地震图像的纹理特征提取及分类
|
摘要
地层由于受到构造运动的影响,会产生断层、裂缝等地质现象,从而留下地质历史变迁的印记。这些痕迹,从图形学上来说,可以认为它们是纹理。当然,由于地质构造不同,纹理的疏密、方向也不相同,因此可以说,不同的纹理区域反映着不同的地质构造。在那些纹理方向或结构发生突变的地方,也意味着地质构造的突变,这些信息对于寻找石油或天然气是重要的。纹理分析是指采用一定的图像处理技术提取出纹理特征参数,从而获得对图像的定量或定性描述的处理过程。它是一种不依赖于图像颜色或亮度变化,反映图像中同质现象的视觉特征的处理方法。本文通过采用纹理分析的方法,来凸显地震图像上纹理发生突变的区域,从而达到识别有效储层的目的。
本文首先介绍了纹理分析的基本概念,然后重点阐述了几种主要的纹理特征提取方法,通过实际数据的试验对比,确定选择灰度共生矩阵法来对地震图像进行特征提取。在图像纹理的分类识别时,考虑到已知的训练样本数少且不同类别间可能不具有线性关系,所以本文选择支持向量机来实现。最后,针对靖边气田部分区段的实际数据,采用灰度共生矩阵的方法提取图像的纹理特征,并应用支持向量机进行分类,试验结果表明,本研究在工区的储层预测上取得了很好的效果。在论文的研究中取得以下成果:
1)灰度共生矩阵法具有很好的稳定性,提取出的纹理特征对不同区块的识别能力也很强。在计算每点的特征值时,以该点为中心进行开窗。通过多次的试验对比,发现当窗口大小选取为7×7或者是9×9时效果最好。
2)在共生矩阵上得到了对比度、逆差矩、能量、熵和相关系数特征,考虑到相关系数特征取值很小且缺乏变化,图像效果较差,所以在图像分类时没有采用。此外,通过对比各个特征的取值分布,可以看出当熵取高值、逆差矩取低值时,正好对应着井的位置。从纹理特征含义的角度看,说明该处的取值随机,图像局部变化快,这也预示着该区的地质构造复杂,可能蕴含油气资源。
3)由于已知的样本数据较少,且储层与属性之间往往不表现出线性关系,本研究中选择采用支持向量机对工区内未知区域的储层参数进行预测,并成功的将工区分为有效储层和无效储层两部分。从分类效果看,大多数的井都能落在有效储层内,预测结果与实际试气井位较一致。
Under the influence of the tectonic movement, strata may present the geological phenomena such as faults and cracks, leaving the marks of the geologic changes. In the view of graphics, these marks can be seen as textures. Since the geological structure is different, the texture density and direction are also not identical. In other words, the different texture region reflects different geological structure. The break in the direction and structure of the texture means the break of the geological structure, which provides us some information for searching oil and gas. Texture analysis is a process that using certain image processing technique to extract the texture characteristic parameters, so as to acquire the quantitative or qualitative description of the image. It is a kind of method which reflects the homogeneous phenomena of the images in the visual identity that not dependent on the image color and brightness changes. In this thesis, we use the method of texture analysis to highlight the break region of the texture in the seismic images to identify the effective reservoir.
In this paper, we firstly introduce the concept of the texture analysis, and then emphatically expound the major extraction method of the texture feature. According to the experimental comparison with the actual data, we determine choose the gray level co-occurrence matrix to extract the features of seismic images. On the process of the image texture classification, we consider that the number of the known training samples is rather limited, and different classes may not be a linear relationship between them. So we choose the support vector machine to accomplish the classification. At last of my thesis, using the actual data of a part of the Jingbian gas field, the results show that we have adopted the method of the gray level co-occurrence matrix to extract the texture features and applied the support vector machine to make classification, which has some remarkable effect in the reservoir prediction. The research results obtained in the thesis are as follows:
1) The method of gray level co-occurrence matrix has good stability and the recognition of the extracted textures’characteristics is strong. In the calculation of the characteristic value of the point, we take the point as the center to open a window. Through many times of experiment, we find that the effect is the best when the window size is 7 to 7 and 9 to 9.
2) Base on the co-occurrence matrix, we calculate the characteristics of contrast, homogeneity, energy, entropy and correlation, but the value of the correlation is very small and lack of changes. Obtaining poor image quality, we don’t adopt the correlation in image classification. In addition, through comparing with the values of the features, we find that the areas where the value of entropy high as well as the homogeneity low in the image are unanimous corresponding to the well position. In the view of the texture interpretation, low homogeneity and high entropy mean the value of the image is random and changes quickly, which also mean the geological structure complex and may contain oil or gas resources.
