基于半监督学习的遥感图像分类研究
|
摘要
随着卫星遥感技术的迅速发展,我们能够利用遥感技术动态、快速、准确地获得大量的遥感数据,尤其是高分辨率的遥感卫星图像。在遥感技术的应用中,通过遥感图像处理和判读来识别各种地表物体是一个非常主要的工作。无论是地物信息提取、土地动态变化检测、还是专题地图制作和遥感图像库的建立等都离不开分类。特别是随着遥感图像分辨率的不断提高,人们迫切要求从遥感图像中获得更多有用的数据和信息,遥感图像的分类在社会生活和经济建设中发挥着越来越重要的作用。
分类的目的是从图像中识别实际地物,进而提取地物信息。近年来随着计算机技术的快速发展,计算机识别分类已经成了遥感技术应用研究中的一个重要组成部分。遥感图像的分类主要有两个方法,一是目视判读,即根据工作人员的经验和知识与多种非遥感信息资料结合,按照一定的规律和方法对图像上的地表物体进行识别；另一种是遥感数字图像的计算机分类,遥感图像的计算机分类,是对遥感图像上的地物进行属性的识别和分类,是模式识别技术在遥感技术领域中的具体运用。
半监督学习是模式识别和机器学习中的重要研究领域。半监督学习方法结合了监督与非监督学习方法的优点,它同时利用有标记样本和大量的无标记样本,相比较传统的监督与非监督学习方法,半监督学习方法能够得到比较好的结果。
本文将半监督学习应用到遥感图像的分类中,通过查阅相关文献,分析和总结前人的工作经验,采用了两种半监督学习方法对遥感图像进行分类,通过实验验证了应用半监督方法进行遥感图像的分类具有非常重要的理论和现实意义。这不仅能减少由于对样本进行人工标记带来的时间和劳力上的浪费,又能有效提高分类的精度。
论文主要进行了以下几个方面的工作：
(1)讨论了遥感图像分类技术的研究现状及其发展趋势,并简要介绍了几种传统的遥感图像监督与非监督分类方法；
(2)介绍了半监督学习方法并对几种半监督算法进行了描述：包括基于生成式模型的半监督学习算法,自训练算法,基于判别式模型的半监督学习算法,基于图正则化框架的半监督学习算法,协同训练(Co-training)算法以及半监督聚类算法；
(3)详细讨论了协同训练(Co-training)算法,该方法是一种非常重要的半监督算法,但由于其要求样本的属性集要能够分割为两个相互冗余的子集,在很多的实际应用中,样本的属性集并不能满足此种分割,因此该方法不能够很好地被直接应用。本文以该算法为基础,将其进行改进,得到一个简化的基于多分类器的半监督分类算法,通过实验比较,该方法优于传统的监督式分类方法,并由于该算法对样本的属性集没有强制性要求,使得其比较适合实际的应用,最后将其应用于对遥感图像进行分类；
(4)介绍了直推式学习,讨论了直推式支持向量机(TSVM)的原理,TSVM方法是一种能同时利用有标记样本和无标记样本从而提高学习效果的方法,在遥感图像的分类中,我们能够利用到的已标记的样本个数较少,但却有大量的无标记样本,因此采用TSVM对遥感图像进行地物分类,通过实验可以得出TSVM方法能够有效地利用到大量的无标记样本的信息,并且随着无标记样本个数的增加,分类的精度能够得到一定的提高。
With the rapid development of remote sensing technology, we can obtain a large number of remote sensing images which play an important role in our practical applications, especially high-resolution remote sensing images. In the application of remote sensing technology, recognizing various ground objects through remote sensing disposal is one very important work. No matter acquiring information of ground objects、detecting dynamic change of grounds、or special map making and establishing image database can't depart from classification. Especially with the improving the resolution of remote sensing images, people press for more useful data and information from remote sensing images, the classification of remote sensing images is playing a more and more important action in social life and economic construction.
The aim of classification is recognizing practical ground objects from images, sequentially, extracting information of ground objects. With the fast development of computer technology nowadays, computer recognition classification has been a most important part of remote sensing technology. The classification of remote sensing images has two methods, one is visual interpretation, by combining workers' experience, knowledge and manifold non-remote sensing information together, according to stated rules and methods, recognize ground objects of images; the other is computer classification of remote sensing images. The computer classification of remote sensing images is a classification of recognizing ground objects' attributes, is pattern recognition applied in remote sensing technology.
Semi-supervised learning is an important research field of pattern recognition and machine learning. The semi-supervised learning combines advantage of supervised and unsupervised learning, it use labeled samples and abundant unlabeled samples, with the help of labeled samples, semi-supervised learning can achieve a better result.
This paper apply semi-supervised learning to the classification of remote sensing images, Through consulting some relevant documents, analyzing and summarizing forerunners' working experience, the paper adopts two kinds of semi-supervised learning methods to class remote sensing images, validates semi-supervised classification of remote sensing images is meaningful in theory and reality. It can reduce the waste of time and work force brought by labeling samples, and it can improve classification accuracy.
The main works are summarized as follows:
(1) Discussing the background of research and the development trend of remote sensing images classification, and introducing some traditional supervise and unsupervised classification of remote sensing images briefly.
(2) Introducing semi-supervised learning and describing a few classical semi-supervised algorithm: Including generative models, self-training, discriminant model, graph based methods, co-training and semi-supervised clustering.
