遥感图像地物纹理特征的识别研究
|
摘要
随着航天遥感技术的发展及高分辨率遥感图像广泛应用,仅依赖图像光谱信息作为地物的特征有着很大局限性。纹理作为空间信息的反映已经成为标示地物的重要特征,纹理特征的提取方法以及如何利用提取出的特征进行地物识别一直是遥感图像处理领域的研究热点,有着重要意义。
针对以往多数识别研究没有很好的将光谱信息和非光谱信息进行结合,文中首先按照地物的光谱信息将济南地区ETM图像中地物划分为两类。有植被覆盖的耕地、山区乔木林地、灌木林地光谱相近,可作为一类,无植被覆盖的住宅区建筑与裸土为一类,后续研究只围绕每一类光谱相近地物展开。
灰度共生矩阵法是一种公认的能有效进行纹理特征分析的方法,常用到的统计量有对比度(CON)、相关(COR)、能量(ASM)、熵(ENT)、逆差矩(IDM),可用这5个统计量构成纹理特征向量。文中用灰度共生矩阵法提取出TM1,TM2,TM3波段ETM图像的纹理特征,对于每一类光谱相近地物,从三个波段的所有统计量中抽取部分构造出灰度共生纹理特征向量。耕地、山区乔木林地、灌木林地可使用{ASMB3, ASMB2, CORB1, ASMB1, ENTB1, IDMB1},住宅区建筑与裸土可使用{CONB3, ASMB3, IDMB3, CONB2, ASMB2, ENTB2, IDMB2, CONB1, CORB1}。
灰度共生矩阵法能够从像元的灰度相关性上对纹理特征进行描述,而分形维数反映了纹理的结构自相似特征。文中利用差分计盒维数法,计算出TM1,TM2,TM3波段ETM图像地物的维数(DIM),并将该维数作为地物的纹理特征,进而与灰度共生纹理特征向量结合构成了灰度共生-差分维数联合特征向量。耕地、山区乔木林地、灌木林地可使用{ASMB3, ASMB2, CORB1, ASMB1, ENTB1, IDMB1,DIMB3, DIMB2, DIMB1},住宅区建筑与裸土可使用{CONB3, ASMB3, IDMB3, CONB2, ASMB2, ENTB2, IDMB2, CONB1, CORB1, DIMB3, DIMB2, DIMB1}。
BP神经网络和朴素贝叶斯网络是模式识别中经常用到的方法。利用从济南地区ETM图像中提取出的灰度共生纹理特征向量和灰度共生-差分维数向量对BP神经网络和朴素贝叶斯网络进行训练,并用训练后的网络对其它地区遥感图像进行地物识别实验。通过实验验证文中所提出的构造灰度共生纹理特征向量方法的可行性,讨论灰度共生纹理特征向量和灰度共生-差分维数联合特征向量的优劣,比较BP神经网络与朴素贝叶斯网络识别方法的差异。
实验结果表明文中所提出的构造灰度共生纹理特征向量的方法是可行的。利用灰度共生纹理特征向量和灰度共生-差分维数联合特征向量结合BP神经网络和朴素贝叶斯网络都能对地物进行有效识别,识别率在70%以上。应用灰度共生-差分维数联合特征向量的识别结果要优于灰度共生纹理特征向量。BP神经网络的平均识别精度比朴素贝叶斯网络识别精度高2%-5%,但模型的建立要耗费大量的时间。地物类别的稳定性是BP识别算法效率的瓶颈,导致其健壮性不如朴素贝叶斯网络。
With the development of space remote sensing technology and widely used high-resolution remote sensing images, the image depending only on the characteristics of spectral information as a feature has great limitations. Texture as a reflection of spatial information having become important features of marked ground objects, texture feature extraction methods and how to use the features of object recognition has been the focus of remote sensing image processing is of great significance.
Most previous studies for the recognition of spectral information is not very good at binding non-spectral information, this paper will be in accordance with the spectrum of information in Jinan ETM image is divided into two types of Feature. Ground objects by vegetation, mountain forest tree, shrub having similar spectrum can be used as a class, residential area without vegetation cover and bare soil, building a class, follow-up study only around the each class of spectra.
Gray Level Co-occurrence Matrix is an effective way for texture analysis, texture feature vector composed by contrast, correlation, energy, entropy, inverse difference moment. In this paper, texture features extracted from TM1, TM2, TM3 band of ETM by GLCM , parts of them are used to construct gray co-occurrence vector for each type of spectral classification. Land, mountain forest tree, shrub land use {ASMB3, ASMB2, CORB1, ASMB1, ENTB1, IDMB1}.Residential construction and the bare soil use {CONB3, ASMB3, IDMB3, CONB2, ASMB2, ENTB2, IDMB2, CONB1, CORB1}.
GLCM describes texture features from pixel correlation of gray and the fractal dimension reflects the structure of self-similar. In this paper, using differential box counting method to calculate the dimension (DIM) of Ground objects from TM1, TM2, TM3 band ETM image and the dimension of the texture features as a feature and then with the combination of Co-occurrence of the vector form the gray co - dimension feature vector. Land, mountain forest tree, shrub land use {ASMB3, ASMB2, CORB1, ASMB1, ENTB1, IDMB1,DIMB3, DIMB2, DIMB1}.Residential construction and the bare soil use {CONB3, ASMB3, IDMB3, CONB2, ASMB2, ENTB2, IDMB2, CONB1, CORB1, DIMB3, DIMB2, DIMB1}.
