Band selection is an important step in the dimensionality reduction processing of hyperspectral images and is highly important for eliminating redundant spectral information and reducing computational costs. In recent years, band selection methods based on ordered partition have been widely used in the dimensionality reduction processing of hyperspectral images. However, most of the methods use coarse and fine partition for band subspace partition, so that the partition results are affected by equal interval partition. Furthermore, existing methods usually select a representative band in each band subspace but do not consider the relationship between the output bands in the selection process, resulting in a certain degree of redundancy between the output bands. To solve the above problems, we propose a band selection method based on global partition clustering that contains band subspace partition and band selection. The band subspace partition is based on coarse and fine partition and the similarity-based ranking-structural similarity method, which divides the band space into band subspaces according to the relationship between the number of bands in the hyperspectral image and the number of selected bands. Band selection is based on the sequential forward selection method, which iteratively selects one band as the output band in each band subspace. The proposed method makes two main contributions. Firstly, this method avoids the negative effect of equal interval partition on the results. Secondly, this method fully considers the relationship between the selected bands and the bands to be selected. The effectiveness of the proposed method is demonstrated via ablation and comparison experiments on three publicly available datasets. Comparison experiments show that the classification accuracy of the proposed method can exceed the accuracy of the comparison methods.

Scholars have performed much research on reducing the redundancy of hyperspectral data. As a measure of the similarity between hyperspectral bands, structural similarity is used in band selection methods. However, existing structural similarity methods calculate all the structural similarity between bands, which leads to excessively long runtimes for these methods. Aiming to address this problem, this paper proposes a band subspace partition method and combines it with the SR-SSIM band selection method to obtain an improved band selection method: E-SR-SSIM. E-SR-SSIM consists of two parts: band subspace partition and band subspace band selection. In the first part, the hyperspectral dataset is divided into subdatasets corresponding to a number of subspaces. In the second part, a modified SR-SSIM method is used for all subdatasets to select the most representative band in each subdataset. The Indian Pines, Salinas Kennedy Space Center and Wuhan unmanned aerial vehicle-borne hyperspectral image LongKou public datasets are used to implement the experiment. The experiment uses random forest as the supervised classifier: 10% of each category sample is randomly selected as training data, and the remaining 90% is used as test data. The evaluation indicators selected in the experiment are overall accuracy, average accuracy, kappa and recall. The experimental results show that E-SR-SSIM can effectively reduce the runtime while ensuring classification compared with SR-SSIM, and quantitative proof that the band subspace partition reduces the calculated amount of structural similarity is obtained through a mathematical analysis. The improved band subspace partition method could partition a dataset more reasonably than the original band subspace partition method.

The redundancy problem of hyperspectral images typically leads to time-consuming and inefficient processing, which requires dimensionality reduction. Among dimensionality reduction methods, band selection methods are popular because of their ability to preserve the physical characteristics of bands. These methods typically rely on the similarity judgment of bands. Therefore, the index similarity metric is critical. In this study, a band selection method is constructed on the basis of similarity measures, such as Shannon entropy (SE) (information entropy) and Boltzmann entropy (thermodynamic entropy), and the effect is compared with that of a band selection method based on structural similarity (SSIM) and the latest entropy band selection method (EFCPC). Experimental results on three hyperspectral datasets show that due to the direct measurement and global range ratio, the band selection method based on SSIM is better than that based on entropy. When the number of bands reaches 20, the F1-scores of similarity-based ranking SSIM (SR-SSIM) on the three datasets are 64.06%, 85.26%, and 85.91%, respectively. Furthermore, the F1-scores of SR-relative Boltzmann entropy (RBE) and SR-absolute Boltzmann entropy (ABE) achieve similar results. When the number of bands reaches 30, the difference between them is 0.91%, 0.73%, and 1.57%, respectively. In contrast, the SR-SE exhibits unstable classification accuracy. When the number of band selections in the Indian Pines dataset is 20, the F1-score of SR-SE is only 43.93%.