3) Because of the known sample dates are very limited, and the relationships are not often linear dependent between the reservoirs and the attributes,so we choose the support vector machine to classification. In the thesis, we predict the reservoir parameters in the unknown area and success in dividing the work area into two parts: the effective reservoir and the invalid reservoir. From the results of the classification, most of the wells can fall on the effective reservoir, which are coincided with the actual gas well position.
本文首先介绍了纹理分析的基本概念,然后重点阐述了几种主要的纹理特征提取方法,通过实际数据的试验对比,确定选择灰度共生矩阵法来对地震图像进行特征提取。在图像纹理的分类识别时,考虑到已知的训练样本数少且不同类别间可能不具有线性关系,所以本文选择支持向量机来实现。最后,针对靖边气田部分区段的实际数据,采用灰度共生矩阵的方法提取图像的纹理特征,并应用支持向量机进行分类,试验结果表明,本研究在工区的储层预测上取得了很好的效果。在论文的研究中取得以下成果:
1)灰度共生矩阵法具有很好的稳定性,提取出的纹理特征对不同区块的识别能力也很强。在计算每点的特征值时,以该点为中心进行开窗。通过多次的试验对比,发现当窗口大小选取为7×7或者是9×9时效果最好。
2)在共生矩阵上得到了对比度、逆差矩、能量、熵和相关系数特征,考虑到相关系数特征取值很小且缺乏变化,图像效果较差,所以在图像分类时没有采用。此外,通过对比各个特征的取值分布,可以看出当熵取高值、逆差矩取低值时,正好对应着井的位置。从纹理特征含义的角度看,说明该处的取值随机,图像局部变化快,这也预示着该区的地质构造复杂,可能蕴含油气资源。
3)由于已知的样本数据较少,且储层与属性之间往往不表现出线性关系,本研究中选择采用支持向量机对工区内未知区域的储层参数进行预测,并成功的将工区分为有效储层和无效储层两部分。从分类效果看,大多数的井都能落在有效储层内,预测结果与实际试气井位较一致。
Under the influence of the tectonic movement, strata may present the geological phenomena such as faults and cracks, leaving the marks of the geologic changes. In the view of graphics, these marks can be seen as textures. Since the geological structure is different, the texture density and direction are also not identical. In other words, the different texture region reflects different geological structure. The break in the direction and structure of the texture means the break of the geological structure, which provides us some information for searching oil and gas. Texture analysis is a process that using certain image processing technique to extract the texture characteristic parameters, so as to acquire the quantitative or qualitative description of the image. It is a kind of method which reflects the homogeneous phenomena of the images in the visual identity that not dependent on the image color and brightness changes. In this thesis, we use the method of texture analysis to highlight the break region of the texture in the seismic images to identify the effective reservoir.
In this paper, we firstly introduce the concept of the texture analysis, and then emphatically expound the major extraction method of the texture feature. According to the experimental comparison with the actual data, we determine choose the gray level co-occurrence matrix to extract the features of seismic images. On the process of the image texture classification, we consider that the number of the known training samples is rather limited, and different classes may not be a linear relationship between them. So we choose the support vector machine to accomplish the classification. At last of my thesis, using the actual data of a part of the Jingbian gas field, the results show that we have adopted the method of the gray level co-occurrence matrix to extract the texture features and applied the support vector machine to make classification, which has some remarkable effect in the reservoir prediction. The research results obtained in the thesis are as follows:
1) The method of gray level co-occurrence matrix has good stability and the recognition of the extracted textures’characteristics is strong. In the calculation of the characteristic value of the point, we take the point as the center to open a window. Through many times of experiment, we find that the effect is the best when the window size is 7 to 7 and 9 to 9.
2) Base on the co-occurrence matrix, we calculate the characteristics of contrast, homogeneity, energy, entropy and correlation, but the value of the correlation is very small and lack of changes. Obtaining poor image quality, we don’t adopt the correlation in image classification. In addition, through comparing with the values of the features, we find that the areas where the value of entropy high as well as the homogeneity low in the image are unanimous corresponding to the well position. In the view of the texture interpretation, low homogeneity and high entropy mean the value of the image is random and changes quickly, which also mean the geological structure complex and may contain oil or gas resources.