(3) Giving a detailed introduction of Co-training, the method is a very important semi-supervised algorithm, but it requires the attributes of the samples must be able to split into two mutually redundant subsets, and in many practical applications, the attributes of samples can not meet such a split, so this method can not be applied well directly. This paper bases on the algorithm, to make improvements, gets a simplified Semi-supervised classification algorithm based on multi-classifier, through experiments, we can see the method is superior to the traditional supervised classification methods and more suitable for practical application, and applying this method to remote sensing image classification.
(4) Introducing transductive learning, and discussing the principle of Transductive Support Vector Machine (TSVM), TSVM can use labeled and unlabeled samples at the same time to improve the learning result.in remote sensing image classification, we can use only a few labeled samples, but a large number of unlabeled samples, so we use TSVM into the classification of remote sensing image, through experiment, we can see TSVM can utilize the information of the large number of unlabeled samples, and as the number of unlabeled samples increasing, the classification accuracy can be improved.
分类的目的是从图像中识别实际地物,进而提取地物信息。近年来随着计算机技术的快速发展,计算机识别分类已经成了遥感技术应用研究中的一个重要组成部分。遥感图像的分类主要有两个方法,一是目视判读,即根据工作人员的经验和知识与多种非遥感信息资料结合,按照一定的规律和方法对图像上的地表物体进行识别；另一种是遥感数字图像的计算机分类,遥感图像的计算机分类,是对遥感图像上的地物进行属性的识别和分类,是模式识别技术在遥感技术领域中的具体运用。
半监督学习是模式识别和机器学习中的重要研究领域。半监督学习方法结合了监督与非监督学习方法的优点,它同时利用有标记样本和大量的无标记样本,相比较传统的监督与非监督学习方法,半监督学习方法能够得到比较好的结果。
本文将半监督学习应用到遥感图像的分类中,通过查阅相关文献,分析和总结前人的工作经验,采用了两种半监督学习方法对遥感图像进行分类,通过实验验证了应用半监督方法进行遥感图像的分类具有非常重要的理论和现实意义。这不仅能减少由于对样本进行人工标记带来的时间和劳力上的浪费,又能有效提高分类的精度。
论文主要进行了以下几个方面的工作：
(1)讨论了遥感图像分类技术的研究现状及其发展趋势,并简要介绍了几种传统的遥感图像监督与非监督分类方法；
(2)介绍了半监督学习方法并对几种半监督算法进行了描述：包括基于生成式模型的半监督学习算法,自训练算法,基于判别式模型的半监督学习算法,基于图正则化框架的半监督学习算法,协同训练(Co-training)算法以及半监督聚类算法；
(3)详细讨论了协同训练(Co-training)算法,该方法是一种非常重要的半监督算法,但由于其要求样本的属性集要能够分割为两个相互冗余的子集,在很多的实际应用中,样本的属性集并不能满足此种分割,因此该方法不能够很好地被直接应用。本文以该算法为基础,将其进行改进,得到一个简化的基于多分类器的半监督分类算法,通过实验比较,该方法优于传统的监督式分类方法,并由于该算法对样本的属性集没有强制性要求,使得其比较适合实际的应用,最后将其应用于对遥感图像进行分类；
(4)介绍了直推式学习,讨论了直推式支持向量机(TSVM)的原理,TSVM方法是一种能同时利用有标记样本和无标记样本从而提高学习效果的方法,在遥感图像的分类中,我们能够利用到的已标记的样本个数较少,但却有大量的无标记样本,因此采用TSVM对遥感图像进行地物分类,通过实验可以得出TSVM方法能够有效地利用到大量的无标记样本的信息,并且随着无标记样本个数的增加,分类的精度能够得到一定的提高。
With the rapid development of remote sensing technology, we can obtain a large number of remote sensing images which play an important role in our practical applications, especially high-resolution remote sensing images. In the application of remote sensing technology, recognizing various ground objects through remote sensing disposal is one very important work. No matter acquiring information of ground objects、detecting dynamic change of grounds、or special map making and establishing image database can't depart from classification. Especially with the improving the resolution of remote sensing images, people press for more useful data and information from remote sensing images, the classification of remote sensing images is playing a more and more important action in social life and economic construction.
The aim of classification is recognizing practical ground objects from images, sequentially, extracting information of ground objects. With the fast development of computer technology nowadays, computer recognition classification has been a most important part of remote sensing technology. The classification of remote sensing images has two methods, one is visual interpretation, by combining workers' experience, knowledge and manifold non-remote sensing information together, according to stated rules and methods, recognize ground objects of images; the other is computer classification of remote sensing images. The computer classification of remote sensing images is a classification of recognizing ground objects' attributes, is pattern recognition applied in remote sensing technology.
Semi-supervised learning is an important research field of pattern recognition and machine learning. The semi-supervised learning combines advantage of supervised and unsupervised learning, it use labeled samples and abundant unlabeled samples, with the help of labeled samples, semi-supervised learning can achieve a better result.
This paper apply semi-supervised learning to the classification of remote sensing images, Through consulting some relevant documents, analyzing and summarizing forerunners' working experience, the paper adopts two kinds of semi-supervised learning methods to class remote sensing images, validates semi-supervised classification of remote sensing images is meaningful in theory and reality. It can reduce the waste of time and work force brought by labeling samples, and it can improve classification accuracy.
