We explore the spectral spatial representation capabilities of convolutional neural networks for the purpose of classification of hyperspectral images. We examine several types of neural networks, including a novel technique that blends the Fourier scattering transform with a convolutional neural network. This method is naturally suited for the representation of hyperspectral data because it decomposes signals into multi-frequency bands, removing small perturbations such as noise, while also having the capability of neural networks to learn a hierarchical representation. We test our proposed method on the standard Pavia University hyperspectral dataset and demonstrate a new training set sampling strategy that reveals the inherent spatial bias present in some purely neural network methods. The results indicate that our form of blended learning is more effective at representing spectral data and less prone to overfitting the artificial spatial bias in hyperspectral data.
We explore the representation capabilities of scattering transforms for the classification of hyperspectral images. We examine several types, including a recently developed technique called the Fourier scattering transform. This method is naturally suited for the representation of hyperspectral data because it decomposes signals into multi-frequency bands and removes small perturbations such as noise. We test on four standard hyperspectral datasets, and the results indicate that the Fourier scattering transform is effective at representing spectral data. We also present a spatial-spectral scattering transform that combines Wavelet and Fourier representations, and this method obtains significantly higher classification accuracies.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.