3) Because of the known sample dates are very limited, and the relationships are not often linear dependent between the reservoirs and the attributes,so we choose the support vector machine to classification. In the thesis, we predict the reservoir parameters in the unknown area and success in dividing the work area into two parts: the effective reservoir and the invalid reservoir. From the results of the classification, most of the wells can fall on the effective reservoir, which are coincided with the actual gas well position.
引文
[1]许存禄.图像纹理分析的新方法及其应用[D ].上海:复旦大学博士学位论文,2005.
[2]崔世凌,张军华等.地震纹理属性在JJD工区断层识别中的应用[J].物探化探技术,2010,5,32(3):304-309.
[3]S.Arivazhagan, L.Ganesan. Texture segmentation using wavelet transform [J].Pattern Recognition Letters, 2003, 8, 24 (3): 3197–3203.
[4]Haralick R.M. Statistical and structural approaches to texture [J].Proceedings of the IEEE, 1979, 67(5):786-804.
[5]A.Apostolico, E.R.Caianiello, E.Fischetti and S.Vitulano. An application of C-calculus to texture analysis: C-transforms[J]. Pattern Recognition, 1978, 7(5):389-396.
[6]S.Y.Lua and K.S.Fua. A syntactic approach to texture analysis [J].Computer Graphics and Image Processing, 1978, 7(3): 303-330.
[7]Larry S. Davis. A new tool for image texture analysis [J].Pattern Recognition,1981, 13(3):219-223.
[8]Dacheng Wang and Sargur N.Srihari.Classification of newspaper image blocks using texture analysis [J]. Computer Vision, Graphics and Image Processing, 1989, 47(3):327-352.
[9]Reed TR and du Buf J.M.H. A review of recent texture segmentation and feature extraction techniques [J]. CVGIP: ImageUnderstanding,1993, 57(3): 359-372.
[10]ChungMing Wu and YungChang Chen.Multi-threshold dimension vector for texture analysis and its application to liver tissue classification [J]. Pattern Recognition, 1993, 26(1):137-144.
[11]Tuceryan M, Jain A K. Texture Analysis, Hand book Pattern Recognition and Computer Vision [M]. Singapore: World Scientific, 1993, 235-276.
[12]Fure-Ching Jeng, Woods J.W, Rastogi S. Compound Gauss-Markov Random Fields for Parallel Image Processing [J]. Markov Random Fields Theory and Application, Academic Press, 1993.
[13]Dengliang Gao.3-D VCM seismic textures: A new technology to quantify seismic interpretation [J].SEG Expanded Abstracts 18, 1037(1999).
[14]Dengliang Gao. Seismic textures aid exploration-Texels enhance mapping, visualization and interpretation [J]. Seismic technology,September,2002,65-66.
[15]Dengliang Gao. Volume texture extraction for 3D seismic visualization and interpretation [J]. Geophysics, july,2003,68(4):1294-1302.
[16]Dengliang Gao. Structure-oriented texture model regression: Application to seismic structure visualization and interpretation [R].SEG/New Orleans 2006 Annual Meeting, 1083-1087.
[17]Dengliang Gao. Application of three-dimensional seismic texture analysis with specialreference to deep-marine facies discrimination and interpretation: Offshore Angola, west Africa [J]. AAPG Bulletin December 2007, 91(12):1665-1683.
[18]Dengliang Gao. Application of seismic texture model regression to seismic facies characterization and interpretation [J]. The Leading Edge. March 2008, 394-397.
[19]Dengliang Gao.3D seismic volume visualization and interpretation: An integrated workflow with case studies [J].Geophysics, January, 2009, 74(1):w1-w12.
[20]Satinder Chopra and Vladimir Alexeev. Applications of texture attribute analysis to 3D seismic data [J]. The Leading Edge. August 2006, 934-940.
[21]Satinder Chopra, Kurt J. Marfurt. Emerging and future trends in seismic attributes [J]. The Leading Edge. March 2008, 298-318.
[22]Satinder Chopra,Kurt J.Marfurt. Interactive seismic facies classification using textural attributes and neural networks [J]. The Leading Edge. March 2008, 296-297.
[23]Jurgen Schlaf Trygve Randen and Lars Sonneland. Introduction to Seismic Texture [R]. Schlumberger Stavanger Research, Norway.
[24]Malleswar Yenugu, Kurt J.Marfurt. Seismic texture analysis for reservoir prediction and characterization [J]. The Leading Edge. September 2010, 1116-1121.
[25]Hongliu Zeng. Seismic geomorphology-based facies classification [J]. The Leading Edge. July 2004, 644-646.
