基于粗糙集理论的RBF神经网络在土地利用/覆盖分类中的应用研究
|
摘要
近年来,从事全球环境变化研究的科学家逐步认识到土地利用/覆盖变化研究在全球环境变化研究中的重要性和必要性,并逐渐加强了这方面的研究。由于不同领域遥感图像的应用对遥感图像处理提出了不同的要求,所以图像处理中重要的环节——图像分类也就显得尤为重要。探索一种高效准确的分类方法成为遥感图像分类研究的热点。
本研究将粗糙集作为神经网络的预处理单元,利用粗糙集消除冗余特征,减少神经网络的输入节点,降低了网络规模,加快了训练速度。粗糙集神经网络利用粗糙集原理进行知识的表达、推理和简化,利用神经网络的并行特点完成网络学习运算,能更有效地处理不确定、不精确及冗余的数据。
本文在前人研究的基础上,把粗糙集理论、遗传算法、神经网络等理论和方法有机结合,力图从数学形态学的角度而不是传统的统计学角度实现土地利用/覆盖信息的分类。其具体研究工作可以归纳为以下几个方面：
(1)根据粗糙集理论基本原理与算法,结合粗糙集在图像处理中的研究现状,找到其在遥感图像分类中的理论支持。
(2)根据遥感数据的特点,提出粗糙集理论在处理遥感数据不确定性中的优势,分析几种粗糙集框架下的遥感信息的知识发现和表达方法,为研究制定合理有效的技术实现手段。
(3)在遥感图像的预处理中,采用了正射校正和辐射校正相结合的办法,有效减小数据的空间域和频率域的误差。
(4)在粗糙集属性简约中的辐射量度决策信息离散化中,采用了遗传算法的方式,弥补了粗糙集核约简存在的不足。
结果表明,粗糙集简约后的决策信息放入RBF神经网络中进行运算,输出结果与BP网络运算结果进行对比,在运算时间和测试精度上均优于BP网络。虽然基于粗糙集理论的RBF神经网络遥感图像分类模型可以解决土地利用/覆盖分类中的一些问题,但仍然需要地形因子等地理信息、地学知识、专家知识的辅助决策支持,才能够有效提高分类识别类型及精度。
Nowadays, the scientists engaged in global environmental research change gradually realized that land use/land cover change research in global environmental change research is importance and necessity, and gradually stepped up this kind of research. As different areas of the application of remote sensing images of remote sensing image processing to a different request, so the remote sensing image classify is particularly important. To explore an efficient and accurate classify become a hot spots of research in this area.
This research will be rough set as a neural network pretreatment unit, using rough sets to eliminate redundant features to reduce the importation of neural network nodes, reducing the size of network, speed up the training pace. Rough sets neural networks using rough set the principle of knowledge, reasoning and simplification, the use of neural network parallel computing features complete net study, to more effectively deal with uncertainty, imprecise and redundant data.
In this paper, on the basis of previous studies, the rough set theory, genetic algorithms, neural networks, and other theory and methods organic combination, in an attempt to mathematical morphology from the perspective rather than the traditional statistical point of view to achieve land use/land cover information classification. Their specific research work can be summarized in the following areas:
(1) According to rough set of basic principles and algorithms, the combination of rough set in image processing of the status, found out the the theoretical to support the remote sensing image classify.
(2) According to the characteristic of the remote sensing data, found out the rough set theory dealing with the uncertainty of remote sensing data in the advantage, analysed the several framework of the rough set to remote sensing information and knowledge mining, ways to study and formulate reasonable and effective means of technology.
(3) At the remote sensing image preprocessing, using the ortho-correction and a combination of radiation calibration methods, to effectively reduce the data space domain and frequency domain error.
(4) At the rough set of attributes simple to measure the radiation dispersion of information for decision-making, using a genetic algorithm, make up a rough set of nuclear reduction of the deficiencies.