BP neural network and Bayesian network are mature technology used in pattern recognition. In this article gray co-occurrence vector and co-dimension feature vector extracted from ETM images of Jinan are used in recognition experiment with BP neural network and Bayesian network. The experiment demonstrates feasibility of the method of using co-occurrence texture feature vector, Discusses pros and cons of co-occurrence texture feature vector and gray co-dimension feature vector, Compares BP Neural Network with Bayesian Network.
Experimental results show that the proposed construction of gray co-occurrence vector is feasible. Ground objects can be effectively recognized by gray co-occurrence vector and gray co - dimension feature vector with BP neural network and Bayesian network, recognition rate of 70%. Application of gray co-dimension feature vector is better than the gray co-occurrence vector. BP neural network's recognition accuracy and time consumption all more than Bayesian network, the accuracy 2% -5% higher. The stability of object types is one bottleneck in BP, leading to its robustness less than naive Bayesian network.
针对以往多数识别研究没有很好的将光谱信息和非光谱信息进行结合,文中首先按照地物的光谱信息将济南地区ETM图像中地物划分为两类。有植被覆盖的耕地、山区乔木林地、灌木林地光谱相近,可作为一类,无植被覆盖的住宅区建筑与裸土为一类,后续研究只围绕每一类光谱相近地物展开。
灰度共生矩阵法是一种公认的能有效进行纹理特征分析的方法,常用到的统计量有对比度(CON)、相关(COR)、能量(ASM)、熵(ENT)、逆差矩(IDM),可用这5个统计量构成纹理特征向量。文中用灰度共生矩阵法提取出TM1,TM2,TM3波段ETM图像的纹理特征,对于每一类光谱相近地物,从三个波段的所有统计量中抽取部分构造出灰度共生纹理特征向量。耕地、山区乔木林地、灌木林地可使用{ASMB3, ASMB2, CORB1, ASMB1, ENTB1, IDMB1},住宅区建筑与裸土可使用{CONB3, ASMB3, IDMB3, CONB2, ASMB2, ENTB2, IDMB2, CONB1, CORB1}。
灰度共生矩阵法能够从像元的灰度相关性上对纹理特征进行描述,而分形维数反映了纹理的结构自相似特征。文中利用差分计盒维数法,计算出TM1,TM2,TM3波段ETM图像地物的维数(DIM),并将该维数作为地物的纹理特征,进而与灰度共生纹理特征向量结合构成了灰度共生-差分维数联合特征向量。耕地、山区乔木林地、灌木林地可使用{ASMB3, ASMB2, CORB1, ASMB1, ENTB1, IDMB1,DIMB3, DIMB2, DIMB1},住宅区建筑与裸土可使用{CONB3, ASMB3, IDMB3, CONB2, ASMB2, ENTB2, IDMB2, CONB1, CORB1, DIMB3, DIMB2, DIMB1}。
BP神经网络和朴素贝叶斯网络是模式识别中经常用到的方法。利用从济南地区ETM图像中提取出的灰度共生纹理特征向量和灰度共生-差分维数向量对BP神经网络和朴素贝叶斯网络进行训练,并用训练后的网络对其它地区遥感图像进行地物识别实验。通过实验验证文中所提出的构造灰度共生纹理特征向量方法的可行性,讨论灰度共生纹理特征向量和灰度共生-差分维数联合特征向量的优劣,比较BP神经网络与朴素贝叶斯网络识别方法的差异。
实验结果表明文中所提出的构造灰度共生纹理特征向量的方法是可行的。利用灰度共生纹理特征向量和灰度共生-差分维数联合特征向量结合BP神经网络和朴素贝叶斯网络都能对地物进行有效识别,识别率在70%以上。应用灰度共生-差分维数联合特征向量的识别结果要优于灰度共生纹理特征向量。BP神经网络的平均识别精度比朴素贝叶斯网络识别精度高2%-5%,但模型的建立要耗费大量的时间。地物类别的稳定性是BP识别算法效率的瓶颈,导致其健壮性不如朴素贝叶斯网络。
With the development of space remote sensing technology and widely used high-resolution remote sensing images, the image depending only on the characteristics of spectral information as a feature has great limitations. Texture as a reflection of spatial information having become important features of marked ground objects, texture feature extraction methods and how to use the features of object recognition has been the focus of remote sensing image processing is of great significance.
Most previous studies for the recognition of spectral information is not very good at binding non-spectral information, this paper will be in accordance with the spectrum of information in Jinan ETM image is divided into two types of Feature. Ground objects by vegetation, mountain forest tree, shrub having similar spectrum can be used as a class, residential area without vegetation cover and bare soil, building a class, follow-up study only around the each class of spectra.
