基于支持向量机的Q3黄土孔隙微观结构研究

被引:8
作者
谷天峰
王家鼎
郭乐
李开超
机构
[1] 西北大学地质系/大陆动力学国家重点实验室
关键词
黄土微观结构; 图像处理; 支持向量机; 孔隙分类;
D O I
10.16030/j.cnki.issn.1000-3665.2010.06.022
中图分类号
P642.131 [];
学科分类号
摘要
为了解决利用黄土SEM图像提取孔隙参数的问题,将孔隙区域的提取问题转化为孔隙像素点的分类问题,通过把整个图像的像素点分为孔隙点和骨架点,从而实现孔隙的提取。利用这种方法,对潼关Q3黄土震陷试验前后的微结构图像进行处理,得到了动力作用前后的孔隙分布图,并计算了孔隙面积、面孔隙度、孔隙分形维数等参数,结果表明:震陷试验后大孔隙数量减小,中、小孔隙数量有所增加,震陷主要是由大孔隙破坏所致。
引用
收藏
页码:102 / 106
页数:5
相关论文
共 19 条
  • [1] The surface fractal dimension of the soil–pore interface as measured by image analysis[J] . A Dathe,S Eins,J Niemeyer,G Gerold. &nbspGeoderma . 2001 (1)
  • [2] Weighted least squares support vector machines: robustness and sparse approximation[J] . J.A.K. Suykens,J. De Brabanter,L. Lukas,J. Vandewalle. &nbspNeurocomputing . 2002 (1)
  • [4] Determining the petrographicfabric of a compacted soil using semivariance analysis:sample preparation and digital petrographic imageanalysis. Dillon C G,Philip L K. Geoderma . 2004
  • [5] Weighted least squares support vector machines: robustness and sparse approximation. Suykens JAK, De Brabanter J, Lukas L, et al. Neurocomputing . 2002
  • [6] A Tlreshold Selection Method from Gray-Level Histo-grams. Otsu N. Automatica . 1975
  • [7] The surface fractal dimension of the soil-pore interface as measured by image analysis. Dathe A, Eins S, Niemeyer J, et al. Geoderma . 2001
  • [8] Support vector machines for histogram-based image classification. Chapelle O, Haffner P, Vapnik V N. IEEE Transactions on Neural Networks . 1999
  • [9] Influence ofimage resolution and evaluation algorithm on estimatesof the lacunarity of porous media. Pendleton D E,Dathe A,Baveye P. Physical Review E Statistical Nonlinear and Soft Matter Physics . 2005
  • [10] 郑西客运专线黄土路基震陷研究
    谷天峰
    王家鼎
    王峻
    [J]. 工程地质学报, 2009, 17 (04) : 557 - 562