The results showed that:after the rough set of simple information for decision-making add to RBF neural network for operation, compared with the results, computing time and accuracy tests on the network are better than BP. Although based on the rough set theory RBF neural network of the remote sensing image classify model can solve some of the problems about the land use/land cover classify, but still need to topographical factors such as geographic information, and knowledge and expertise to support the decision-making, in order to effectively improve the classify type and accuracy.
本研究将粗糙集作为神经网络的预处理单元,利用粗糙集消除冗余特征,减少神经网络的输入节点,降低了网络规模,加快了训练速度。粗糙集神经网络利用粗糙集原理进行知识的表达、推理和简化,利用神经网络的并行特点完成网络学习运算,能更有效地处理不确定、不精确及冗余的数据。
本文在前人研究的基础上,把粗糙集理论、遗传算法、神经网络等理论和方法有机结合,力图从数学形态学的角度而不是传统的统计学角度实现土地利用/覆盖信息的分类。其具体研究工作可以归纳为以下几个方面：
(1)根据粗糙集理论基本原理与算法,结合粗糙集在图像处理中的研究现状,找到其在遥感图像分类中的理论支持。
(2)根据遥感数据的特点,提出粗糙集理论在处理遥感数据不确定性中的优势,分析几种粗糙集框架下的遥感信息的知识发现和表达方法,为研究制定合理有效的技术实现手段。
(3)在遥感图像的预处理中,采用了正射校正和辐射校正相结合的办法,有效减小数据的空间域和频率域的误差。
(4)在粗糙集属性简约中的辐射量度决策信息离散化中,采用了遗传算法的方式,弥补了粗糙集核约简存在的不足。
结果表明,粗糙集简约后的决策信息放入RBF神经网络中进行运算,输出结果与BP网络运算结果进行对比,在运算时间和测试精度上均优于BP网络。虽然基于粗糙集理论的RBF神经网络遥感图像分类模型可以解决土地利用/覆盖分类中的一些问题,但仍然需要地形因子等地理信息、地学知识、专家知识的辅助决策支持,才能够有效提高分类识别类型及精度。
Nowadays, the scientists engaged in global environmental research change gradually realized that land use/land cover change research in global environmental change research is importance and necessity, and gradually stepped up this kind of research. As different areas of the application of remote sensing images of remote sensing image processing to a different request, so the remote sensing image classify is particularly important. To explore an efficient and accurate classify become a hot spots of research in this area.
This research will be rough set as a neural network pretreatment unit, using rough sets to eliminate redundant features to reduce the importation of neural network nodes, reducing the size of network, speed up the training pace. Rough sets neural networks using rough set the principle of knowledge, reasoning and simplification, the use of neural network parallel computing features complete net study, to more effectively deal with uncertainty, imprecise and redundant data.
In this paper, on the basis of previous studies, the rough set theory, genetic algorithms, neural networks, and other theory and methods organic combination, in an attempt to mathematical morphology from the perspective rather than the traditional statistical point of view to achieve land use/land cover information classification. Their specific research work can be summarized in the following areas:
(1) According to rough set of basic principles and algorithms, the combination of rough set in image processing of the status, found out the the theoretical to support the remote sensing image classify.
(2) According to the characteristic of the remote sensing data, found out the rough set theory dealing with the uncertainty of remote sensing data in the advantage, analysed the several framework of the rough set to remote sensing information and knowledge mining, ways to study and formulate reasonable and effective means of technology.
(3) At the remote sensing image preprocessing, using the ortho-correction and a combination of radiation calibration methods, to effectively reduce the data space domain and frequency domain error.
(4) At the rough set of attributes simple to measure the radiation dispersion of information for decision-making, using a genetic algorithm, make up a rough set of nuclear reduction of the deficiencies.
The results showed that:after the rough set of simple information for decision-making add to RBF neural network for operation, compared with the results, computing time and accuracy tests on the network are better than BP. Although based on the rough set theory RBF neural network of the remote sensing image classify model can solve some of the problems about the land use/land cover classify, but still need to topographical factors such as geographic information, and knowledge and expertise to support the decision-making, in order to effectively improve the classify type and accuracy.
引文
[1]Z.Pawlak Rough sets[J]. International Journal of computer and Information Sciences,1982; (11):341-356.
