Abstract: Affected by speckles, SAR image can not be classified well by using the traditional methods. This paper proposes an automatic SAR image classification algorithm, which extracts the feature based on the gray level co-occurrence matrix, and designs classifier with AdaBoost and error correcting code. Experimental results show that the algorithm is effective for SAR image classification. Compared with maximum likelihood method, the classification accuracy is improved significantly.

Key words: error correcting codes, gray level co-occurrence matrix, synthetic aperture radar, classification

摘要： 受相干斑噪声的影响，传统的SAR图像分类方法很难得到较好的分类效果。文中提出一种SAR图像自动分类算法，该算法基于灰度共生矩阵提取特征，结合了AdaBoost和纠错编码设计分类器。实验结果表明，该算法可以得到较好的分类结果。与传统的最大似然法相比，分类精度得到了显著的提高。

关键词: 纠错输出码, 灰度共生矩阵, 合成孔径雷达, 分类

CLC Number: 

• TP37