The main works are summarized as follows:
(1) Discussing the background of research and the development trend of remote sensing images classification, and introducing some traditional supervise and unsupervised classification of remote sensing images briefly.
(2) Introducing semi-supervised learning and describing a few classical semi-supervised algorithm: Including generative models, self-training, discriminant model, graph based methods, co-training and semi-supervised clustering.
(3) Giving a detailed introduction of Co-training, the method is a very important semi-supervised algorithm, but it requires the attributes of the samples must be able to split into two mutually redundant subsets, and in many practical applications, the attributes of samples can not meet such a split, so this method can not be applied well directly. This paper bases on the algorithm, to make improvements, gets a simplified Semi-supervised classification algorithm based on multi-classifier, through experiments, we can see the method is superior to the traditional supervised classification methods and more suitable for practical application, and applying this method to remote sensing image classification.
(4) Introducing transductive learning, and discussing the principle of Transductive Support Vector Machine (TSVM), TSVM can use labeled and unlabeled samples at the same time to improve the learning result.in remote sensing image classification, we can use only a few labeled samples, but a large number of unlabeled samples, so we use TSVM into the classification of remote sensing image, through experiment, we can see TSVM can utilize the information of the large number of unlabeled samples, and as the number of unlabeled samples increasing, the classification accuracy can be improved.
引文
[1]梅安新.遥感导论[M].北京：高等教育出版社,2001,1-3.
[2]汤国安.遥感数字图像处理[M].北京：科学出版社,2004,170-173.
[3]易星.半监督学习若干问题的研究[D].北京：清华大学,2004.
[4]祁亨年,杨建刚,方陆明.基于多类支持向量机的遥感图像分类及其半监督式改进策略[J].复旦学报(自然科学版),2004,781-784.
[5]陈定贵,周德民,吕宪国,等.三江平原红河自然保护区湿地遥感分类研究[J].遥感技术与应用,2007,22(4)：485-491.
[6]张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J].遥感学报,2006,10(1)：49-57.
[7]周志华,王珏.机器学习及其应用[M].北京：清华大学出版社,2007,259-275.
[8]Z.-H. Zhou and M. Li. Tri-training:Exploiting unlabeled data using three classifiers. IEEE Transactions on Knowledge and Data Engineering,2005, 17(11):1529-1541.
[9]X.J. Zhu. Semi-supervised learning literature survey [R]. University of Wisconsin-Madison, Tech Rep:1530,2005.
[10]Blum A, Mitchell T. Combining labeled and unlabeled data with co-training [C]. Proceedings of the 11 th Annual Conference on Computational Learning Theory, Madison, WI,1998:92-100.
[11]Vapnik V. The Nature of Statistical Learning [M].New York Springer.1995.
[12]Ge M, Du R, Zhang C C, Xu Y S, Fault diagnosis using support vector machine with an application in sheet metal stamping operations [J]. Mechanical Systems and Signal Processing,2004,18:143-159.
[13]Guo G D, Li S Z Content-based Audio Classification and Retrieval by Support Vector Machines [J].IEEE Trans on Neural Network,2003,14(1):209-215.
[14]Gammerman A, Vapnik V, Vowk V. Learning by transduction. In:Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence. Wisconsin,1998, 148-156.
[15]Joachims T. Transductive inference for text classification using support vector machines. In:Proceedings of the 16th International Conference on Machine Learning (ICML). San Francisco:Morgan Kaufmann Publishers,1999.200-209.
[16]Vapnik V. Statistical Learning Theory. John Wiley and Sons,1998.
[17]Bennett K. Combining support vector and mathematical programming methods for classification. In:Scholkopf B, Burges C, Smola A, eds. Advances in Kernel Methods——Support Vector Learning. MIT Press,1998.
[18]Branson K. A naive Bayes classifier using transductive inference for text classification.2001. http://www-cse.ucsd.edu/.
[19]Blum A, Mitchell T. Combining labeled and unlabeled data with co-training. In: Annual Conference on Computational Learning Theory (COLT'98),1998, 92-100.
[20]Nigam K, McCallum A, Mitchell T. Learning to classify text from labeled and unlabeled documents. In:Proceedings of the AAAI'98,1998.
[21]朱述龙,张占睦.遥感图像获取与分析[M].北京；科学技术出版社,2000.
[22]陈华,陈书海,张平,等.K-means算法在遥感分类中的应用[J].红外与激光工程.2000,29(2)：26-30.
[23]James J, Timothy J, et al. An improved hybrid clustering algorithm for natural sciences[J]. IEEE Transaction on Geoscience and Remote Sensing,2000,38 (2): 1016-1032.
[24]Lee Sanghoon, Crawford Melba M. Hierarchical clustering approach for unsupervised image classification of hyper spectral data [J]. International Geoscience and Remote Sensing Symposium(IGARSS).2004,2:941-944.
[25]Du Qian. Independent component analysis to hyperspectral image classification Proceedings of SPIE-The International Society for Optical Engineering [J]. Imagine Spectrometry X.2004,5546:366-373.
[26]Shah Chintan A, Arora Manoj K, Varshney Pramod K. Unsupervised classification of hyperspectral data:An ICA mixture model based approach International Journal of Remote Sensing.2004,25(2):481-487.
[27]Koltunov A, Ben-Dor E. Mixture density separation as a tool for high quality interpretation of multi-source sensing data and related issues [J]. International Journal of Remote Sensing.2004,5425:118-129.