[2]Z. Pawlak Rough Sets Theory and it's Application to Data Analysis [J]. Cybernetics System,An International Journal,1998,29:667-668.
[3]Chmielewski M R, Grzymala-Busse J W. Global discratization of continuous attributes as preprocessing for machine learning[J]. International Journal of Approximate Reasoning,1996,15:319-331.
[4]Z. Pawlak Rough sets:Theoretical Aspects of Reasoning about Data[A]. Boston:Kluwer Academic Publishers,1991.
[5]Chan C C. A rough set approach to attribute generalization in data mining [J]. Journal of Information Sciences,1998,107:169-176.
[6]Lingras P J, Yao Y Y, Data mining using extenions of the rough set model [J]. Journal of the American Society for Information Science,1998,49(5):415-422.
[7]Mc Sherry D. Knowledge discovery by inspection[J]. Decision Support Systems,1997,21: 43-47
[8]Z. Pawlak Rough sets approach to Knowledge-based decision support[J]. European Journal of Operational Research,1997,99:48-57.
[9]Pomerol J C. Artificial intelligence and human decision making(J]. European Journal of Operational Research,1997,99:3-25.
[10]张文修,吴伟志,梁吉业,李德玉.粗糙集理论与方法.科学出版社.2001.7.
[11]周开利,康耀红.神经网络模型及其Matlab仿真程序设计[M].北京：清华大学出版社,2005,12.
[12]哈斯巴干.神经网络及其组合算法的遥感数据分类研究[D].北京：中国科学院研究生院,2003.
[13]李小涛.地统计学和神经网络在遥感影像分类中的应用研究[D].山东：山东科技大学,2001,9.
[14]杨吟冬.基于径向基函数神经网络的曲面(线)重构的仿真研究[D].广西：广西大学,2007,6.
[15]Robert M. Texture Features for Image Classification[J]. IEEE Transactions On System, Man and Cybernetic, vol. SMC-3, No.6, Nov 1973:610-621.
[16]Unser M. Sum and difference histograms for texture classification [J], IEEE Trans PAMI Vol.PAMI-8,Jan 1986.
[17]Benedoltsson J A. Neural network approaches versus statistical methods in classification of multisource remote sensing data[J]. IEEE Trans. Geoscience and Remote sensing, vol.28, July 1990:540-552.
[18]Bischof H, Pinz A J. Multispectral Classification of Landsat-Images Using Neural Networks [J].IEEE Trans. on Geoscience and Remote Sensing 1992,30(3):482-490.
[19]Heermann P D. Classification of multispectral remote sensing data using a back-propagation neural network[J]. IEEE Trans. Geoscience and Remote sensing, vol.30, Jan.1992:81-88.
[20]Hush D R. Progress in supervised neural networks [J]. IEEE Signal processing magazine, vol.10, No.1,1993:89-90.
[21]Salu and Y, Tilton J Classification of Multispectral Image Data by the Binary Diamond Neural Networks and by Nonparametric Pixel-by-Pixel Methods [J]. IEEE Trans On Geoscience and Remote Sensing.1993,31,31 (3):606-617.
[22]Haysin S. Neural networks:A comprehensive foundation[M]New York, NY:Macmilan,1994.
[23]Yamazaki T, Gingras D. Image Classification Using Spectral and Information Based on MAR Models[J]. IEEE Trans on Image Processing.1995,14(9):1333-1339.
[24]Egmont-Peterson, M.; De Ridder, D., and Handels, H. Image processing with neural networks-a review. Pattern Recognition,2002,35,2279-2301.
[25]CONGER, C.L.; FLETCHER, C.H., and BARBEE, M. Artificial Neural Network Classification of Sand in All Visible Submarine and Subaerial Regions of a Digital Image. Journal of Coastal Research,2005,21(6),1173-1177.
[26]Ed iriw ickrema J Khorran S H ierarchical Maxinum-Likelihood Classification for Improved Accuracies [J]. IEEE Trans on Geoscience and Remote Sensing 1997, 35(4):810-816.
