遥感影像特征提取与选择及在影像分类中的应用  

The application of the feature extraction & selection to image classification

作　　者：秦永[1] 宋伟东[2] 

机构地区：[1]山东理工大学建筑工程学院,山东淄博255900 [2]辽宁工程技术大学测绘工程学院,辽宁阜新123000

出　　处：《测绘科学》2008年第1期176-178,199,共4页Science of Surveying and Mapping

摘　　要：利用模式识别中特征提取和特征选择的相关理论对遥感影像的纹理特征进行遴选和变换处理,得到描述纹理的二次特征。实验证明这些新特征能够提高影像分类精度和分类效率。In this paper, some problems in image texture are studied making use of the theories of feature extraction and selection.15 texture features are gained through gray-level histogram, co-occurrence matrix and run-length matrix.2～3 new features have been chosen out of these 15 texture features and have done a better work on image classification.

关 键 词：特征提取 特征选择 影像分类 纹理特征 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]