[28]Salazar Jose S, PostBrian N. A novel distribution-free segmentation approach applied to multispectral thermal imager data. Proceedings of SPIE-The International Society for Optical Engineering.2004,5425:118-129.
[29]孙家柄.遥感原理与应用[M].武汉：武汉大学出版社,2002.
[30]Ediriwickrema. J, Khorram. S. Hierarchical Maximum-Likelihood Classification for Imp roved Accuracies [J]. IEEE Trans. on Geoscience and Remote Sensing, 1997,35(4):810-816.
[31]刘伟强,陈鸿,夏德深.基于马尔可夫随机场的快速图像分割[J].中国图象图形学报,2001,6(3)：228-233.
[32]刘德连,张建奇.一种基于纹理分割的遥感图像目标探测算法.红外与毫米波学报,2006,25(3)：236-240
[33]Dundar M. M, Landgrebe D.A. Toward an optimal supervised classifier for the analysis of hyperspectral data. Geoscience and Remote Sensing, IEEE Transactions on.2004,42(1):271-277.
[34]Rand Robert S. Spectral/spatial annealing of hyperspectral imagery initialized by a supervised classification method. Proceedings of SPIE-The International Society for Optical Engineering.2002,4725:242-253.
[35]Landgrebe David, Murat Dundar M. A model-based mixture-supervised classification approach in hyperspectral data analysis. IEEE Transactions on Geoscience and Remote Sensing.2002,40(12):2692-2699.
[36]Tony Jebara. Discriminative, Generative and Imitative Learning. PhD thesis, Massachusetts Inst.of Technology Media laboratory, Dec 2001.
[37]Tommi Jaakkola, Maria Meila, and Tony Jebara. Maximum entropy discrimination.Technical Report AITR-1668, Massachusetts Inst. of Technology AI lab,1999. http://www.ai.mit.edu/
[38]A.McCallum, R.Rosenfeld, T.Mitchell, and A. Ng. Improving text classification by shrinkage in a hierarchy of classes. In Proc.15th Intl. conf. on Machine Learning(ICML)[ICML98],1998.359-67.
[39]Roderick J. Little and Donald B.Rubin.Statistical analysis with missing data.Wiley, NewYork,1987.
[40]J.L. chafer. Analysis of Incomplete Multivariate Data. Chapman& all,1997.
[41]Kamal Nigam, Andrew Mccallum, Sebastian Thrun, Tom Mitchell, Text Classification from Labeled and Unlabeled Documents using EM, Machine Learning,2000,39:103-134.
[42]J. Larsen, A. Szymkowiak, and L. K. Hansen. Probabilistic Hierarchical Clustering with labeled and Unlabeled Data, invited submission for Int. Journal of Knowledge Based Intelligent Engineering Systems, 2001. http://citeseer.nj.nec.com/larsen01probabilistic.html
[43]Martin Szummer and Tommi Jaakkola. Kernel expansions with unlabeled examples. In Advances in Neural Information Processing Systems(NIPS)[NIP01], 2001.626-632.
[44]Martin Szummer and Tommi Jaakkola. Partially labeled classification with markov random walks.In Advances in Neural Information Processing Systems(NIPS)[NIP02],2002.945-952.
[45]Fabio Cozman,Ira Cohen, Marcelo Cirelo, Semi-Supervised Learning of Mixture Models, In Proc. of ICML2003.
[46]K. P. Bennett and A. Demiriz. Semi-supervised support vector machines, Advances in Neural Information Processing Systems, Cambridge, MA,1998, 10:368-374.
[47]Tobias Scheffer and Stefan Wrobel. Active learning of partially hidden markov models. In Proceedings of the ECML/PKDD Workshop on Instance Selection, 2001.
[48]Kiri Wagstaff, Claire Cardie, Seth Rogers, and Stefan Schroedl, Constrained K-means Clustering with Background Knowledge, ICML-2001.577-584
[49]Sugato Basu, Arindam Banerjee, Raymond J. Mooney:Semi-supervised Clustering by Seeding. ICML 2002.19-26.
[50]Charles C. Kemp, Thomas L. Griffiths, Sean Stromsten, Joshua B. Tenenbaum, Semi-Supervised Learning with Trees, In Proc. of NIPS 2003.
[51]Aharon Bar-Hillel, Tomer Hertz, Noam Shental, and Daphna Weinshall. Learning distance functions using equivalence relations. In Proc. of 20th International Conference on Machine Learning,2003.11-18.
[52]Fabien Letouzey, Francois Denis, and R'emi Gilleron. Learning from positive and unlabeled examples. In 11-th Intl. Conf. on Algorithmic Learning Theory (ALT), Sydney, Australia, December 2000.71-85.
[53]Bing Liu Liub, Philip S, Yu, Xiaoli Li. Partially Supervised Classification of Text Documents, Proc.19th Intl. Conf. on Machine Learning, Sydney, Australia, July 2002.387-394.
[54]Wee Sun Lee, Bing Liu, Learning with Positive and Unlabeled Examples Using Weighted Logistic Regression, In Proc. of ICML 2003.448-455.
[55]Blum, A. and Chawla, S. Learning from Labeled and Unlabeled Data using Graph Mincuts. In Proceedings of ICML 2001.
[56]M. Belkin, P. Niyogi, Using Manifold Structure for Partially Labeled Classification, Advances in Neural Information Processing Systems 15(NIPS 2002),2002.