[27]M clachlaug J Basfold K E.The EM A lgorithm and Extensions[M].New York John Wiley,1997.
[28]朱大奇,史慧.人工神经网络原理及应用.北京：科学出版社,2006：1.
[29]李石华,王金亮,陈姚,等.遥感图像分类方法研究综述[J].国土源遥感,2005,64(2)：1-6.
[30]傅肃性.遥感专题分析与地学图谱[M].北京：科学出版社,2002.
[31]孙家抦.遥感原理与应用[M].武汉：武汉人学出版社,2002.
[32]林培.农业遥感[M].北京：北京农业人学出版社,1991.
[33]梅安新,彭望绿,秦其明,等.遥感导论[M].北京：高等教育出版社,2001.
[34]于秀兰,莫红.Markcov随机场模型在多光谱遥感图像分类中的应用[J].中国农业资源与区划,1999,20(5)：48-53.
[35]朱建华,刘政凯,俞能海.一种多光谱遥感图像的自适应最小距离分类方法[J].中国图象图形学报,2000,5(1)：21-23.
[36]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.
[37]萧嵘,孙晨.一种具有容噪性能的SVM多值分类器[J].计算机研究与发展,2000,37(9)：1071-1075.
[38]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.
[39]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.
[40]王志刚,朱振海,等.光谱角度填图方法及其在岩性识别中的应用[J].遥感学报,1999,3(1)：60-65.
[41]吴革洪,高才松,刘玉民.聚类分析在油藏分类中的应用[J].断块油气田,2001,8(1)：36-37.
[42]贺德化,朱锋峰,彭英伟.有类间距离因素聚类结果的比较分析[J].运筹学学报,1998,2(2)：36-41.
[43]李祚泳.用BP神经网络实现多波段遥感图像的监督分类[J].红外与毫米波学报,1998,17(2)：153-156.
[44]李强,王正志.基于人工神经网络和经验知识的遥感信息分类综合方法[J].自动化学报,2000,26(2)：233-238.
[45]骆剑承,周成虎,杨艳.基于径向基函数(RBF)映射理论的遥感影像分类模型研究[J].中国图象图形学报,2000,5(2)：94-99.
[46]王耀南.小波神经网络的遥感图像分类[J].中国图象图形学报,1999,4(5)：368-371.
[47]阎静,王坟,李湘阁.利用神经网络方法提取水稻种植而积—以湖北省双季水稻为例[J].遥感学报,2001,5(3)：227-230.
[48]Ziarko W. Rough Sets, Fuzzy Sets and Knowledge Discovery. Springer-Verge.1994.
[49]魏敏洁,刘健勤.粗糙集的RBF表示与非监督模式分类[J].湘潭征业学院学报,1998,13(2)：20-23.
[50]徐立中,王慧敏,刘美林,等.粗糙集理论在图像增强中的应用[J].数据采集与处理,1999,14(3)：307-310
[51]徐立中,王慧斌,杨锦堂.基于粗糙集理论的图像增强方法[J].仪器仪表学报,2000,21(5)：514-516.
[52]刘燕,张学庆,杨绍国.一种基于粗糙集分类的图像压缩方法[J].物探化探计算技术,2002,24(2)：174-177.
[53]董广军,范永弘,罗睿.基于粗糙集理论的遥感影像分类研究[J].计算机工程与应用,2003.13：103-105
[54]郭海涛,田坦,张春田,朱昊.利用粗糙集和属性直方图的图像增强方法[J].光电工程,2005,32(3)：51-53.
[55]王晓辉,张少敏,武中利.基于粗糙集图像分层算法的研究[J].华北电力大学学报,2005,32(2)：75-79.
[56]陈素玲,刘文奇.一种基于颜色特征的图像分类检索与约简方法[J].昆明理工大学学报(理工版),2005,30(6)：117-120.
[57]王胜科,王知衍,吴志成.一种基于粗糙集理论的票据图像识别分类方法[J].微计算机信息(测控自动化),2006,22(11)：187-189.