[26]Marcilio Castro de Matos, Paulo Leo Manassi Osorio and Paulo Roberto Schroeder Johann. Unsupervised seismic facies analysis using wavelet transform and self-organizing maps [J]. Geophysics, January, 2007, 72(1):9-21.
[27]Piotr W.Mirowski,Daniel M.Tetzlaff,Roy C.Davies. Stationarity Scores on Training Images for Multipoint Geostatistics [J]. Math Geosciences, 2009, 41: 447-474.
[28]A.Carrillat,T.Randen and L.Sonneland.3D texture attributes aid seismic facies classification[J]. Geosciences, February, 2003, 78-81.
[29]Brian P.West,Steve R.May,John E.Eastwood,Christine C.Rossen.Interactive Seismic Facies Classification of Stack and AVO Data Using Textural Attributes and Neural Networks [R]. AAPG Annual Meeting, September 9-14,2001.
[30]William Helland Hansen. Facies and stacking patterns of shelf-deltas within the Palaeogene Battfjellet Formation, Nordenskiold Land,Svalbard: implications for subsurface reservoir prediction [J].Sedimentology,2009,57,190–208.
[31]马晓川,赵荣椿.特征符号随机场—Gibbs模型及其在纹理分割中的应用[J].电子学报.1998(10):81-85.
[32]贾天旭,郑南宁,张元亮.Shannon小波包分解自适应Gabor滤波器设计及其在纹理分割中的应用[J].电子学报1998(10):75-80.
[33]Stephane Mallat,Sifen Zhong.Characterization of Signals form Multiscale Edges [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, July, 1992, 14(7): 710-732.
[34]Love P.L, Simian M。Segmentation of Seismic Section Via Image Processing and AI Techniques [J]. Pattern Recognition, 1992, 25(9): 929-945.
[35]吕知辛.地震剖面图分割的模式识别方法[D].北京:清华大学硕士学位论文,1988.
[36]I.Pitas and C.Kotropoulos. A texture-based approach to the segmentation of seismic images [J]. Pattern Recognition.Vol.25, No.9, 1992, 931-943.
[37]Zhen Zhang. A knowledge-based System Controlled by an Iterative Quad tree Splitting Scheme for Segmentation of Seismic Sections [J]. IEEE Trans, On Geosciences and Remote Sensing, Vol.26, No.5, September 1998, 518-524.
[38]Erik Monsen, Jan E.degard. Segmentation of seismic data with complex stratigraphy using water-shedding-preliminary results [J]. IEEE Trans, Geosciences and Remote Sensing. May 2002, 68-71.
[39]赵荣椿.一种图像分割新方法及其在石油勘探中的应用[J].计算机学报,17(1),1994,622-635.
[40]Marwan A Simaan, Zhen Zhang. Estimation of Texture Orientation in Seismic Images Using an Artificial Neural Network [J].Geosciences and Remote Sensing Symposium,2(3),1999, 1372-1374.
[41]黄伟.纹理分析及其在地震剖面图像分割中的应用[D].南京:南京理工大学硕士学位论文,2007.11.
[42]杨淑莹编著.VC++图像处理程序设计[M].北京:清华大学出版社,2003.
[43]张德丰等编著.MATLAB数字图像处理[M].北京:机械工业出版社,2009.
[44]王华,王祈,孙金玮.基于自相关函数的自然纹理图像分形维数的估计[J].北京航空航天大学学报.30(8), 2004, 718-722.
[45]李亚标等.基于小波变换的图像纹理特征提取方法及其应用[J].传感技术学报,9(9),2009, 1309-1311.
[46]倪林编著.小波变换与图像处理[M].合肥:中国科学技术大学出版社,2010.6.
[47]董少峰,陈洪德,赵俊兴等.鄂尔多斯盆地靖边气田北部马41亚段储层特征[J].沉积与特提斯地质,2009,29(2):66-70.
[48]谢传礼,蔡俩.靖边气田马五段碳酸盐岩层序地层研究[J].断块油气田,2006,13(1):17-20.
[50]孙即祥编著.现代模式识别[M].北京:高等教育出版社,2008.10.
[51]白鹏张喜斌张斌李彦等.支持向量机理论及工程应用实例[J].西安:西安电子科技大学出版,2008.1.
[52]马波.支持向量机多类分类算法的分析与设计[D].扬州:扬州大学2008年硕士论文.
[53]阎辉张学工李衍达.应用SVM方法进行沉积微相识别[J].物探化探计算技,2000,22 (2) : 159-60.