Gray Level Co-occurrence Matrix is an effective way for texture analysis, texture feature vector composed by contrast, correlation, energy, entropy, inverse difference moment. In this paper, texture features extracted from TM1, TM2, TM3 band of ETM by GLCM , parts of them are used to construct gray co-occurrence vector for each type of spectral classification. Land, mountain forest tree, shrub land use {ASMB3, ASMB2, CORB1, ASMB1, ENTB1, IDMB1}.Residential construction and the bare soil use {CONB3, ASMB3, IDMB3, CONB2, ASMB2, ENTB2, IDMB2, CONB1, CORB1}.
GLCM describes texture features from pixel correlation of gray and the fractal dimension reflects the structure of self-similar. In this paper, using differential box counting method to calculate the dimension (DIM) of Ground objects from TM1, TM2, TM3 band ETM image and the dimension of the texture features as a feature and then with the combination of Co-occurrence of the vector form the gray co - dimension feature vector. Land, mountain forest tree, shrub land use {ASMB3, ASMB2, CORB1, ASMB1, ENTB1, IDMB1,DIMB3, DIMB2, DIMB1}.Residential construction and the bare soil use {CONB3, ASMB3, IDMB3, CONB2, ASMB2, ENTB2, IDMB2, CONB1, CORB1, DIMB3, DIMB2, DIMB1}.
BP neural network and Bayesian network are mature technology used in pattern recognition. In this article gray co-occurrence vector and co-dimension feature vector extracted from ETM images of Jinan are used in recognition experiment with BP neural network and Bayesian network. The experiment demonstrates feasibility of the method of using co-occurrence texture feature vector, Discusses pros and cons of co-occurrence texture feature vector and gray co-dimension feature vector, Compares BP Neural Network with Bayesian Network.
Experimental results show that the proposed construction of gray co-occurrence vector is feasible. Ground objects can be effectively recognized by gray co-occurrence vector and gray co - dimension feature vector with BP neural network and Bayesian network, recognition rate of 70%. Application of gray co-dimension feature vector is better than the gray co-occurrence vector. BP neural network's recognition accuracy and time consumption all more than Bayesian network, the accuracy 2% -5% higher. The stability of object types is one bottleneck in BP, leading to its robustness less than naive Bayesian network.
引文
[1]戴昌达,姜小光,唐伶俐.遥感图像应用处理与分析[M].北京:清华大学出版社,2004:3.
[2]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,2003:56.
[3]韦玉春,汤国安,杨昕等.遥感数字图像处理教程[M].北京:科学出版社,2007:1.
[4]关泽群,刘继琳等.遥感图像解译[M].武汉:武汉大学出版社,2007:17.
[5]赵英时等.遥感应用分析原理与方法[M].北京:科学出版社,2003:366.
[6]朱述龙,朱宝山,王红卫.遥感图像处理与应用[M].北京:科学出版社,2006:1
[7]丁宇虹.遥感图像辐射矫正与增强的研究与进展[J]. Friend of Science Amateurs,2009,3: 3-5.
[8]陈志明,李家国,余涛. TM遥感影像的地形辐射校正研究[J].遥感应用,2009,2:29-33.
[9]张友水,冯学智,周成虎.多时相TM影像相对辐射校正研究[J].测绘学报,2006,35(2): 122-127.
[10]樊沛,黄文骞,于彩霞. TM影像几何校正算法的精度比较[J].测绘科学,2008,33(6): 103-105.
[11]程红,王志强,张耀宇.航空影像几何校正方法的研究[J].东北师大学报(自然科学版),2009,41(3):50-54.
[12]王会峰.一种成像测量图像径向几何畸变的校正方法[J].应用光学,2010,31(1):55-59.
[13]刘松涛,吴钢.基于广义直方图均衡的图像增强新方法[J].电光与控制,2010,17(3):12-14.
[14]朱会平,魏峰远.探讨图像增强中直方图均衡化的应用[J].测绘与空间地理信息,2010,33(1):174-176.
[15]乔闹生,叶玉堂,刘霖.基于均值去噪与图像增强的方差滤波器[J].光电子激光,2008,19(12):1666-1669.
[16]郎文杰,宋小鹏.基于小波变换的中值滤波图像去噪[J].机械工程与自动化,2009,6:66-67.
[17]刘尚平,陈骥.基于Gabor滤波与数学形态学的视网膜图像增强方法[J].光电子激光,2010,21(2):318-322.
[18]康牧,王宝树.一种基于图像增强的图像滤波方法[J].武汉大学学报(信息科学版),2009,34(7):822-825.
[19]杨军,张秀琼,高志升等.用于人脸识别的两类主成分分析融合[J].计算机工程与应用,2010,46(1):194-199.
[20]苏琦,杨凤海,王明亮等.基于K-T变换的NDV提取方法研究[J].测绘与空间地理信息,2010,33(1):150-152.
[21]孙勇强,秦媛媛.基于微粒群算法的彩色图像增强研究[J].徐州工程学院学报(自然科学版),2009,24(3):36-40.
[22]张霞,焦全军,张兵等.利用MODIS_EVI图像时间序列提取作物种植模式初探[J].农业工程学报,2008,24(5):161-165.
[23]孟庆伟,张韬,刘佳慧等.内蒙古西部湿地类型TM影像解译标志的建立[J].内蒙古农业大学学报,2007,28(2):35-40.
