Abstract In recent decades, spatial feature extraction has greatly improved the performance of hyperspectral image (HSI) classification. This paper presents an HSI classification method based on multiple spatial features extraction and fusion (MSFs-EF). The method consists of five sequential steps. 1- Principal component analysis is applied for HSI dimensionality reduction. 2- A mean curvature filter is used to extract the spatial texture features from the HSI. 3- The spatial correlation features are obtained using a domain transform normalized convolution filter. 4- Spatial texture features and spatial correlation features are combined. 5- The multiple spatial features are classified using the Large Margin Distribution Machine. Three hyperspectral data sets are used to verify the performance. This method improves the accuracy of HSI classification compared with SVM method, edge-preserving filter, recursive filter method, and deep learning method. In the case of ratios of training samples of 5%, 0.6%, and 5%, the overall accuracy of three data sets reaches 98.23%, 99.17%, and 98.21% respectively, and are about 1.3%∼19%, 0.2%∼13%, and 0.4%∼13% higher than other fourteen algorithms. In the case of ratios of training samples of 10%, 1%, and 10%, the overall accuracy of the three data sets reaches 98.63%, 99.53%, and 98.99%, respectively and still outperform other methods.

中文翻译：

---

用于高光谱图像分类的多空间特征提取和融合

摘要 近几十年来，空间特征提取极大地提高了高光谱图像（HSI）分类的性能。本文提出了一种基于多空间特征提取与融合（MSFs-EF）的HSI分类方法。该方法由五个连续的步骤组成。1- 主成分分析应用于 HSI 降维。2- 平均曲率滤波器用于从 HSI 中提取空间纹理特征。3-使用域变换归一化卷积滤波器获得空间相关特征。4-结合空间纹理特征和空间相关特征。5- 使用大边距分配机对多个空间特征进行分类。三个高光谱数据集用于验证性能。与SVM方法、边缘保留滤波器、递归滤波器方法和深度学习方法相比，该方法提高了HSI分类的准确性。在训练样本比例为5%、0.6%、5%的情况下，三个数据集的整体准确率分别达到98.23%、99.17%和98.21%，分别约为1.3%∼19%、0.2%∼ 13%，比其他 14 种算法高 0.4%∼13%。在训练样本比例分别为10%、1%和10%的情况下，三个数据集的整体准确率分别达到了98.63%、99.53%和98.99%，仍然优于其他方法。比其他十四种算法高3%∼19%、0.2%∼13%、0.4%∼13%。在训练样本比例分别为10%、1%和10%的情况下，三个数据集的整体准确率分别达到了98.63%、99.53%和98.99%，仍然优于其他方法。比其他十四种算法高3%∼19%、0.2%∼13%、0.4%∼13%。在训练样本比例分别为10%、1%和10%的情况下，三个数据集的整体准确率分别达到了98.63%、99.53%和98.99%，仍然优于其他方法。