[57]Xiaojin Zhu, Zoubin Ghahramani, John Lafferty, Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions, In Proc. of ICML 2003.
[58]Chapelle.O, J.Weston and B.Scholkopf, Cluster Kernels for Semi-Supervised Learning. Advances in Neural Information Processing Systems 15.
[59]F. d'Alche Buc, Y. Grandvalet, and C. Ambroise. Semi-supervised margin boost. In T.G.Dietterich, S.Becker, and Z. Ghahramani, editors, Advances in Neural Information Processing Systems 14. MIT Press,2002.
[60]Eric P. Xing, Andrew Y. Ng, Michael I. Jordan and Stuart Russell. Distance metric learning, with application to clustering with side-information, Advances in Neural Information Processing Systems. The MIT Press.
[61]M. Belkin, P. Niyogi. Semi-supervised learning on Riemannian manifolds. Machine Learning,2004,56(1-3):209-239.
[62]A. Blum, S. Chawla. Learning from labeled and unlabeled data using graph mincuts. In:Proceedings of the 18th International Conference on Machine Learning (ICML'01), San Francisco, CA,2001,19-26.
[63]A. Blum, T. Mitchell. Combining labeled and unlabeled data with co-training. In:Proceedings of the 11 th Annual Conference on Computational Learning Theory (COLT'98), Wisconsin, MI,1998,92-100.
[64]A.Dempster, N Laird, D Rubin, Maximum likelihood form incomplete data via the EM algorithm, Journal of the Royal Statistical Scotiety B,39:1-38,1977.
[65]D. Titterington, A. Smith, U. Makov, Statistical Analysis of Finite Mixture Distributions. Wiley Series in Probability and Mathematical Statistics, Wiley, 1st edition,1985.
[66]Joachims. SVMlight.2001. http://www-ai.cs.uni-dortmund.de/SOFTWARE/S VM_LIGHT/svm_light.eng.html.
[67]UCI repository of machine learning databases [EB/OL]. http://www.ics.uci.edu/mlearn/MLRepository.html.
[68]K.Bennett and A.Demiriz. Semi-supervised support vector machines. In NIPS, 1998.
[69]G.Fung and O.Mangasarian. Semi-supervised support vector machines for unlabeled data classification. In Optimization Methods and Software,2001.
[70]Lawrence N D, Jordan M I. Semi-supervised learning via Gaussian processes. In: Saul L K, Weiss Y, Bottou L, eds. Advances in Neural Information Processing System 17, Cambridge, MA:MIT Press,2005,753-760.
[71]Grandvalet Y Bengio Y. Semi-supervised learning by entropy minimization. In: Saul L K, Weiss Y, Bottou L, eds. Advances in Neural Information Processing System 17, Cambridge, MA:MIT Press,2005,529-539.
[72]Zhou D, Bousquet O, Lal T N, Weston J, Scholkopf B. Learning with local and global consistency. In:Thrun S, Saul L, Scholkopf B, eds. Advances in Neural Information Processing System 17, Cambridge, MA:MIT Press,2004,321-328.
[73]Mind-Der Yang,Yeh-Fen Yang. Genetic algorithm for unsupervised classification of remote sensing imagery. Image Processing:Algorithm and Systems Proc. Of SPIE-IS&T Electronic imaging.2004,5298:395-402.
[74]邱磊.李国辉.代科学.遥感图像的半监督的改进FCM算法[J].计算机应用研究,2006,252-260.
[75]Huang C, Davis L S. Townshend J R G. An assessment of support vector machines for land cover classification[J]. International Journal of Remote Sensing.2002,23:725-749.
[76]李金莲,刘晓玫,李恒鹏.SPOT-5影像纹理特征提取与土地利用信息识别方法[J].遥感学报,2006,10(6)：926-931.
[77]黄昕,张良培,李平湘.基于多尺度特征融合和支持向量机的高分辨率遥感影像分类[J].遥感学报,2007,11(1)：48-54.
[78]崔林丽,唐娉,赵忠明,等.一种基于对象和多种特征整合的分类识别方法研究[J].遥感学报,2006,10(1)：104-110.
[79]Demiriz A, Benneit KP, Embrechts MJ. Semi-supervised clustering using genetic algorithms[A]. Artificial Neural Networks in Engineering[C]. ANNIE299: 809-814.
[80]Wagstaff K, Cardie C, Rogers S, et al. Constrained K-Means clustering with background knowledge[A]. ICML[C],2001.577-584.
[81]Basu S, Benerjee A, Mooney RJ. Semi-supervised clustering by seeding[A]. ICML[C],2002.19-26.
[82]Klein D, Kamvar SD, Manning C. From instance-level constraints to space-level constraints:Making the most of prior knowledge in data clustering[A]. ICML [C],2002.307-314.
[83]Xing EP, NGAY, Jordan MI, et al. Distance metric learning with application to clustering with side-information[J]. Advances in Neural Information Processing Systems 15:50-512.
[84]Bilenko M, Basu S, Mooney RJ. Integrating constraints and metric learning in semi-supervise clustering[A], ICML[C],2004.
[85]陈毅松,汪国平,董事海.基于支持向量机的渐进直推式分类学习算法[J].软件学报,2003,14(3)：451-460.
[86]Zhang J, Zhang y, Zhou T. Classification of hyperspectral data using support vector machine[C]. In IEEE International Conference on Image Processing 2001: 882-885.
