Semi-supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification
This work addresses classification challenges in hyperspectral imaging, offering a domain-specific improvement for remote sensing applications.
The paper tackles hyperspectral image classification by developing a graph-based semi-supervised framework with a novel covariance-based superpixel algorithm, resulting in outperformance over three state-of-the-art methods, particularly with extremely small labeled datasets.
In this paper, we present a graph-based semi-supervised framework for hyperspectral image classification. We first introduce a novel superpixel algorithm based on the spectral covariance matrix representation of pixels to provide a better representation of our data. We then construct a superpixel graph, based on carefully considered feature vectors, before performing classification. We demonstrate, through a set of experimental results using two benchmarking datasets, that our approach outperforms three state-of-the-art classification frameworks, especially when an extremely small amount of labelled data is used.