【摘要】 SAR图像包含有相干斑噪声 ,传统的方法不能很好地对SAR图像进行分类。为了能对SAR进行精确分类 ,将图像的灰度和纹理特征 ,空域和频域特征相结合 ,提出了一种新的SAR图像分类方法。该方法采用由树型小波中频纹理能量特征、灰度共生矩阵特征、树型小波滤波后的灰度组成的特征矢量对SAR图像进行分类。实验结果分析表明 ,该方法是一种有效的SAR图像分类方法。更多还原

【Abstract】 Containing speckles, an SAR image, can not be classified well by using the traditional methods. A new method of SAR image classification is proposed with the features in the space domain and frequency domain to get the accurate result of classification. The SAR image is classified by using the feature vector which is composed of wavelet texture energy features, the gray-level co-occurrence matrix features and the tone of filtered SAR image with tree wavelet. The results of experiment prove that the method is efficient for SAR image classification.更多还原