[87]Rozita Dara and Mohamed Kamel. Sharing Training Patterns among Multiple Classifiers MCS 2004, LNCS 3077.2004.243-252.
[88]杨余旺,杨静宇.多距离分类器组合试验在人脸识别中的应用.计算机工程.2005.31(5)：175-177.
[89]S.Lang and T.Blascher. Hierarchical object representation-Comparative multi-scale mapping of anthropogenic and natural features. International Archives of Photogrammetry, Remote Sensing and spatial information sciences.2003.34(3):181-186.
[90]蔡振江,王渝,张娟.基于离散平稳小波变换和FCM的纹理图像分割.计算机工程,2005,31(15)：142-143.
[2]汤国安.遥感数字图像处理[M].北京：科学出版社,2004,170-173.
[3]易星.半监督学习若干问题的研究[D].北京：清华大学,2004.
[4]祁亨年,杨建刚,方陆明.基于多类支持向量机的遥感图像分类及其半监督式改进策略[J].复旦学报(自然科学版),2004,781-784.
[5]陈定贵,周德民,吕宪国,等.三江平原红河自然保护区湿地遥感分类研究[J].遥感技术与应用,2007,22(4)：485-491.
[6]张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J].遥感学报,2006,10(1)：49-57.
[7]周志华,王珏.机器学习及其应用[M].北京：清华大学出版社,2007,259-275.
[8]Z.-H. Zhou and M. Li. Tri-training:Exploiting unlabeled data using three classifiers. IEEE Transactions on Knowledge and Data Engineering,2005, 17(11):1529-1541.
[9]X.J. Zhu. Semi-supervised learning literature survey [R]. University of Wisconsin-Madison, Tech Rep:1530,2005.
[10]Blum A, Mitchell T. Combining labeled and unlabeled data with co-training [C]. Proceedings of the 11 th Annual Conference on Computational Learning Theory, Madison, WI,1998:92-100.
[11]Vapnik V. The Nature of Statistical Learning [M].New York Springer.1995.
[12]Ge M, Du R, Zhang C C, Xu Y S, Fault diagnosis using support vector machine with an application in sheet metal stamping operations [J]. Mechanical Systems and Signal Processing,2004,18:143-159.
[13]Guo G D, Li S Z Content-based Audio Classification and Retrieval by Support Vector Machines [J].IEEE Trans on Neural Network,2003,14(1):209-215.
[14]Gammerman A, Vapnik V, Vowk V. Learning by transduction. In:Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence. Wisconsin,1998, 148-156.
[15]Joachims T. Transductive inference for text classification using support vector machines. In:Proceedings of the 16th International Conference on Machine Learning (ICML). San Francisco:Morgan Kaufmann Publishers,1999.200-209.
[16]Vapnik V. Statistical Learning Theory. John Wiley and Sons,1998.
[17]Bennett K. Combining support vector and mathematical programming methods for classification. In:Scholkopf B, Burges C, Smola A, eds. Advances in Kernel Methods——Support Vector Learning. MIT Press,1998.
[18]Branson K. A naive Bayes classifier using transductive inference for text classification.2001. http://www-cse.ucsd.edu/.
[19]Blum A, Mitchell T. Combining labeled and unlabeled data with co-training. In: Annual Conference on Computational Learning Theory (COLT'98),1998, 92-100.
[20]Nigam K, McCallum A, Mitchell T. Learning to classify text from labeled and unlabeled documents. In:Proceedings of the AAAI'98,1998.
[21]朱述龙,张占睦.遥感图像获取与分析[M].北京；科学技术出版社,2000.
[22]陈华,陈书海,张平,等.K-means算法在遥感分类中的应用[J].红外与激光工程.2000,29(2)：26-30.
[23]James J, Timothy J, et al. An improved hybrid clustering algorithm for natural sciences[J]. IEEE Transaction on Geoscience and Remote Sensing,2000,38 (2): 1016-1032.
[24]Lee Sanghoon, Crawford Melba M. Hierarchical clustering approach for unsupervised image classification of hyper spectral data [J]. International Geoscience and Remote Sensing Symposium(IGARSS).2004,2:941-944.
[25]Du Qian. Independent component analysis to hyperspectral image classification Proceedings of SPIE-The International Society for Optical Engineering [J]. Imagine Spectrometry X.2004,5546:366-373.
[26]Shah Chintan A, Arora Manoj K, Varshney Pramod K. Unsupervised classification of hyperspectral data:An ICA mixture model based approach International Journal of Remote Sensing.2004,25(2):481-487.
[27]Koltunov A, Ben-Dor E. Mixture density separation as a tool for high quality interpretation of multi-source sensing data and related issues [J]. International Journal of Remote Sensing.2004,5425:118-129.
[28]Salazar Jose S, PostBrian N. A novel distribution-free segmentation approach applied to multispectral thermal imager data. Proceedings of SPIE-The International Society for Optical Engineering.2004,5425:118-129.
[29]孙家柄.遥感原理与应用[M].武汉：武汉大学出版社,2002.
[30]Ediriwickrema. J, Khorram. S. Hierarchical Maximum-Likelihood Classification for Imp roved Accuracies [J]. IEEE Trans. on Geoscience and Remote Sensing, 1997,35(4):810-816.
[31]刘伟强,陈鸿,夏德深.基于马尔可夫随机场的快速图像分割[J].中国图象图形学报,2001,6(3)：228-233.
