Abstract: In this paper, a texture-based remote-sensing image segmentation approach is pursued, where the features are computed over multiple spatial orientations and frequencies based on 2-D Gabor filters with the theory of multichannel decomposition. The method is applied to a number of remote-senting images. Experimental results are provided to illustrate the feasibility and efficacy of this segmentation method.

摘要： 提出了一种基于Gabor小波滤波器的遥感图像多频道纹理分析算法，大量实验证明本算法方便有效地解决了由于遥感图像目标与背景对比度差、图像边缘模糊、噪声较大而给图像处理带来的困难。

关键词: 遥感图像, Gabor小波滤波器, 多频道纹理分析

CLC Number: 

• TP751