【摘要】 最大似然分类法是基于地物光谱信息的 ,因此无法正确区分光谱特征混淆的地物。本文以北京丰台区为实验区 ,采用纹理分析方法对高分辨率图像的纹理信息进行分析 ,选取统计指标熵 ,通过确定熵的最佳阈值 ,进行边界匹配和图像的分割 ,将光谱易混淆地物如菜地和耕地分割开来 ,并将此分割结果与 TM图像分类结果进行叠合 ,得到最终的分类结果。实验结果表明 :将纹理分析方法应用于图像分类中可区分光谱混合的地类 ,得到较好的分类结果更多还原

【Abstract】 Because Maximum likelihood classification is based on spectrum of objects, it cannot correctly distinguish objects that have same spectrums. In this paper , we take FengTai District of Beijing as an example and analyze texture of high-resolution image by using of texture analysis .The optimal threshold is got according to entropy. Objects that have same spectrums such as vegetation and cultivated land are distinguished using image segmentation in virtue of the optimal threshold. The final result is obtained through combining image segmentation with original classification. The application showed that objects that have same spectrums are distinguished and better results can be obtained by using texture analysis in image classification.更多还原