[32]刘德连,张建奇.一种基于纹理分割的遥感图像目标探测算法.红外与毫米波学报,2006,25(3)：236-240
[33]Dundar M. M, Landgrebe D.A. Toward an optimal supervised classifier for the analysis of hyperspectral data. Geoscience and Remote Sensing, IEEE Transactions on.2004,42(1):271-277.
[34]Rand Robert S. Spectral/spatial annealing of hyperspectral imagery initialized by a supervised classification method. Proceedings of SPIE-The International Society for Optical Engineering.2002,4725:242-253.
[35]Landgrebe David, Murat Dundar M. A model-based mixture-supervised classification approach in hyperspectral data analysis. IEEE Transactions on Geoscience and Remote Sensing.2002,40(12):2692-2699.
[36]Tony Jebara. Discriminative, Generative and Imitative Learning. PhD thesis, Massachusetts Inst.of Technology Media laboratory, Dec 2001.
[37]Tommi Jaakkola, Maria Meila, and Tony Jebara. Maximum entropy discrimination.Technical Report AITR-1668, Massachusetts Inst. of Technology AI lab,1999. http://www.ai.mit.edu/
[38]A.McCallum, R.Rosenfeld, T.Mitchell, and A. Ng. Improving text classification by shrinkage in a hierarchy of classes. In Proc.15th Intl. conf. on Machine Learning(ICML)[ICML98],1998.359-67.
[39]Roderick J. Little and Donald B.Rubin.Statistical analysis with missing data.Wiley, NewYork,1987.
[40]J.L. chafer. Analysis of Incomplete Multivariate Data. Chapman& all,1997.
[41]Kamal Nigam, Andrew Mccallum, Sebastian Thrun, Tom Mitchell, Text Classification from Labeled and Unlabeled Documents using EM, Machine Learning,2000,39:103-134.
[42]J. Larsen, A. Szymkowiak, and L. K. Hansen. Probabilistic Hierarchical Clustering with labeled and Unlabeled Data, invited submission for Int. Journal of Knowledge Based Intelligent Engineering Systems, 2001. http://citeseer.nj.nec.com/larsen01probabilistic.html
[43]Martin Szummer and Tommi Jaakkola. Kernel expansions with unlabeled examples. In Advances in Neural Information Processing Systems(NIPS)[NIP01], 2001.626-632.
[44]Martin Szummer and Tommi Jaakkola. Partially labeled classification with markov random walks.In Advances in Neural Information Processing Systems(NIPS)[NIP02],2002.945-952.
[45]Fabio Cozman,Ira Cohen, Marcelo Cirelo, Semi-Supervised Learning of Mixture Models, In Proc. of ICML2003.
[46]K. P. Bennett and A. Demiriz. Semi-supervised support vector machines, Advances in Neural Information Processing Systems, Cambridge, MA,1998, 10:368-374.
[47]Tobias Scheffer and Stefan Wrobel. Active learning of partially hidden markov models. In Proceedings of the ECML/PKDD Workshop on Instance Selection, 2001.
[48]Kiri Wagstaff, Claire Cardie, Seth Rogers, and Stefan Schroedl, Constrained K-means Clustering with Background Knowledge, ICML-2001.577-584
[49]Sugato Basu, Arindam Banerjee, Raymond J. Mooney:Semi-supervised Clustering by Seeding. ICML 2002.19-26.
[50]Charles C. Kemp, Thomas L. Griffiths, Sean Stromsten, Joshua B. Tenenbaum, Semi-Supervised Learning with Trees, In Proc. of NIPS 2003.
[51]Aharon Bar-Hillel, Tomer Hertz, Noam Shental, and Daphna Weinshall. Learning distance functions using equivalence relations. In Proc. of 20th International Conference on Machine Learning,2003.11-18.
[52]Fabien Letouzey, Francois Denis, and R'emi Gilleron. Learning from positive and unlabeled examples. In 11-th Intl. Conf. on Algorithmic Learning Theory (ALT), Sydney, Australia, December 2000.71-85.
[53]Bing Liu Liub, Philip S, Yu, Xiaoli Li. Partially Supervised Classification of Text Documents, Proc.19th Intl. Conf. on Machine Learning, Sydney, Australia, July 2002.387-394.
[54]Wee Sun Lee, Bing Liu, Learning with Positive and Unlabeled Examples Using Weighted Logistic Regression, In Proc. of ICML 2003.448-455.
[55]Blum, A. and Chawla, S. Learning from Labeled and Unlabeled Data using Graph Mincuts. In Proceedings of ICML 2001.
[56]M. Belkin, P. Niyogi, Using Manifold Structure for Partially Labeled Classification, Advances in Neural Information Processing Systems 15(NIPS 2002),2002.
[57]Xiaojin Zhu, Zoubin Ghahramani, John Lafferty, Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions, In Proc. of ICML 2003.
[58]Chapelle.O, J.Weston and B.Scholkopf, Cluster Kernels for Semi-Supervised Learning. Advances in Neural Information Processing Systems 15.
[59]F. d'Alche Buc, Y. Grandvalet, and C. Ambroise. Semi-supervised margin boost. In T.G.Dietterich, S.Becker, and Z. Ghahramani, editors, Advances in Neural Information Processing Systems 14. MIT Press,2002.
[60]Eric P. Xing, Andrew Y. Ng, Michael I. Jordan and Stuart Russell. Distance metric learning, with application to clustering with side-information, Advances in Neural Information Processing Systems. The MIT Press.
