Semisupervised Hyperspectral Image Classification via Superpixel-Based Graph Regularization With Local and Nonlocal Features

Abstract

Although a graph-based Semi-supervised learning (SSL) approach can utilize limited numbers of labeled samples for hyperspectral image (HSI) classification, it is difficult to use the large amount of pixels in an HSI to construct a large-scale graph. In this paper, we therefore propose a superpixel-based graph model for HSI classification, using anchor graph regularization to improve the extraction of local and non-local spatial information. To avoid the large-scale graph problem, the superpixel-based graph model constructs a scalable anchor graph using a small number of anchor points for graph-based SSL. The proposed approach consists of three key components: (1) First, local and non-local features are extracted from the principal components of an HSI using the locally grouped order pattern (LGOP) and the non-local binary pattern (NLBP) approaches. (2) Second, the extracted features are combined with the original spectral information and used as input to an improved simple line iteration clustering method (ISLIC) to obtain superpixels, the centers of which are used as anchors in the anchor graph approach. (3) Third, we use superpixel-based graph regularization (SGR) to model the global information among the superpixels for better predictions of the label of each unlabeled pixel sample. Experimental results demonstrate that the proposed approach outperforms other state-of-the-art Semi-supervised HSI classification approaches for cases with a limited quantity of labeled samples.