一个改进的遥感图像目标纹理分类识别算法  

A Removed Texture Classification and Distinction Algorithm of Remoted Sensing Martial Object

作　　者：杨斌[1] 赵红漫[1] 赵宗涛[1] 张乐[1] 

机构地区：[1]第二炮兵工程学院,陕西西安710025

出　　处：《微电子学与计算机》2004年第9期111-113,共3页Microelectronics & Computer

基　　金：二炮科研项目(EP010240-10)

摘　　要：提出了一种基于自组织特征映射SOFM网络模型的纹理分类算法,通过提取遥感图像的局部纹理谱特征,刻划图像整体的灰度分布特性并进行纹理分类。实践证明:该算法对飞机,桥架等的识别准确率分别达到91.39%和80%以上。In this paper, a texture classification based on SOFM is put forward. Through it, the local feature of texture spectrum is picked up, so that the whole remote sensing can be classified. It is proved that the precision of algorithm for plan is 91.39%,and that of bridge, highway and vegatation is over 80%.

关 键 词：SOFM 纹理谱 波谱分析 规则分类 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]