[24]陈祖耀,王士同.新的特征选择算法[J].计算机工程与设计,2009,30(4):948-951.
[25]党杨梅,杨敏华,常正科. SPOT5影像目视判读在土地利用类型更新中的应用研究[J].测绘与空间地理信息,2009,32(2):125-127.
[26]吴献超,刘莎,侯晓荣等.掌纹识别的一种新的特征提取方法[J].计算机应用研究,2009,26(7):2777-2779.
[27]任源,杨晓晶.遥感技术在现代环境监测与环境保护中的应用[J].环境保护科学,2007,33(3):81-84. [28 ]曹凯,江南.基于TM6的地热资源的热红外遥感探查模型研究[J].遥感信息,2006,(2):18-21.
[29]李志忠,杨日红,党福星等.高光谱遥感卫星技术及其地质应用[J].地质通报,2009,28(2~3):270-277.
[30]刘云,邓玉林,许云磊等.GIS与GIS在区域规划中的应用[J].商业文化,2009,(1):167.
[31]高珍,王超.遥感技术与地理信息系统相结合在区域规划中的应用[J].科技论坛,2009,(5):21.
[32]K.Hammouchea, M.Diafa, J.G. Postaire.A clustering method based on multidimensional texture analysis[J]. Pattern Recognition,2006,39(7):1265-1277.
[33] J. Senthilnath, M. Rajeshwari, S. N. Omkar. Automatic road extraction using high resolution satellite image based on texture progressive analysis and normalized cut method[J]. Journal of the Indian Society of Remote Sensing,2009,37(3):351-361.
[34] F. Kayitakire, C. Hamel,P. Defourny. Retrieving forest structure variables based on image texture analysis and IKONOS-2 imagery[J]. Remote Sensing of Environment,2006,102(33): 390-401.
[35] Pantelis Theocharakisa,Dimitris Glotsosb, Ioannis Kalatzisb. Pattern recognition system for the discrimination of multiple sclerosis from cerebral microangiopathy lesions based on texture analysis of magnetic resonance images[J]. Magnetic Resonance Imaging,2009,27(3): 417-422.
[36] W. James MacLean, John K.Tsotsos. Fast pattern recognition using normalized grey-scale correlation in a pyramid image representation[J]. Machine Vision and Applications,2008, 19(5):163-179. [37 ]Engin Avci ,Abdulkadir Sengur, Davut Hanbay. An optimum feature extraction method fortexture classification[J]. Expert Systems with Applications,2009,36: 6036–6043.
[38]郭德军,宋蛰存.基于灰度共生矩阵的纹理图像分类研究[J].林业机械与木工设备,2005,33(7):21-23.
[39]冯建辉,杨玉静.基于灰度共生矩阵提取纹理特征图像的研究[J].北京测绘,2007,7:19-22.
[40] Engin Avci. An expert system based on Wavelet Neural Network-Adaptive Norm Entropy for scale invariant texture classification[J]. Expert Systems with Applications ,2007,32: 919-926.
[41]王耀南,王绍源,毛建旭.基于分形维数的图像纹理分析[J].湖南大学学报(自然科学版),2006,33(5):67-72.
[42]王迪吉,赵海英,彭宏.基于分形维数的纹理特征的提取与应用[J].石河子大学学报(自然科学版),2007,25(5):650-653.
[43]周振华,李敏,张桂林.GMRF纹理模型在ATR评估系统中的应用[J].计算机与数字工程,2007,35(3):106-109.
[44]柴晓荣,刘锦高.基于纹理分析的精确车牌定位算法[J].计算机系统应用,2010,19(2):160-163.
[45]Abdulkadir Sengur ,Ibrahim Turkoglu, M. Cevdet Ince , Wavelet packet neural networks for texture classification[J]. Expert Systems with Applications ,2007,32: 527–533.
[46]Haim Permutera, Joseph Francosb, Ian Jermync. A study of Gaussian mixture models of color and texture features for image classification and segmentation[J]. Pattern Recognition , 2006,39: 695– 706.
[47]S. Arivazhagan , L. Ganesan ,T.G. Subash Kumar . Texture classification using ridgelet t ransform[J]. Pattern Recognition Letters 2006,27:1875–1883. [48 ]Domenec Puig, Miguel Angel Garcia. Automatic texture feature selection for image pixel classification[J]. Pattern Recognition, 2006,39:1996– 2009.
[49]A.Balaguer ,L.A.Ruiz,T.Hermosilla, J.A.Recio. Definition of a comprehensive set of texture semivariogram features and their evaluation for object-oriented image classification. Computers & Geosciences 2010,36: 231–240.
[50]P.S. Hiremath, S. Shivashankar. Wavelet based co-occurrence histogram features for texture classification with an application to script identification in a document image[J]. Pattern Recognition Letters,2008,29 :1182–1189.
[51]Miguel Angel Garc?a, Domenec Puig. Supervised texture classification by integration of multiple texture methods and evaluation windows[J]. Image and Vision Computing ,2007,25:1091–1106.