[61]M. Belkin, P. Niyogi. Semi-supervised learning on Riemannian manifolds. Machine Learning,2004,56(1-3):209-239.
[62]A. Blum, S. Chawla. Learning from labeled and unlabeled data using graph mincuts. In:Proceedings of the 18th International Conference on Machine Learning (ICML'01), San Francisco, CA,2001,19-26.
[63]A. Blum, T. Mitchell. Combining labeled and unlabeled data with co-training. In:Proceedings of the 11 th Annual Conference on Computational Learning Theory (COLT'98), Wisconsin, MI,1998,92-100.
[64]A.Dempster, N Laird, D Rubin, Maximum likelihood form incomplete data via the EM algorithm, Journal of the Royal Statistical Scotiety B,39:1-38,1977.
[65]D. Titterington, A. Smith, U. Makov, Statistical Analysis of Finite Mixture Distributions. Wiley Series in Probability and Mathematical Statistics, Wiley, 1st edition,1985.
[66]Joachims. SVMlight.2001. http://www-ai.cs.uni-dortmund.de/SOFTWARE/S VM_LIGHT/svm_light.eng.html.
[67]UCI repository of machine learning databases [EB/OL]. http://www.ics.uci.edu/mlearn/MLRepository.html.
[68]K.Bennett and A.Demiriz. Semi-supervised support vector machines. In NIPS, 1998.
[69]G.Fung and O.Mangasarian. Semi-supervised support vector machines for unlabeled data classification. In Optimization Methods and Software,2001.
[70]Lawrence N D, Jordan M I. Semi-supervised learning via Gaussian processes. In: Saul L K, Weiss Y, Bottou L, eds. Advances in Neural Information Processing System 17, Cambridge, MA:MIT Press,2005,753-760.
[71]Grandvalet Y Bengio Y. Semi-supervised learning by entropy minimization. In: Saul L K, Weiss Y, Bottou L, eds. Advances in Neural Information Processing System 17, Cambridge, MA:MIT Press,2005,529-539.
[72]Zhou D, Bousquet O, Lal T N, Weston J, Scholkopf B. Learning with local and global consistency. In:Thrun S, Saul L, Scholkopf B, eds. Advances in Neural Information Processing System 17, Cambridge, MA:MIT Press,2004,321-328.
[73]Mind-Der Yang,Yeh-Fen Yang. Genetic algorithm for unsupervised classification of remote sensing imagery. Image Processing:Algorithm and Systems Proc. Of SPIE-IS&T Electronic imaging.2004,5298:395-402.
[74]邱磊.李国辉.代科学.遥感图像的半监督的改进FCM算法[J].计算机应用研究,2006,252-260.
[75]Huang C, Davis L S. Townshend J R G. An assessment of support vector machines for land cover classification[J]. International Journal of Remote Sensing.2002,23:725-749.
[76]李金莲,刘晓玫,李恒鹏.SPOT-5影像纹理特征提取与土地利用信息识别方法[J].遥感学报,2006,10(6)：926-931.
[77]黄昕,张良培,李平湘.基于多尺度特征融合和支持向量机的高分辨率遥感影像分类[J].遥感学报,2007,11(1)：48-54.
[78]崔林丽,唐娉,赵忠明,等.一种基于对象和多种特征整合的分类识别方法研究[J].遥感学报,2006,10(1)：104-110.
[79]Demiriz A, Benneit KP, Embrechts MJ. Semi-supervised clustering using genetic algorithms[A]. Artificial Neural Networks in Engineering[C]. ANNIE299: 809-814.
[80]Wagstaff K, Cardie C, Rogers S, et al. Constrained K-Means clustering with background knowledge[A]. ICML[C],2001.577-584.
[81]Basu S, Benerjee A, Mooney RJ. Semi-supervised clustering by seeding[A]. ICML[C],2002.19-26.
[82]Klein D, Kamvar SD, Manning C. From instance-level constraints to space-level constraints:Making the most of prior knowledge in data clustering[A]. ICML [C],2002.307-314.
[83]Xing EP, NGAY, Jordan MI, et al. Distance metric learning with application to clustering with side-information[J]. Advances in Neural Information Processing Systems 15:50-512.
[84]Bilenko M, Basu S, Mooney RJ. Integrating constraints and metric learning in semi-supervise clustering[A], ICML[C],2004.
[85]陈毅松,汪国平,董事海.基于支持向量机的渐进直推式分类学习算法[J].软件学报,2003,14(3)：451-460.
[86]Zhang J, Zhang y, Zhou T. Classification of hyperspectral data using support vector machine[C]. In IEEE International Conference on Image Processing 2001: 882-885.
[87]Rozita Dara and Mohamed Kamel. Sharing Training Patterns among Multiple Classifiers MCS 2004, LNCS 3077.2004.243-252.
[88]杨余旺,杨静宇.多距离分类器组合试验在人脸识别中的应用.计算机工程.2005.31(5)：175-177.
[89]S.Lang and T.Blascher. Hierarchical object representation-Comparative multi-scale mapping of anthropogenic and natural features. International Archives of Photogrammetry, Remote Sensing and spatial information sciences.2003.34(3):181-186.
[90]蔡振江,王渝,张娟.基于离散平稳小波变换和FCM的纹理图像分割.计算机工程,2005,31(15)：142-143.