Hyperspectral image reconstruction using multi-colour and time-multiplexed LED illumination

Show simple item record

dc.contributor.author Tschannerl, Julius
dc.contributor.author Ren, Jinchang
dc.contributor.author Zhao, Huimin
dc.contributor.author Kao, Fu-Jen
dc.contributor.author Marshall, Stephen
dc.contributor.author Yuen, Peter W. T.
dc.date.accessioned 2019-06-06T11:42:51Z
dc.date.available 2019-06-06T11:42:51Z
dc.date.issued 2019-05-06
dc.identifier.citation Tschannerl J, Ren J, Zhao H, et al., (2019) Hyperspectral image reconstruction using multi-colour and time-multiplexed LED illumination. Optics and Lasers in Engineering, Volume 121, October 2019, pp. 352-357 en_UK
dc.identifier.issn 0143-8166
dc.identifier.uri https://doi.org/10.1016/j.optlaseng.2019.04.014
dc.identifier.uri http://dspace.lib.cranfield.ac.uk/handle/1826/14227
dc.description.abstract The rapidly rising industrial interest in hyperspectral imaging (HSI) has generated an increased demand for cost effective HSI devices. We are demonstrating a mobile and low-cost multispectral imaging system, enabled by time-multiplexed RGB Light Emitting Diodes (LED) illumination, which operates at video framerate. Critically, a deep Multi-Layer Perceptron (MLP) with HSI prior in the spectral range of 400–950 nm is trained to reconstruct HSI data. We incorporate regularisation and dropout to compensate for overfitting in the largely ill-posed problem of reconstructing the HSI data. The MLP is characterised by a relatively simple design and low computational burden. Experimental results on 51 objects of various references and naturally occurring materials show the effectiveness of this approach in terms of reconstruction error and classification accuracy. We were also able to show that utilising additional colour channels to the three R, G and B channels adds increased value to the reconstruction. en_UK
dc.language.iso en en_UK
dc.publisher Elsevier en_UK
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International *
dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/4.0/ *
dc.subject Hyperspectral imaging (HSI) en_UK
dc.subject Deep learning en_UK
dc.subject Spectral reconstruction en_UK
dc.subject LED illumination en_UK
dc.title Hyperspectral image reconstruction using multi-colour and time-multiplexed LED illumination en_UK
dc.type Article en_UK
dc.identifier.cris 23453697

Files in this item

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 International Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International

Search CERES


My Account