[54]马帅营.基于灰度共生矩阵和BP神经网络集成的纹理图像分类[J].大连民族学院学报,2009, 5 : 260-263.
[2]崔世凌,张军华等.地震纹理属性在JJD工区断层识别中的应用[J].物探化探技术,2010,5,32(3):304-309.
[3]S.Arivazhagan, L.Ganesan. Texture segmentation using wavelet transform [J].Pattern Recognition Letters, 2003, 8, 24 (3): 3197–3203.
[4]Haralick R.M. Statistical and structural approaches to texture [J].Proceedings of the IEEE, 1979, 67(5):786-804.
[5]A.Apostolico, E.R.Caianiello, E.Fischetti and S.Vitulano. An application of C-calculus to texture analysis: C-transforms[J]. Pattern Recognition, 1978, 7(5):389-396.
[6]S.Y.Lua and K.S.Fua. A syntactic approach to texture analysis [J].Computer Graphics and Image Processing, 1978, 7(3): 303-330.
[7]Larry S. Davis. A new tool for image texture analysis [J].Pattern Recognition,1981, 13(3):219-223.
[8]Dacheng Wang and Sargur N.Srihari.Classification of newspaper image blocks using texture analysis [J]. Computer Vision, Graphics and Image Processing, 1989, 47(3):327-352.
[9]Reed TR and du Buf J.M.H. A review of recent texture segmentation and feature extraction techniques [J]. CVGIP: ImageUnderstanding,1993, 57(3): 359-372.
[10]ChungMing Wu and YungChang Chen.Multi-threshold dimension vector for texture analysis and its application to liver tissue classification [J]. Pattern Recognition, 1993, 26(1):137-144.
[11]Tuceryan M, Jain A K. Texture Analysis, Hand book Pattern Recognition and Computer Vision [M]. Singapore: World Scientific, 1993, 235-276.
[12]Fure-Ching Jeng, Woods J.W, Rastogi S. Compound Gauss-Markov Random Fields for Parallel Image Processing [J]. Markov Random Fields Theory and Application, Academic Press, 1993.
[13]Dengliang Gao.3-D VCM seismic textures: A new technology to quantify seismic interpretation [J].SEG Expanded Abstracts 18, 1037(1999).
[14]Dengliang Gao. Seismic textures aid exploration-Texels enhance mapping, visualization and interpretation [J]. Seismic technology,September,2002,65-66.
[15]Dengliang Gao. Volume texture extraction for 3D seismic visualization and interpretation [J]. Geophysics, july,2003,68(4):1294-1302.
[16]Dengliang Gao. Structure-oriented texture model regression: Application to seismic structure visualization and interpretation [R].SEG/New Orleans 2006 Annual Meeting, 1083-1087.
[17]Dengliang Gao. Application of three-dimensional seismic texture analysis with specialreference to deep-marine facies discrimination and interpretation: Offshore Angola, west Africa [J]. AAPG Bulletin December 2007, 91(12):1665-1683.
[18]Dengliang Gao. Application of seismic texture model regression to seismic facies characterization and interpretation [J]. The Leading Edge. March 2008, 394-397.
[19]Dengliang Gao.3D seismic volume visualization and interpretation: An integrated workflow with case studies [J].Geophysics, January, 2009, 74(1):w1-w12.
[20]Satinder Chopra and Vladimir Alexeev. Applications of texture attribute analysis to 3D seismic data [J]. The Leading Edge. August 2006, 934-940.
[21]Satinder Chopra, Kurt J. Marfurt. Emerging and future trends in seismic attributes [J]. The Leading Edge. March 2008, 298-318.
[22]Satinder Chopra,Kurt J.Marfurt. Interactive seismic facies classification using textural attributes and neural networks [J]. The Leading Edge. March 2008, 296-297.
[23]Jurgen Schlaf Trygve Randen and Lars Sonneland. Introduction to Seismic Texture [R]. Schlumberger Stavanger Research, Norway.
[24]Malleswar Yenugu, Kurt J.Marfurt. Seismic texture analysis for reservoir prediction and characterization [J]. The Leading Edge. September 2010, 1116-1121.
[25]Hongliu Zeng. Seismic geomorphology-based facies classification [J]. The Leading Edge. July 2004, 644-646.
[26]Marcilio Castro de Matos, Paulo Leo Manassi Osorio and Paulo Roberto Schroeder Johann. Unsupervised seismic facies analysis using wavelet transform and self-organizing maps [J]. Geophysics, January, 2007, 72(1):9-21.
