I. Introduction
Hyperspectral image (HSI) captured by the hyperspectral remote sensor records the electromagnetic wave of the Earth’s surface, which contains dozens or even hundreds of continuous spectral bands from the visible to near-infrared spectrum region [1], [2]. The HSI provides rich spectral information for identifying ground objects, but the strong correlations among spectral bands usually result in huge redundant data that consume high computing and storage resources [3]. In addition, the high-dimensional characteristic of HSI causes the Hughes phenomenon that the performance of HSI classification declines as the dimensionality increases, especially when only limited training samples are available [4], [5]. Therefore, it is an urgent issue to significantly reduce the dimensionality of HSI without any appreciable loss of useful information [6].