[58]李荣花.基于粗集理论的神经网络研究与应用[D].大庆：大庆学院,2003.
[59]巫兆聪.粗集理论在遥感影像分类中的应用[D].武汉：武汉大学,2004.
[60]王丹.粗糙集理论在图像处理中的若干问题研究[D].北京：国防科学技术大学研究生院,2005.
[61]张春美.基于粗糙集的自适应神经模糊推理系统的研究和应用[D].太原：太原理工大学,2005.
[62]田霞.基于粗糙集的机器视觉图像分割[D].太原：太原理工大学,2005.
[63]王珍.基于粗糙集和神经网络的属性约简方法研究[D].河南;中国人民解放军信息工程大学电子技术学院,2006.
[64]杨洋.粗糙集相关问题与粗糙集神经网络模型的研究[D].上海：同济大学电子与信息工程学院,2006.
[65]B.L.Turner Ⅱ, R. H. Moss and D.L.Skole.1993.Relating Land Use and Global Land-Cover Change. IGBP Report No.24, IHDP Report No.5.
[66]刘纪远,等著.20世纪90年代中国土地利用变化遥感时空信息研究[M].北京;科学出版社,2005：21.
[67]郑学芬.遥感影像的不确定性及信息量的计算方法研究[D].山东科技大学,2006,5.
[68]葛咏,王劲峰,梁怡,马江洪.遥感信息不确定性研究[J].遥感学报,2004,8(4)：339-348.
[69]承继成,郭华东,史文中等.遥感数据的不确定性问题[M],北京,科学出版社,2004.
[70]史文中.空间数据与空间分析的不确定性原理[M],北京,科学出版社,2005.
[71]汤国安,张友顺,刘咏梅等著.遥感数字图像处理[M].北京;科学出版社,2004;60.
[72]王耀南.计算机智能信息处理技术及其应用[M].长沙：湖南人学出版社,1999.
[73]Gyanesh Chander and Brian Markham. Revised Landsat-5 TM Radiometric Calibration Procedures and Postcalibration Dynamic Ranges[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING.2003,41(11):2674-2678
[2]Z. Pawlak Rough Sets Theory and it's Application to Data Analysis [J]. Cybernetics System,An International Journal,1998,29:667-668.
[3]Chmielewski M R, Grzymala-Busse J W. Global discratization of continuous attributes as preprocessing for machine learning[J]. International Journal of Approximate Reasoning,1996,15:319-331.
[4]Z. Pawlak Rough sets:Theoretical Aspects of Reasoning about Data[A]. Boston:Kluwer Academic Publishers,1991.
[5]Chan C C. A rough set approach to attribute generalization in data mining [J]. Journal of Information Sciences,1998,107:169-176.
[6]Lingras P J, Yao Y Y, Data mining using extenions of the rough set model [J]. Journal of the American Society for Information Science,1998,49(5):415-422.
[7]Mc Sherry D. Knowledge discovery by inspection[J]. Decision Support Systems,1997,21: 43-47
[8]Z. Pawlak Rough sets approach to Knowledge-based decision support[J]. European Journal of Operational Research,1997,99:48-57.
[9]Pomerol J C. Artificial intelligence and human decision making(J]. European Journal of Operational Research,1997,99:3-25.
[10]张文修,吴伟志,梁吉业,李德玉.粗糙集理论与方法.科学出版社.2001.7.
[11]周开利,康耀红.神经网络模型及其Matlab仿真程序设计[M].北京：清华大学出版社,2005,12.
[12]哈斯巴干.神经网络及其组合算法的遥感数据分类研究[D].北京：中国科学院研究生院,2003.
[13]李小涛.地统计学和神经网络在遥感影像分类中的应用研究[D].山东：山东科技大学,2001,9.
[14]杨吟冬.基于径向基函数神经网络的曲面(线)重构的仿真研究[D].广西：广西大学,2007,6.
[15]Robert M. Texture Features for Image Classification[J]. IEEE Transactions On System, Man and Cybernetic, vol. SMC-3, No.6, Nov 1973:610-621.
