Hyperspectral image reconstruction using Multi-colour and Time-multiplexed LED illumination. (October 2019)

• Record Type: Journal Article
• Authors: Tschannerl, Julius; Ren, Jinchang; Zhao, Huimin; Kao, Fu-Jen; Marshall, Stephen; Yuen, Peter
• Is Part Of: Optics and lasers in engineering. Volume 121(2019)
• Page Start: 352
• Page End: 357
• Publication Date: 2019-10
• Subjects: Hyperspectral imaging (HSI) -- Deep learning -- Spectral reconstruction -- LED illumination; Lasers in engineering -- Periodicals; Optical measurements -- Periodicals; Optics -- Periodicals; Lasers en ingénierie -- Périodiques; Mesures optiques -- Périodiques; Optique -- Périodiques; 621.36605
• DOI: 10.1016/j.optlaseng.2019.04.014
• Languages: English
• ISSNs: 0143-8166

Abstract

Highlights: A cost effective, portable MSI system is proposed using RGB LED illumination. RGB LEDs are used to create several colour channels across the VIS range. MSI data can effectively reconstruct HSI data using deep learning with HSI prior. Using more colour channels than RGB generates additional information. 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.