基于双树复小波和灰度共生矩阵的遥感图像分割

Remote sensing image segmentation based on dual-tree complex wavelet transform and gray-level co-occurrence matrix

提出了一种将双树复小波变换和灰度共生矩阵相结合描述遥感图像局部纹理特征并用于分割的方法。该方法采用双树复小波高频模值子带Gamma分布与Lognormal分布参数组合特征、灰度共生矩阵特征组成的联合纹理特征作为遥感图像每一像素特征,然后用Canberra距离进行相似性度量,最终通过聚类完成遥感图像分割。实验结果表明,该纹理特征提取方法可以有效地表征遥感图像的纹理,得到更为精确的遥感图像分割结果。

In this paper,we propose a method to describe remote sensing image texture features based on dual-tree complex wavelet transform（DT-CWT） and Gray-level Co-occurrence Matrix.This method uses DT-CWT high-frequency sub-bands＇ Gamma and Lognormal parameters and features of GLCM as the feature vector of remote sensing image pixels.Then,uses Canberra distance to measure the similarity.At last,uses clustering to complete remote sensing image segmentation.The results of experiment prove that the method can efficiently represent the different texture of remote sensing image.The feature based on this method can obtain more accurate remote sensing image segmentation results.