplications.2002,5(4):333-350
[101]韩建峰,杨哲海.组合分类器及其在高光谱影像分类中的应用[J].测绘科学技术学报.2007，24（3）:231-234
[102] Ahmed Al-Ani,Mohamed Deriche. A New Technique for Combining MultipleClassifiers using The Dempster-Shafer Theory of Evidence[J].Journal ofArtificial Intelligence Research2002,17:333-361
[103]蒋宏,田野.雷达专家系统目标识别和红外图像目标识别的D-S融合[J].航空科学技术.2010,2:30-33
[104]刘明,袁保宗,苗振江,唐晓芳.基于模糊规则的多分类器融合[J],电子与信息学报,2007,29(7):1707-1712
[105]马颂德.计算机视觉（计算理论与算法基础）[M]，科学出版社，1998:52-53
[106]章毓晋编著.图像工程(第2版)[M].清华大学出版社，2006:47-52
[107]郑南宁.计算机视觉与模式识别[M].国防工业出版社，1998:14-20
[108]（美）桑卡等著，艾海舟等译.图像处理、分析与机器视觉（第二版）[M].人民邮电出版社,2003:393-395
[109]陈柘，赵荣椿.几何不变性及其在3D物体识别中的应用[J].中国图像图形学报,2003,8(9):993-1000
[110]李玉山.数字视觉视频技术[M].西安：西安电子科技大学出版社，2006:128-129
[111]孙既祥.模式识别中的特征提取与计算机视觉不变量[M].国防工业出版社.2001:238-240
[112]李科,王润生,王程.一种用于飞机型号识别的树分类器方法[J].计算机工程与科学,2006,28(11):136-139
[113]夏良正，李久贤编著.数字图像处理(第2版)[M].东南大学出版社，2005:253-254
[114] Mark Nixon, Alberto Aguado. Feature Extraction and Image Processing(secondEdition)[M]，2008：311-314
[115] Gabriel Taubin,David B. Cooper.Object Recognition Based on Moment (orAlgebraic) Invariants[J]. Geometric Invariance in Computer Vision.1992:375-397
[116] Jan Flusser. Moment Invariants in Image Analysis[C]. Proceeding of worldacademy of science,engineering and technology,2006,11：196-201
[117] D. Shen, H.S.Ip. Horace, Discriminative wavelet shapedescriptors for recognition of2-D patterns[J]. Pattern Recognition.1999,32(2):151–165.
[118] Arbter K, Snyder WE,Burkhant H,etal. Application of affine-invariant fourierdescriptors to recognition of3D objects[J]. IEEE TransPAMI,1990,12(7):640-647
[119] Richard J. Prokop Anthony P. Reeves. A Survey of Moment-Based Techniques ForUnoccluded Object Representation and Recognition[J]. CVGIP: GraphicalModels and Image Processing,1992,54(5):438-460
[120]姚军，蒋晓瑜，黄应清.目标识别中Hu矩、Zernike矩和小波矩的比较[J].装甲兵工程学院学报.2006,20(3):34-36
[121]郭宇晨,马惠敏,廖庆敏.基于二维成像的三维物体形状特征分析[J].清华大学学报(自然科学版),2009,49(10):73-77
[122]卢汉清,彭嘉,万发贯.角点在目标识别分类中的应用[J].数据采集与处理,1992,7(3):182-186
[123] Krystian Mikolajczyk，Cordelia Schmid. A performance evaluation of localdescriptors[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.2005,27(10):1615-1630.
[124] Krystian Mikolajczyk, Bastian Leibe, Bernt Schiele.Local Features for ObjectClass Recognition[C]. IEEE International Conference on Computer Vision(ICCV'05).2005,2:1792-1799,
[125]张天序著.成像自动目标识别[M].湖北科学技术出版社，2005：263-269
[126]孙即祥.现代模式识别[M].高等教育出版社，2008：637-640
[127]边肇祺，张学工等编著.模式识别（第二版）[M].清华大学出版社，2000:296-303
[128] Vladimir Cherkassky and Yunqian Ma. Practical selection of SVM parametersand noise estimation for SVM regression [J]. Neural Networks,2004,17:113-126.