[52]Xue-wen Chen, Xiangyan Zeng, Deborah van Alphen. Multi-class feature selection for textureclassification[J]. Pattern Recognition Letters,2006,27:1685-1691. [53 ]Chia-Hsiang Wu, Yung-Nien Sun. Segmentation of kidney from ultrasound B-mode images with texture-based classification[J]. Computer Methods and Programs in Biomedicine,2006, 84:114-123.
[54]Uri Lipowezky.Grayscale aerial and space image colorization using texture classification[J]. Pattern Recognition Letters , 2006,27: 275–286.
[55]AndréRicardoBackes, Wesley NunesGon?alves, AlexandreSoutoMartinez. Texture analysis and classification using deterministic tourist walk[J]. Pattern Recognition ,2010,43: 685- 694.
[56] C.Umarani,L.Ganesan,S. Radhakrishnan. Combined Statistical and Structural Approach for Unsupervised Texture Classification[J]. Pattern Recognition Letters,2008,2(1):162-165.
[57] Humphrey Murray, Arko Lucieer, Raymond William.Texture-based classification of sub-Antarctic vegetation communities on Heard Island[J]. International Journal of Applied Earth Observation and Geoinformation.2010,12(3):138-149.
[58]余远东,胡荣强,田密.融合卫星云图的直方图统计法纹理检测[J].光电工程,2006, 33(10):115-120.
[59]徐小军,邵英,郭尚芬.基于灰度共生矩阵的火焰图像纹理特征分析[J].计算技术与自动化,2007,26(4):64-67.
[60]郭文强.数字图像处理[M].西安:西安电子科技大学出版社,2009:202.
[61]蔡吉花,王东阳,赵琳琳.基于Laws纹理能量测度的鲁棒水印方案[J].黑龙江科技学院学报,2008,18(4):315-322.
[62]梁蕻.基于自相关函数的目标识别方法研究[J].实验技术与管理,23(4):32-35.
[63]任宁,于海鹏,刘一星.木材纹理的分形特征与计算[J].东北林业大学学报,2007,3(2):9-11.
[64]冯江浪.改进灰色马尔科夫模型及其在水资源预测中的利用[J].物探化探计算技术, 2010,32(1):109-112.
[65]HARALICK R M,SHANMUGAM K,DINSTEIN I H . Texture features for image classification[J].IEEE Transactions on Systems,Man and Cybernetics,1973,3(6):610—621.
[66] Chris Ebey Honeycutt,Roy Plotnick. Image analysis techniques and gray-level co-occurrence matrices(GLCM) for calculating bioturbation indices and characterizing biogenic sedimentary structures[J]. Computers & Geosciences,2008,34:1461– 1472.
[67]苑丽红,付丽.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用,2009,29(4):1018-1021.
[68]彭光雄,李京,何宇华.利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息[J].遥感技术与应用,2007,22(1):8-13.
[69]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析.电子学报,2006,34(1):155-158.
[70]李忠.迭代混沌分形[M].北京:科学出版社,2007:41.
[71] K.J.Falconer.分形几何-数学基础及其应用[M].北京:人民邮电出版社,2007,85.
[72]陈永强,陆安生,胡汉平.基于分形的图像分析方法综述[J].计算机工程与设计,2005,26(7):1781-1783.
[73]曹文伦,史忠科,封建湖.分形维数及其在图像分类中的应用研究[J].计算机应用研究,2007,24(4):156-157.
[74]张小京,孙万蓉,乔静.基于分形维数的白细胞图像特征提取研究[J].计算机工程与设计,2009,30(4):941-943.
[75]詹亮,刘浏.基于分形维数的火焰特征提取方法[J].西华大学学报(自然科学版),2009,28(5):45-49.
[76]王娟,张军,吕兆峰.基于分形纹理的遥感影像土地覆盖的分类方法研究[J].测绘科学,2008,33(3):15-17.
[77]郑君杰,黄峰,张韧.基于纹理与分形理论的气象卫星云图目标地物识别[J].气象科学,2005,25(3):244-248.
[78]Wen-Li Leea, Kai-Sheng Hsiehb. A robust algorithm for the fractal dimension of images and its applications to the classification of natural images and ultrasonic liver images[J]. Signal Processing,2010,90(6):1894-1904.
[79]R.Lopesa,N.Betrounia. Fractal and multifractal analysis: A review[J]. Medical Image Analysis,2009,13(4):634-649.
[80]张涛,孙林,黄爱民.图像分形维数的差分盒方法的改进研究[J].电光与控制,2007,14(5):55-57.
[81]张涛,杨志标,黄爱民.一种改进的遥感图像分形维数提取算法[J].军械工程学院学报,2006,18(5):61-65.
[82]赵莹,高隽,陈果等.一种基于分形理论的多尺度多方向纹理特征提取方法[J].仪器仪表学报,2008,29(4):787-791.
[83]齐敏,李大健,郝重阳.模式识别导论[M].北京:清华大学出版社,2009:82.
[84]钟珞,侥文碧,邹承明.人工神经网络及其融合应用技术[M].北京:科学出版社,2007:6.
[85]朱大奇,史慧.人工神经网络原理及应用[M].北京:科学出版社,2006:33.
[86]葛哲学,孙志强.神经网络理论与MATLABR2007实现[M].北京:电子工业出版社,2007:46.