[16]Unser M. Sum and difference histograms for texture classification [J], IEEE Trans PAMI Vol.PAMI-8,Jan 1986.
[17]Benedoltsson J A. Neural network approaches versus statistical methods in classification of multisource remote sensing data[J]. IEEE Trans. Geoscience and Remote sensing, vol.28, July 1990:540-552.
[18]Bischof H, Pinz A J. Multispectral Classification of Landsat-Images Using Neural Networks [J].IEEE Trans. on Geoscience and Remote Sensing 1992,30(3):482-490.
[19]Heermann P D. Classification of multispectral remote sensing data using a back-propagation neural network[J]. IEEE Trans. Geoscience and Remote sensing, vol.30, Jan.1992:81-88.
[20]Hush D R. Progress in supervised neural networks [J]. IEEE Signal processing magazine, vol.10, No.1,1993:89-90.
[21]Salu and Y, Tilton J Classification of Multispectral Image Data by the Binary Diamond Neural Networks and by Nonparametric Pixel-by-Pixel Methods [J]. IEEE Trans On Geoscience and Remote Sensing.1993,31,31 (3):606-617.
[22]Haysin S. Neural networks:A comprehensive foundation[M]New York, NY:Macmilan,1994.
[23]Yamazaki T, Gingras D. Image Classification Using Spectral and Information Based on MAR Models[J]. IEEE Trans on Image Processing.1995,14(9):1333-1339.
[24]Egmont-Peterson, M.; De Ridder, D., and Handels, H. Image processing with neural networks-a review. Pattern Recognition,2002,35,2279-2301.
[25]CONGER, C.L.; FLETCHER, C.H., and BARBEE, M. Artificial Neural Network Classification of Sand in All Visible Submarine and Subaerial Regions of a Digital Image. Journal of Coastal Research,2005,21(6),1173-1177.
[26]Ed iriw ickrema J Khorran S H ierarchical Maxinum-Likelihood Classification for Improved Accuracies [J]. IEEE Trans on Geoscience and Remote Sensing 1997, 35(4):810-816.
[27]M clachlaug J Basfold K E.The EM A lgorithm and Extensions[M].New York John Wiley,1997.
[28]朱大奇,史慧.人工神经网络原理及应用.北京：科学出版社,2006：1.
[29]李石华,王金亮,陈姚,等.遥感图像分类方法研究综述[J].国土源遥感,2005,64(2)：1-6.
[30]傅肃性.遥感专题分析与地学图谱[M].北京：科学出版社,2002.
[31]孙家抦.遥感原理与应用[M].武汉：武汉人学出版社,2002.
[32]林培.农业遥感[M].北京：北京农业人学出版社,1991.
[33]梅安新,彭望绿,秦其明,等.遥感导论[M].北京：高等教育出版社,2001.
[34]于秀兰,莫红.Markcov随机场模型在多光谱遥感图像分类中的应用[J].中国农业资源与区划,1999,20(5)：48-53.
[35]朱建华,刘政凯,俞能海.一种多光谱遥感图像的自适应最小距离分类方法[J].中国图象图形学报,2000,5(1)：21-23.
[36]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.
[37]萧嵘,孙晨.一种具有容噪性能的SVM多值分类器[J].计算机研究与发展,2000,37(9)：1071-1075.
[38]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.
[39]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.
[40]王志刚,朱振海,等.光谱角度填图方法及其在岩性识别中的应用[J].遥感学报,1999,3(1)：60-65.
[41]吴革洪,高才松,刘玉民.聚类分析在油藏分类中的应用[J].断块油气田,2001,8(1)：36-37.
[42]贺德化,朱锋峰,彭英伟.有类间距离因素聚类结果的比较分析[J].运筹学学报,1998,2(2)：36-41.
[43]李祚泳.用BP神经网络实现多波段遥感图像的监督分类[J].红外与毫米波学报,1998,17(2)：153-156.
[44]李强,王正志.基于人工神经网络和经验知识的遥感信息分类综合方法[J].自动化学报,2000,26(2)：233-238.
