基于岩屑图像的火山岩岩性识别
Lithologic Identification of Volcanic Based on Cutting Figures
摘要:
本文提出了一种基于岩屑图像的火山岩岩性识别方法,首先通过实验分析并确定了对火山岩岩屑识别率较高的颜色与纹理特征;其次通过对这些特征的组合研究,提出了基于线性加权的特征融合法;最后采用极限学习机作为分类器,对特征融合后的火山岩岩屑进行测试。最终实验表明,融合特征对于火山岩岩屑能达到92.05%的识别率,为火山岩的岩性识别提供了一种可靠的参考依据。
Abstract:
In this paper, a new method based on features fusion for volcanic rocks lithology recognition is proposed. First, the color and texture with higher recognition rate are analyzed and determined through experiments. Secondly, a method based on feature fusion is proposed by combining the features into a new integration feature. And finally the extreme learning machine is used as the classifier. Experiments show that the recognition accuracy of integration features is up to 92.05%. This method provides a reliable reference for lithology identification of volcanic.
参考文献
[1]
|
赵辉, 司马立强, 戴思华. 火成岩岩性测井识别的思路和方法[J]. 大庆石油地质与开发, 2012, 31(4): 159-162.
|
[2]
|
杨晓敏, 冉飞, 吴炜, 等. 一种基于支持向量机与纹理的岩屑识别算法[J]. 石油化工高等学校学报, 2009, 22(2): 88-92.
|
[3]
|
张国英, 王娜娜, 张润生, 等. 基于主成分分析的BP神经网络在岩性识别中的应用[J]. 北京石油化工学院学报, 2008, 16(3): 43-46.
|
[4]
|
杨晓明, 李文东, 慈兴华, 等. 基于和差直方图的岩屑纹理分析与分类识别[J]. 中国海洋大学学报, 2011, 41(3): 99-104.
|
[5]
|
王东强, 李文东, 刘宗林, 等. 基于傅立叶变换的岩屑纹理特征提取及岩性识别方法研究[J]. 石油实验地质, 2008, 30(4): 420-423.
|
[6]
|
姚金铸. 岩屑图像识别系统的研究与应用[D]: [硕士学位论文]. 成都: 四川大学, 2014.
|
[7]
|
Du, X. and Zhang, R.Q. (2014) Fusing Color and Texture Features for Blurred Face Recognition. Infrared and Laser Engineering, 43, 4192-4197.
|
[8]
|
Huang, G.B., Zhu, Q.Y. and Siew, C.-K. (2004) Extreme Learning Machine: A New Learning Scheme of Feed forward Neural Networks. Proceedings of International Joint Conference on Neural Networks (IJCNN2004), Budapest, 25-29 July 2004, 985-990.
|
[9]
|
Bulasundaram, S., Gupta, D. and Kapil (2014) 1-Norm Extreme Learning Machine for Regression and Multiclass Classification Using Newton Method. Neurocomputing, 128, 4-14. http://dx.doi.org/10.1016/j.neucom.2013.03.051
|
[10]
|
樊振宇. BP神经网络模型与学习算法[J]. 软件导刊, 2011, 10(7): 66-68.
|