摘要
依托MATLAB仿真平台研究岩浆岩断面结晶度有效特征。采用直方图均衡化进行图像增强预处理,通过几何特征算法提取水平周长、垂直周长与面积数据,计算粒度相对值参数;采用频域算法将频谱图像分割成环形区域,分析高频数据,通过积分求和得到高频区参数。通过两种算法融合,综合提取8维图像特征向量,可以准确表征岩浆岩的结晶程度及粒度大小。
Based on the MATLAB simulation platform,the effective characteristics of the magma rock section crystallinity in the study area are studied.Histogram equalization was applied for image enhancement preprocessing.Geometric feature algorithms were used to extract horizontal perimeter,vertical perimeter,and area data to calculate the relative value parameters of granularity.The frequency domain algorithm was used to segment the spectral image into circular regions,and the high-frequency data were analyzed and integrated to obtain the high-frequency region parameters.By combining two algorithms and comprehensively extracting 8-dimensional image feature vectors,the crystallization degree and particle size of magmatic rocks are accurately characterized.
作者
李敏
王婷
王晓红
周嘉林
韩征
张诗檬
许飞青
周捷铭
LI Min;WANG Ting;WANG Xiaohong;ZHOU Jialin;HAN Zheng;ZHANG Shimeng;XU Feiqing;ZHOU Jieming(Beijing Institute of Geological and Mineral Exploration,Beijing 100195,China;Shandong Special Industry Group Co.,Ltd.,Zibo 255201,Shandong,China;Beijing Geological Survey and Research Institute,Beijing 102206,China)
出处
《城市地质》
2024年第2期267-273,共7页
Urban Geology
基金
北京市自然科学基金项目(8204076)资助。
关键词
北京东庄铁矿区
岩浆岩
特征提取
几何特征
频域特征
地质勘查
Beijing Dongzhuang Iron Mine Area
magmatic rocks
feature extraction
geometric features
frequency domain characteristics
geological exploration
