Semi-supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification
Computer Vision and Pattern Recognition
2019-05-16 v4 Machine Learning
Machine Learning
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.
Cite
@article{arxiv.1901.04240,
title = {Semi-supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification},
author = {Philip Sellars and Angelica Aviles-Rivero and Nicolas Papadakis and David Coomes and Anita Faul and Carola-Bibane Schönlieb},
journal= {arXiv preprint arXiv:1901.04240},
year = {2019}
}
Comments
Four pages with two figures