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

Tschannerl, Julius; Ren, Jinchang; Zhao, Huimin; Kao, Fu-Jen; Marshall, Stephen; Yuen, Peter

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.

Citation

TSCHANNERL, J., REN, J., ZHAO, H., KAO, F.-J., MARSHALL, S. and YUEN, P. 2019. Hyperspectral image reconstruction using multi-colour and time-multiplexed LED illumination. Optics and lasers in engineering [online], 121, pages 352-357. Available from: https://doi.org/10.1016/j.optlaseng.2019.04.014

• Journal Article Type: Article
• Acceptance Date: Apr 14, 2019
• Online Publication Date: May 6, 2019
• Publication Date: Oct 31, 2019
• Deposit Date: May 6, 2022
• Publicly Available Date: Jun 28, 2022
• Journal: Optics and Lasers in Engineering
• Print ISSN: 0143-8166
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 121
• Pages: 352-357
• DOI: https://doi.org/10.1016/j.optlaseng.2019.04.014
• Keywords: Hyperspectral imaging (HSI); Deep learning; Spectral reconstruction; LED illumination
• Public URL: https://rgu-repository.worktribe.com/output/1085523