Deep subspace mapping in hyperspectral imaging

Niclas Wadströmer; David Gustafsson; Henrik Perersson; David Bergström

doi:10.1117/12.2241771

Translator Disclaimer

21 October 2016 Deep subspace mapping in hyperspectral imaging

Niclas Wadströmer, David Gustafsson, Henrik Perersson, David Bergström

Author Affiliations +

Proceedings Volume 9988, Electro-Optical Remote Sensing X; 99880Q (2016) https://doi.org/10.1117/12.2241771
Event: SPIE Security + Defence, 2016, Edinburgh, United Kingdom

Abstract

We propose a novel Deep learning approach using autoencoders to map spectral bands to a space of lower dimensionality while preserving the information that makes it possible to discriminate different materials. Deep learning is a relatively new pattern recognition approach which has given promising result in many applications. In Deep learning a hierarchical representation of increasing level of abstraction of the features is learned. Autoencoder is an important unsupervised technique frequently used in Deep learning for extracting important properties of the data. The learned latent representation is a non-linear mapping of the original data which potentially preserve the discrimination capacity.

Citation Download Citation

Niclas Wadströmer, David Gustafsson, Henrik Perersson, and David Bergström "Deep subspace mapping in hyperspectral imaging", Proc. SPIE 9988, Electro-Optical Remote Sensing X, 99880Q (21 October 2016); https://doi.org/10.1117/12.2241771

ACCESS THE FULL ARTICLE