[87]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社,2005:25.
[88]W.K. Wong, C.W.M. Yuen. Stitching defect detection and classification using wavelet transform and BP neural network[J]. Expert Systems with Applications.2009,36(2):3845-3856.
[89]虞欣.贝叶斯网络在航空影像纹理分类中的应用研究[J].测汇学报,2009,38(4):375
[90]王强,彭思龙.基于贝叶斯网络模型的纹理分析及分类[J].计算机辅助设计与图形学学报,2007,19(12):1564-1568.
[91]张璇,左敏.一种改进的朴素贝叶斯分类器在文本分类中的应用研究[J].北京工商大学学报(自然科学版),2009,27(4):52-55.
[92]Eunseog Youna,Myong K.Jeong. Class dependent feature scaling method using naive Bayes classifier for text datamining[J]. Pattern Recognition Letters,2009,30(5):477-485.
[93]Mi-HyunPark,MichaelK.Stenstrom. Classifying environmentally significant urban land uses with satellite imagery[J]. Journal of Environmental Management,2008,86(1):181-192.
[2]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,2003:56.
[3]韦玉春,汤国安,杨昕等.遥感数字图像处理教程[M].北京:科学出版社,2007:1.
[4]关泽群,刘继琳等.遥感图像解译[M].武汉:武汉大学出版社,2007:17.
[5]赵英时等.遥感应用分析原理与方法[M].北京:科学出版社,2003:366.
[6]朱述龙,朱宝山,王红卫.遥感图像处理与应用[M].北京:科学出版社,2006:1
[7]丁宇虹.遥感图像辐射矫正与增强的研究与进展[J]. Friend of Science Amateurs,2009,3: 3-5.
[8]陈志明,李家国,余涛. TM遥感影像的地形辐射校正研究[J].遥感应用,2009,2:29-33.
[9]张友水,冯学智,周成虎.多时相TM影像相对辐射校正研究[J].测绘学报,2006,35(2): 122-127.
[10]樊沛,黄文骞,于彩霞. TM影像几何校正算法的精度比较[J].测绘科学,2008,33(6): 103-105.
[11]程红,王志强,张耀宇.航空影像几何校正方法的研究[J].东北师大学报(自然科学版),2009,41(3):50-54.
[12]王会峰.一种成像测量图像径向几何畸变的校正方法[J].应用光学,2010,31(1):55-59.
[13]刘松涛,吴钢.基于广义直方图均衡的图像增强新方法[J].电光与控制,2010,17(3):12-14.
[14]朱会平,魏峰远.探讨图像增强中直方图均衡化的应用[J].测绘与空间地理信息,2010,33(1):174-176.
[15]乔闹生,叶玉堂,刘霖.基于均值去噪与图像增强的方差滤波器[J].光电子激光,2008,19(12):1666-1669.
[16]郎文杰,宋小鹏.基于小波变换的中值滤波图像去噪[J].机械工程与自动化,2009,6:66-67.
[17]刘尚平,陈骥.基于Gabor滤波与数学形态学的视网膜图像增强方法[J].光电子激光,2010,21(2):318-322.
[18]康牧,王宝树.一种基于图像增强的图像滤波方法[J].武汉大学学报(信息科学版),2009,34(7):822-825.
[19]杨军,张秀琼,高志升等.用于人脸识别的两类主成分分析融合[J].计算机工程与应用,2010,46(1):194-199.
[20]苏琦,杨凤海,王明亮等.基于K-T变换的NDV提取方法研究[J].测绘与空间地理信息,2010,33(1):150-152.
[21]孙勇强,秦媛媛.基于微粒群算法的彩色图像增强研究[J].徐州工程学院学报(自然科学版),2009,24(3):36-40.
[22]张霞,焦全军,张兵等.利用MODIS_EVI图像时间序列提取作物种植模式初探[J].农业工程学报,2008,24(5):161-165.
[23]孟庆伟,张韬,刘佳慧等.内蒙古西部湿地类型TM影像解译标志的建立[J].内蒙古农业大学学报,2007,28(2):35-40.
[24]陈祖耀,王士同.新的特征选择算法[J].计算机工程与设计,2009,30(4):948-951.
[25]党杨梅,杨敏华,常正科. SPOT5影像目视判读在土地利用类型更新中的应用研究[J].测绘与空间地理信息,2009,32(2):125-127.
[26]吴献超,刘莎,侯晓荣等.掌纹识别的一种新的特征提取方法[J].计算机应用研究,2009,26(7):2777-2779.
[27]任源,杨晓晶.遥感技术在现代环境监测与环境保护中的应用[J].环境保护科学,2007,33(3):81-84. [28 ]曹凯,江南.基于TM6的地热资源的热红外遥感探查模型研究[J].遥感信息,2006,(2):18-21.
[29]李志忠,杨日红,党福星等.高光谱遥感卫星技术及其地质应用[J].地质通报,2009,28(2~3):270-277.
[30]刘云,邓玉林,许云磊等.GIS与GIS在区域规划中的应用[J].商业文化,2009,(1):167.
