一种大尺寸遥感图像基于内容检索的纹理特征提取算法  

A Method for Extracting Texture Characters from Large-Scale Remote Sensing Image

作　　者：曾志明[1] 李峰[1] 傅琨[1] 丁赤飚[1] 

机构地区：[1]中国科学院电子学研究所

出　　处：《武汉大学学报（信息科学版）》2005年第12期1080-1083,共4页Geomatics and Information Science of Wuhan University

基　　金：国家863计划资助项目(2003AA131152)

摘　　要：针对50万像素以上的大尺寸遥感图像基于内容检索的需要,通过将大尺寸图像按照区域类别分块,用灰度共生矩阵法对各子块提取出纹理特征,并利用类似Hu的不变矩的方法对各子块纹理信息进行统计,从而提取出与大尺寸图像中各纹理的空间位置相关的一组纹理特征值。该方法对传统的共生矩阵法进行了改进,使其适用于大尺寸图像多区域类别的纹理特征提取,可用于大尺寸遥感图像的基于内容的检索和初分类研究。This paper introduces an improved method for extracting image texture characters from the large-scale remote sensing image on the basis of retrieval based on image content, which has over 500 000 pixels. This method divides image into sub-images and extracts their texture characters with the method of co-occurrence matrices firstly, then calculates some statistics of these texture characters using a statistical method like Hu＇s invariable moment. So we can extract a group of texture characters connected with the texture＇s position in image. It improves the method of co-occurrence matrices and makes the texture characters con- tain more information. This method can be used in large-scale remote sensing image retrieval and classification.

关 键 词：图像 纹理 共生矩阵 不变矩 基于内容的检索 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]