[129]王树国，黄勇杰，张生.可见光图像中飞机目标的特征选择及提取[J].哈尔滨工业大学学报,2010,42(7):1056-1059
[130]黄洁,张海.利用支持向量机的飞机目标检测[J].电光与控制,2008,15(9):6-9
[131]周静，黄心汉，彭刚.基于多特征融合的飞机目标识别[J].华中科技大学学报(自然科学版),2009,37(1):38-41
[132]王彦杰,基于显著局部特征的视觉物体表示方法[博士学位论文][D].北京理工大学，2010
[133] L.Fei-Fei and P. Perona. A Bayesian hierarchical model for learning naturalscene categories[C]. CVPR2005,2:524-531
[134] Roberto Toldo,Umberto Castellani, Andrea Fusiello. A Bag of Words Approachfor3D Object Categorization[C].MIRAGE2009, LNCS5496:116-127
[135] Roberto Toldo, Umberto Castellani, Andrea Fusiello.The bag of words approachfor retrieval and categorization of3D objects [J]. The Visual Computer:International Journal of Computer Graphics-Special Issue on3D ObjectRetrieval,26(10),2010:1257-1268
[136] Diane Larlus,Jakob Verbeek,Frédéric Jurie. Category Level ObjectSegmentation by Combining Bag-of-Words Models with Dirichlet Processes andRandom Fields[J]. International Journal of Computer Vision,2009,88(2):238-253
[137]贾世杰，孔祥维，付海燕，金光.基于互补特征和类描述的商品图像自动分类[J].电子与信息学报,2010,32(10):2294-2300
[138]张子明，刘金刚.图片分类特征增强的统计方法.计算机工程与应用，2009,45(5):177-179
[139] C. Schmid. Beyond bags of features: Spatial pyramid matching for recognizingnatural scene categories [C]. in CVPR,2006:2169–2178
[140] J. Wu and J. M. Rehg. Beyond the euclidean distance: Creating effectivevisual codebooks using the histogram intersection kernel [C]. in ICCV,2009:630-637
[141] L. Yang, R. Jin, and R. Sukthankar. Unifying discriminative visual codebookgeneration with classifier training for object category reorganization[C].CVPR2008:1-8
[142]刘硕研,须德,冯松鹤,刘镝,裘正定.一种基于上下文语义信息的图像块视觉单词生成算法[J].电子学报,2010,38(5):1156-1161
[143]刘萍萍，赵宏伟，臧雪柏，戴金波.一种快速局部特征描述算法[J].自动化学报,2010,36(1):40-45
[144] J. Winn, A. Criminisi and T. Minka.Object categorization by learned universalvisual dictionary[C]. ICCV2005,2:1800-1807
[145] Frederic Jurie,Bill Triggs. Creating Effcient Codebooks for VisualRecognition[C].ICCV2005,1:604-610
[146] Xue Bai and Siwei Luo. Combining Bag of Words Model and Information TheoreticMethod for Image Clustering [J]. Advances in Neural Network Research andApplications,2010,67(5):423-430
[147]Coleman G B．Anrews H C．Image segmentation by clustering[J]．Proceeding ofthe IEEE，1979，67,5：773-785．
[148]Bezdek Je. Pattern Recognition with Fuzzy Objective FunctionAlgorithms[M]．Plenum Press，NewYork，1981
[149]彭丽.数据挖掘中几种划分聚类算法的比较及改进[硕士学位论文][D].大连理工大学，2008:25-26
[150]冯晓蒲，张铁峰.四种聚类方法之比较[J].微型机与应用.2010,29(16):1-3
[151]Yong Rui, Thomas S. Huang, Michael Ortega,etal. Relevance Feedback: A PowerTool for Interactive Content-Based Image Retrieval [J]. IEEE TRANSACTIONS ONCIRCUITS AND VIDEO TECHNOLOGY,2002:1-13
[152]周斌.多生物特征融合理论的研究与实验[博士学位论文][D]，清华大学,2007
[153]张铁柱，蒋宏.机载雷达和红外数据融合的智能目标识别[J].红外与激光工程,2010,39(4):756-760
[154]Jordi Inglada. Automatic recognition of man-made objects in high resolutionoptical remote sensing images by SVM classification of geometric imagefeatures[J]. ISPRS Journal of Photogrammetry&Remote Sensing,2007,62:236–248
[155]朱树先，张仁杰. BP和RBF神经网络在人脸识别中的比较[J].仪器仪表学报,2007,28(2):375-379
[156]谭琨,杜培军.基于支持向量机的高光谱遥感图像分类[J].红外与毫米波学报,2008,27(2):123-128
[157]林传力.基于内容的图像检索和Sift算法的应用[硕士论文][D].上海交通大学，2008.
[158]Craig Belcher,Yingzi Du. Region-based SIFT approach to irisrecognition[J].Optics and Lasers in Engineering.2009,47:139–147
[159] Yan Ke, Rahul Sukthankar.PCA-SIFT: A More Distinctive Representation forLocal Image Descriptors[C]. CVPR2004，2：506-513
[160]Luo Juan, Oubong Gwun. A Comparison of SIFT, PCA-SIFT and SURF[J].International Journal of Image Processing (IJIP).2010,3(4):143-152
[161]路小波,凌小静,刘斌.基于组合特征的车牌字符识别[J].仪器仪表学报,2006,27(7):698-701
[162]程咏梅,潘泉,张洪才,王刚.信息融合图像识别算法及其在三维飞机图像识别中的应用研究[J].航空学报.2004,25(2):176-179
[163]彭晓明，丁明跃，周成平，马茜.信息融合的飞机识别方法[J].光电工程，2003，30(6)：50-54
[164] R.Muralidharan, C.Chandrasekar.Object Recognition using SVM-KNN based onGeometric Moment Invariant [J]. International Journal of Computer Trends andTechnology,2011,1(1):215-220
[165]邹小波,赵杰文.基于小波去噪和支持向量机的苹果品种识别法[J].仪器仪表学报,2007,28(3):534-538
[166] C.De Stefano,A.Della Cioppa, A.Marcelli. An Adaptive Weighted Majority VoteRule for Combining Multiple Classifiers[C]. Proceedings16th InternationalConference on Pattern Recognition.2002,2:192-195