[31]高珍,王超.遥感技术与地理信息系统相结合在区域规划中的应用[J].科技论坛,2009,(5):21.
[32]K.Hammouchea, M.Diafa, J.G. Postaire.A clustering method based on multidimensional texture analysis[J]. Pattern Recognition,2006,39(7):1265-1277.
[33] J. Senthilnath, M. Rajeshwari, S. N. Omkar. Automatic road extraction using high resolution satellite image based on texture progressive analysis and normalized cut method[J]. Journal of the Indian Society of Remote Sensing,2009,37(3):351-361.
[34] F. Kayitakire, C. Hamel,P. Defourny. Retrieving forest structure variables based on image texture analysis and IKONOS-2 imagery[J]. Remote Sensing of Environment,2006,102(33): 390-401.
[35] Pantelis Theocharakisa,Dimitris Glotsosb, Ioannis Kalatzisb. Pattern recognition system for the discrimination of multiple sclerosis from cerebral microangiopathy lesions based on texture analysis of magnetic resonance images[J]. Magnetic Resonance Imaging,2009,27(3): 417-422.
[36] W. James MacLean, John K.Tsotsos. Fast pattern recognition using normalized grey-scale correlation in a pyramid image representation[J]. Machine Vision and Applications,2008, 19(5):163-179. [37 ]Engin Avci ,Abdulkadir Sengur, Davut Hanbay. An optimum feature extraction method fortexture classification[J]. Expert Systems with Applications,2009,36: 6036–6043.
[38]郭德军,宋蛰存.基于灰度共生矩阵的纹理图像分类研究[J].林业机械与木工设备,2005,33(7):21-23.
[39]冯建辉,杨玉静.基于灰度共生矩阵提取纹理特征图像的研究[J].北京测绘,2007,7:19-22.
[40] Engin Avci. An expert system based on Wavelet Neural Network-Adaptive Norm Entropy for scale invariant texture classification[J]. Expert Systems with Applications ,2007,32: 919-926.
[41]王耀南,王绍源,毛建旭.基于分形维数的图像纹理分析[J].湖南大学学报(自然科学版),2006,33(5):67-72.
[42]王迪吉,赵海英,彭宏.基于分形维数的纹理特征的提取与应用[J].石河子大学学报(自然科学版),2007,25(5):650-653.
[43]周振华,李敏,张桂林.GMRF纹理模型在ATR评估系统中的应用[J].计算机与数字工程,2007,35(3):106-109.
[44]柴晓荣,刘锦高.基于纹理分析的精确车牌定位算法[J].计算机系统应用,2010,19(2):160-163.
[45]Abdulkadir Sengur ,Ibrahim Turkoglu, M. Cevdet Ince , Wavelet packet neural networks for texture classification[J]. Expert Systems with Applications ,2007,32: 527–533.
[46]Haim Permutera, Joseph Francosb, Ian Jermync. A study of Gaussian mixture models of color and texture features for image classification and segmentation[J]. Pattern Recognition , 2006,39: 695– 706.
[47]S. Arivazhagan , L. Ganesan ,T.G. Subash Kumar . Texture classification using ridgelet t ransform[J]. Pattern Recognition Letters 2006,27:1875–1883. [48 ]Domenec Puig, Miguel Angel Garcia. Automatic texture feature selection for image pixel classification[J]. Pattern Recognition, 2006,39:1996– 2009.
[49]A.Balaguer ,L.A.Ruiz,T.Hermosilla, J.A.Recio. Definition of a comprehensive set of texture semivariogram features and their evaluation for object-oriented image classification. Computers & Geosciences 2010,36: 231–240.
[50]P.S. Hiremath, S. Shivashankar. Wavelet based co-occurrence histogram features for texture classification with an application to script identification in a document image[J]. Pattern Recognition Letters,2008,29 :1182–1189.
[51]Miguel Angel Garc?a, Domenec Puig. Supervised texture classification by integration of multiple texture methods and evaluation windows[J]. Image and Vision Computing ,2007,25:1091–1106.
[52]Xue-wen Chen, Xiangyan Zeng, Deborah van Alphen. Multi-class feature selection for textureclassification[J]. Pattern Recognition Letters,2006,27:1685-1691. [53 ]Chia-Hsiang Wu, Yung-Nien Sun. Segmentation of kidney from ultrasound B-mode images with texture-based classification[J]. Computer Methods and Programs in Biomedicine,2006, 84:114-123.
[54]Uri Lipowezky.Grayscale aerial and space image colorization using texture classification[J]. Pattern Recognition Letters , 2006,27: 275–286.
[55]AndréRicardoBackes, Wesley NunesGon?alves, AlexandreSoutoMartinez. Texture analysis and classification using deterministic tourist walk[J]. Pattern Recognition ,2010,43: 685- 694.
[56] C.Umarani,L.Ganesan,S. Radhakrishnan. Combined Statistical and Structural Approach for Unsupervised Texture Classification[J]. Pattern Recognition Letters,2008,2(1):162-165.
[57] Humphrey Murray, Arko Lucieer, Raymond William.Texture-based classification of sub-Antarctic vegetation communities on Heard Island[J]. International Journal of Applied Earth Observation and Geoinformation.2010,12(3):138-149.
