| 基于图像分类的矿物含量测定及精度评价 |
| |
| 引用本文： | 叶润青,牛瑞卿,张良培,易顺华.基于图像分类的矿物含量测定及精度评价[J].中国矿业大学学报,2011(5). |
| |
| 作者姓名： | 叶润青 牛瑞卿 张良培 易顺华 |
| |
| 作者单位： | 中国地质大学地球物理与空间信息学院;武汉大学测绘遥感信息工程国家重点实验室;中国地质大学地球科学学院; |
| |
| 基金项目： | 国家高技术研究发展计划(863)项目(2007AA12Z160,2009AA122004) |
| |
| 摘 要： | 针对传统矿物含量测定中存在人为误差、缺乏精度评价等问题,提出了基于图像分类的矿物含量测定及精度评价方法,该方法通过统计分类后图像中每种矿物的像元数量测定矿物含量,并采用混淆矩阵评价含量测定精度.根据岩石图像的光谱和纹理特征,提出了两种基本的矿物含量测定方式:1)对于纹理简单、矿物光谱区分度大的岩石图像,采用直接分类方式测定矿物含量,花岗岩手标本照片矿物分类实验表明监督分类效果优于非监督分类,且监督分类中最大似然法分类(MLC)的精度最高,其含量测定精度为94.25%;2)针对复杂纹理(如干涉色、双晶等)的岩石图像,引入了面向对象(矿物或矿物集合体)的多尺度图像分割算法,在分割基础上分类并统计每类矿物含量.白云母二长花岗岩镜下照片矿物分类实验得到其含量测定精度为94.85%.
|
| 关 键 词： | 矿物含量 精度评价 岩石图像 多尺度分割 |
Mineral contents determination and accuracy evaluation based on classification of petrographic images |
| |
| YE Run-qing,NIU Rui-qing,ZHANG Liang-pei,YI Shun-hua.Mineral contents determination and accuracy evaluation based on classification of petrographic images[J].Journal of China University of Mining & Technology,2011(5). |
| |
| Authors: | YE Run-qing NIU Rui-qing ZHANG Liang-pei YI Shun-hua |
| |
| Affiliation: | YE Run-qing1,NIU Rui-qing1,ZHANG Liang-pei2,YI Shun-hua3(1.Institute of Geophysics and Geomatics,China University of Geosciences,Wuhan,Hubei 430074,China,2.State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Hubei 430079,3.Faulty of Earth Science,China) |
| |
| Abstract: | There are many human errors and lack accuracy evaluation existing in the mineral contents determination for traditional methods.A new approach is proposed for mineral contents determination and accuracy evaluation based on images classification.The method is firstly to divide the petrographic images into different mineral classes by using image classification algorithms,and then to obtain the mineral contents through pixel statistic,finally contents accuracy evaluation is carried out by Confusion Matrix(CM)... |
| |
| Keywords: | mineral content accuracy evaluation petrographic image Multi-resolution Segmentation |
| 本文献已被 CNKI 等数据库收录！ |
|