[27]Piotr W.Mirowski,Daniel M.Tetzlaff,Roy C.Davies. Stationarity Scores on Training Images for Multipoint Geostatistics [J]. Math Geosciences, 2009, 41: 447-474.
[28]A.Carrillat,T.Randen and L.Sonneland.3D texture attributes aid seismic facies classification[J]. Geosciences, February, 2003, 78-81.
[29]Brian P.West,Steve R.May,John E.Eastwood,Christine C.Rossen.Interactive Seismic Facies Classification of Stack and AVO Data Using Textural Attributes and Neural Networks [R]. AAPG Annual Meeting, September 9-14,2001.
[30]William Helland Hansen. Facies and stacking patterns of shelf-deltas within the Palaeogene Battfjellet Formation, Nordenskiold Land,Svalbard: implications for subsurface reservoir prediction [J].Sedimentology,2009,57,190–208.
[31]马晓川,赵荣椿.特征符号随机场—Gibbs模型及其在纹理分割中的应用[J].电子学报.1998(10):81-85.
[32]贾天旭,郑南宁,张元亮.Shannon小波包分解自适应Gabor滤波器设计及其在纹理分割中的应用[J].电子学报1998(10):75-80.
[33]Stephane Mallat,Sifen Zhong.Characterization of Signals form Multiscale Edges [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, July, 1992, 14(7): 710-732.
[34]Love P.L, Simian M。Segmentation of Seismic Section Via Image Processing and AI Techniques [J]. Pattern Recognition, 1992, 25(9): 929-945.
[35]吕知辛.地震剖面图分割的模式识别方法[D].北京:清华大学硕士学位论文,1988.
[36]I.Pitas and C.Kotropoulos. A texture-based approach to the segmentation of seismic images [J]. Pattern Recognition.Vol.25, No.9, 1992, 931-943.
[37]Zhen Zhang. A knowledge-based System Controlled by an Iterative Quad tree Splitting Scheme for Segmentation of Seismic Sections [J]. IEEE Trans, On Geosciences and Remote Sensing, Vol.26, No.5, September 1998, 518-524.
[38]Erik Monsen, Jan E.degard. Segmentation of seismic data with complex stratigraphy using water-shedding-preliminary results [J]. IEEE Trans, Geosciences and Remote Sensing. May 2002, 68-71.
[39]赵荣椿.一种图像分割新方法及其在石油勘探中的应用[J].计算机学报,17(1),1994,622-635.
[40]Marwan A Simaan, Zhen Zhang. Estimation of Texture Orientation in Seismic Images Using an Artificial Neural Network [J].Geosciences and Remote Sensing Symposium,2(3),1999, 1372-1374.
[41]黄伟.纹理分析及其在地震剖面图像分割中的应用[D].南京:南京理工大学硕士学位论文,2007.11.
[42]杨淑莹编著.VC++图像处理程序设计[M].北京:清华大学出版社,2003.
[43]张德丰等编著.MATLAB数字图像处理[M].北京:机械工业出版社,2009.
[44]王华,王祈,孙金玮.基于自相关函数的自然纹理图像分形维数的估计[J].北京航空航天大学学报.30(8), 2004, 718-722.
[45]李亚标等.基于小波变换的图像纹理特征提取方法及其应用[J].传感技术学报,9(9),2009, 1309-1311.
[46]倪林编著.小波变换与图像处理[M].合肥:中国科学技术大学出版社,2010.6.
[47]董少峰,陈洪德,赵俊兴等.鄂尔多斯盆地靖边气田北部马41亚段储层特征[J].沉积与特提斯地质,2009,29(2):66-70.
[48]谢传礼,蔡俩.靖边气田马五段碳酸盐岩层序地层研究[J].断块油气田,2006,13(1):17-20.
[50]孙即祥编著.现代模式识别[M].北京:高等教育出版社,2008.10.
[51]白鹏张喜斌张斌李彦等.支持向量机理论及工程应用实例[J].西安:西安电子科技大学出版,2008.1.
[52]马波.支持向量机多类分类算法的分析与设计[D].扬州:扬州大学2008年硕士论文.
[53]阎辉张学工李衍达.应用SVM方法进行沉积微相识别[J].物探化探计算技,2000,22 (2) : 159-60.
[54]马帅营.基于灰度共生矩阵和BP神经网络集成的纹理图像分类[J].大连民族学院学报,2009, 5 : 260-263.