21 October 2016 Deep subspace mapping in hyperspectral imaging
Author Affiliations +
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.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Niclas Wadströmer, Niclas Wadströmer, David Gustafsson, David Gustafsson, Henrik Perersson, Henrik Perersson, David Bergström, David Bergström, } "Deep subspace mapping in hyperspectral imaging", Proc. SPIE 9988, Electro-Optical Remote Sensing X, 99880Q (21 October 2016); doi: 10.1117/12.2241771; https://doi.org/10.1117/12.2241771
PROCEEDINGS
15 PAGES


SHARE
Back to Top