基于Gabor变换与克隆选择的遥感图像分类算法

A Classification Algorithm Based on Gabor Transformation and Clonal Selection for Remote Sensing Image

提出了一种Gabor变换与克隆选择算法相结合的遥感图像分类算法。该算法首先对遥感图像进行离散Gabor变换,以Gabor变换系数模的平均值作为该图像的纹理特征,然后利用克隆选择算法对纹理特征进行优化,得到最优纹理特征。实验结果表明,该算法要优于传统的Gabor变换分类算法,分类精度和kappa系数都有较大提高。

In this paper, a classification algorithm based on Gabor transformation and clonal selection algorithm for remote sensing image is proposed. The discrete Gabor transformation is employed to process the remote sensing images and the coefficient norm of this transformation is used as the texture features of the images. Then clonal selection algorithm is applied to find the optimal texture features which are the input of classifier. An example is provided to illustrate the advantage of the new algorithm,which gives a better precision and kappa coefficient.