[45]骆剑承,周成虎,杨艳.基于径向基函数(RBF)映射理论的遥感影像分类模型研究[J].中国图象图形学报,2000,5(2)：94-99.
[46]王耀南.小波神经网络的遥感图像分类[J].中国图象图形学报,1999,4(5)：368-371.
[47]阎静,王坟,李湘阁.利用神经网络方法提取水稻种植而积—以湖北省双季水稻为例[J].遥感学报,2001,5(3)：227-230.
[48]Ziarko W. Rough Sets, Fuzzy Sets and Knowledge Discovery. Springer-Verge.1994.
[49]魏敏洁,刘健勤.粗糙集的RBF表示与非监督模式分类[J].湘潭征业学院学报,1998,13(2)：20-23.
[50]徐立中,王慧敏,刘美林,等.粗糙集理论在图像增强中的应用[J].数据采集与处理,1999,14(3)：307-310
[51]徐立中,王慧斌,杨锦堂.基于粗糙集理论的图像增强方法[J].仪器仪表学报,2000,21(5)：514-516.
[52]刘燕,张学庆,杨绍国.一种基于粗糙集分类的图像压缩方法[J].物探化探计算技术,2002,24(2)：174-177.
[53]董广军,范永弘,罗睿.基于粗糙集理论的遥感影像分类研究[J].计算机工程与应用,2003.13：103-105
[54]郭海涛,田坦,张春田,朱昊.利用粗糙集和属性直方图的图像增强方法[J].光电工程,2005,32(3)：51-53.
[55]王晓辉,张少敏,武中利.基于粗糙集图像分层算法的研究[J].华北电力大学学报,2005,32(2)：75-79.
[56]陈素玲,刘文奇.一种基于颜色特征的图像分类检索与约简方法[J].昆明理工大学学报(理工版),2005,30(6)：117-120.
[57]王胜科,王知衍,吴志成.一种基于粗糙集理论的票据图像识别分类方法[J].微计算机信息(测控自动化),2006,22(11)：187-189.
[58]李荣花.基于粗集理论的神经网络研究与应用[D].大庆：大庆学院,2003.
[59]巫兆聪.粗集理论在遥感影像分类中的应用[D].武汉：武汉大学,2004.
[60]王丹.粗糙集理论在图像处理中的若干问题研究[D].北京：国防科学技术大学研究生院,2005.
[61]张春美.基于粗糙集的自适应神经模糊推理系统的研究和应用[D].太原：太原理工大学,2005.
[62]田霞.基于粗糙集的机器视觉图像分割[D].太原：太原理工大学,2005.
[63]王珍.基于粗糙集和神经网络的属性约简方法研究[D].河南;中国人民解放军信息工程大学电子技术学院,2006.
[64]杨洋.粗糙集相关问题与粗糙集神经网络模型的研究[D].上海：同济大学电子与信息工程学院,2006.
[65]B.L.Turner Ⅱ, R. H. Moss and D.L.Skole.1993.Relating Land Use and Global Land-Cover Change. IGBP Report No.24, IHDP Report No.5.
[66]刘纪远,等著.20世纪90年代中国土地利用变化遥感时空信息研究[M].北京;科学出版社,2005：21.
[67]郑学芬.遥感影像的不确定性及信息量的计算方法研究[D].山东科技大学,2006,5.
[68]葛咏,王劲峰,梁怡,马江洪.遥感信息不确定性研究[J].遥感学报,2004,8(4)：339-348.
[69]承继成,郭华东,史文中等.遥感数据的不确定性问题[M],北京,科学出版社,2004.
[70]史文中.空间数据与空间分析的不确定性原理[M],北京,科学出版社,2005.
[71]汤国安,张友顺,刘咏梅等著.遥感数字图像处理[M].北京;科学出版社,2004;60.
[72]王耀南.计算机智能信息处理技术及其应用[M].长沙：湖南人学出版社,1999.
[73]Gyanesh Chander and Brian Markham. Revised Landsat-5 TM Radiometric Calibration Procedures and Postcalibration Dynamic Ranges[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING.2003,41(11):2674-2678