[58]余远东,胡荣强,田密.融合卫星云图的直方图统计法纹理检测[J].光电工程,2006, 33(10):115-120.
[59]徐小军,邵英,郭尚芬.基于灰度共生矩阵的火焰图像纹理特征分析[J].计算技术与自动化,2007,26(4):64-67.
[60]郭文强.数字图像处理[M].西安:西安电子科技大学出版社,2009:202.
[61]蔡吉花,王东阳,赵琳琳.基于Laws纹理能量测度的鲁棒水印方案[J].黑龙江科技学院学报,2008,18(4):315-322.
[62]梁蕻.基于自相关函数的目标识别方法研究[J].实验技术与管理,23(4):32-35.
[63]任宁,于海鹏,刘一星.木材纹理的分形特征与计算[J].东北林业大学学报,2007,3(2):9-11.
[64]冯江浪.改进灰色马尔科夫模型及其在水资源预测中的利用[J].物探化探计算技术, 2010,32(1):109-112.
[65]HARALICK R M,SHANMUGAM K,DINSTEIN I H . Texture features for image classification[J].IEEE Transactions on Systems,Man and Cybernetics,1973,3(6):610—621.
[66] Chris Ebey Honeycutt,Roy Plotnick. Image analysis techniques and gray-level co-occurrence matrices(GLCM) for calculating bioturbation indices and characterizing biogenic sedimentary structures[J]. Computers & Geosciences,2008,34:1461– 1472.
[67]苑丽红,付丽.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用,2009,29(4):1018-1021.
[68]彭光雄,李京,何宇华.利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息[J].遥感技术与应用,2007,22(1):8-13.
[69]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析.电子学报,2006,34(1):155-158.
[70]李忠.迭代混沌分形[M].北京:科学出版社,2007:41.
[71] K.J.Falconer.分形几何-数学基础及其应用[M].北京:人民邮电出版社,2007,85.
[72]陈永强,陆安生,胡汉平.基于分形的图像分析方法综述[J].计算机工程与设计,2005,26(7):1781-1783.
[73]曹文伦,史忠科,封建湖.分形维数及其在图像分类中的应用研究[J].计算机应用研究,2007,24(4):156-157.
[74]张小京,孙万蓉,乔静.基于分形维数的白细胞图像特征提取研究[J].计算机工程与设计,2009,30(4):941-943.
[75]詹亮,刘浏.基于分形维数的火焰特征提取方法[J].西华大学学报(自然科学版),2009,28(5):45-49.
[76]王娟,张军,吕兆峰.基于分形纹理的遥感影像土地覆盖的分类方法研究[J].测绘科学,2008,33(3):15-17.
[77]郑君杰,黄峰,张韧.基于纹理与分形理论的气象卫星云图目标地物识别[J].气象科学,2005,25(3):244-248.
[78]Wen-Li Leea, Kai-Sheng Hsiehb. A robust algorithm for the fractal dimension of images and its applications to the classification of natural images and ultrasonic liver images[J]. Signal Processing,2010,90(6):1894-1904.
[79]R.Lopesa,N.Betrounia. Fractal and multifractal analysis: A review[J]. Medical Image Analysis,2009,13(4):634-649.
[80]张涛,孙林,黄爱民.图像分形维数的差分盒方法的改进研究[J].电光与控制,2007,14(5):55-57.
[81]张涛,杨志标,黄爱民.一种改进的遥感图像分形维数提取算法[J].军械工程学院学报,2006,18(5):61-65.
[82]赵莹,高隽,陈果等.一种基于分形理论的多尺度多方向纹理特征提取方法[J].仪器仪表学报,2008,29(4):787-791.
[83]齐敏,李大健,郝重阳.模式识别导论[M].北京:清华大学出版社,2009:82.
[84]钟珞,侥文碧,邹承明.人工神经网络及其融合应用技术[M].北京:科学出版社,2007:6.
[85]朱大奇,史慧.人工神经网络原理及应用[M].北京:科学出版社,2006:33.
[86]葛哲学,孙志强.神经网络理论与MATLABR2007实现[M].北京:电子工业出版社,2007:46.
[87]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社,2005:25.
[88]W.K. Wong, C.W.M. Yuen. Stitching defect detection and classification using wavelet transform and BP neural network[J]. Expert Systems with Applications.2009,36(2):3845-3856.
[89]虞欣.贝叶斯网络在航空影像纹理分类中的应用研究[J].测汇学报,2009,38(4):375
[90]王强,彭思龙.基于贝叶斯网络模型的纹理分析及分类[J].计算机辅助设计与图形学学报,2007,19(12):1564-1568.
[91]张璇,左敏.一种改进的朴素贝叶斯分类器在文本分类中的应用研究[J].北京工商大学学报(自然科学版),2009,27(4):52-55.
[92]Eunseog Youna,Myong K.Jeong. Class dependent feature scaling method using naive Bayes classifier for text datamining[J]. Pattern Recognition Letters,2009,30(5):477-485.
[93]Mi-HyunPark,MichaelK.Stenstrom. Classifying environmentally significant urban land uses with satellite imagery[J]. Journal of Environmental Management,2008,86(1):181-192.