
基于谱-空-纹特征融合的高光谱影像分类方法
Classification for Hyperspectral Images by Fusing Spectral-Spatial-Texture Features
文章提出了一种融合光谱信息, 空间信息和纹理信息的高光谱影像分类方法. 首先采用主成分分析降低高光谱影像的维度, 然后利用灰度共生矩阵从各主成分提取纹理信息, 并根据数学形态学特征和光谱信息定义了一种融合谱-空-纹的相似度距离, 最后通过伪近邻(pseudo nearest neighbor, PNN)分类器对影像地物进行分类. 为了说明所提出方法的有效性, 文章对两个常用的具有不同空间分辨率和光谱分辨率的真实高光谱影像数据集进行了相应的实验, 试验结果和比较结果表明, 利用所提出的方法可以得到较高的分类精度.
A classification method for hyperspectral images is proposed by fusing spectral-spatial-texture features. The principal component analysis is first used to reduce the dimension of hyperspectral image, and then the texture is extracted by gray-level co-occurrence matrix (GLCM) from the obtained principal components. At last, the classification results are obtained by using of PNN classifier. To demonstrate the validity of the proposed method, two real hyperspectral images with the different spatial and spectral resolutions are fed to the proposal. The experimental and comparative results indicate that it is important to consider spectral-spatial-texture features to classify remote sensing images.
谱-空-纹 / 特征融合 / PNN 分类器 / 高光谱分类. {{custom_keyword}} /
/
〈 |
|
〉 |