基于灰度共生矩阵的遥感图像纹理库设计  

Design of Texture Library of Remote Sensing Images Based on Gray Level Co-occurrence Matrix

作　　者：周旭[1] 白深模 

机构地区：[1]78138部队

出　　处：《海洋测绘》2010年第5期72-76,共5页Hydrographic Surveying and Charting

摘　　要：随着很多高分辨率卫星陆续发射和应用,遥感影像中纹理信息也越来越丰富,图像纹理数据的分析纹理显得十分重要。通过对图像进行纹理分析,并建立纹理数据库,能够进一步提高纹理信息在遥感影像质量分析、影像分类、计算机自动识别等方面的精度和效率。研究了如何对图像的纹理进行有效的提取和统计,通过基于灰度共生矩阵的实验进行纹理分析,得到一系列相关数据,为纹理库的设计提出了相应的思路。As the launching and application of lots of high-resolution satellites,texture information of remote sensing image is also increasingly wider,so the analysis of the texture data becomes more and more important.We could have an effective management on a variety of textures with statistical information in order to enhance the quality of analysis of remote sensing image classification,the computer automatical identification of the areas in accuracy and efficiency through the analysis of the texture and establishment of texture library.Here we will have a discussion on how to get texture extraction effectively from remote sensing image.We have got series of relevant data through the experiments of texture analysis based on the gray-level co-occurrence matrix,which correspondingly makes it possible for us to establish the texture library.

关 键 词：遥感影像 纹理 纹理库 纹理分析 灰度共生矩阵 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]