Semi-Supervised Learning with Graphs: Covariance Based Superpixels for Hyperspectral Image Classification
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Sellars, Philip https://orcid.org/0000-0002-9800-7010
Aviles-Rivero, AI
Papadakis, N
Coomes, David https://orcid.org/0000-0002-8261-2582
Faul, A
Abstract
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.
Description
Keywords
Hyperspectral Imaging, Superpixels, Covariance, Graphs, Semi-Supervised Learning, Classification
Journal Title
International Geoscience and Remote Sensing Symposium (IGARSS)
Conference Name
IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium
Journal ISSN
2153-6996
Volume Title
Publisher
IEEE
Publisher DOI
Sponsorship
Engineering and Physical Sciences Research Council (EP/N014588/1)
Case Studentship with the NPL