Spectral reconstruction with model-based neural network for liquid crystal modulator devices

Jizhou Zhang; Tingfa Xu; Qingwang Qin; Yuhan Zhang

doi:10.1117/12.2604353

Spectral reconstruction with model-based neural network for liquid crystal modulator devices

Jizhou Zhang, Tingfa Xu^*, Qingwang Qin, Yuhan Zhang

^*Corresponding author for this work

School of Optics and Photonics

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The liquid crystal modulator devices (LCMD) have become an important technique in the field of hyperspectral imaging. However, the spectral resolution and accuracy of LCMD-based imaging spectrometers are limited due to their principle. To break this limitation and promote the application of LCMD, we propose a spectral reconstruction method using model-based neural networks. The calibrated spectral transmittance of LCMD and a carefully designed loss function are used to constraint the calculation. Experiments on reconstructing both substance spectra and spectral image cubes have validated the effectiveness and superiority of the proposed method.

Original language	English
Title of host publication	Twelfth International Conference on Information Optics and Photonics, CIOP 2021
Editors	Yue Yang
Publisher	SPIE
ISBN (Electronic)	9781510649897
DOIs	https://doi.org/10.1117/12.2604353
Publication status	Published - 2021
Event	12th International Conference on Information Optics and Photonics, CIOP 2021 - Xi'an, China Duration: 23 Jul 2021 → 26 Jul 2021

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	12057
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	12th International Conference on Information Optics and Photonics, CIOP 2021
Country/Territory	China
City	Xi'an
Period	23/07/21 → 26/07/21

Keywords

LCMD
Model-based neural network
Spectral reconstruction

Access to Document

10.1117/12.2604353

Cite this

Zhang, J., Xu, T., Qin, Q., & Zhang, Y. (2021). Spectral reconstruction with model-based neural network for liquid crystal modulator devices. In Y. Yang (Ed.), Twelfth International Conference on Information Optics and Photonics, CIOP 2021 Article 120570U (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12057). SPIE. https://doi.org/10.1117/12.2604353

@inproceedings{06a2bb9ae0de4418b5378ce20cd8f24c,

title = "Spectral reconstruction with model-based neural network for liquid crystal modulator devices",

abstract = "The liquid crystal modulator devices (LCMD) have become an important technique in the field of hyperspectral imaging. However, the spectral resolution and accuracy of LCMD-based imaging spectrometers are limited due to their principle. To break this limitation and promote the application of LCMD, we propose a spectral reconstruction method using model-based neural networks. The calibrated spectral transmittance of LCMD and a carefully designed loss function are used to constraint the calculation. Experiments on reconstructing both substance spectra and spectral image cubes have validated the effectiveness and superiority of the proposed method.",

keywords = "LCMD, Model-based neural network, Spectral reconstruction",

author = "Jizhou Zhang and Tingfa Xu and Qingwang Qin and Yuhan Zhang",

note = "Publisher Copyright: {\textcopyright} 2021 COPYRIGHT SPIE.; 12th International Conference on Information Optics and Photonics, CIOP 2021 ; Conference date: 23-07-2021 Through 26-07-2021",

year = "2021",

doi = "10.1117/12.2604353",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Yue Yang",

booktitle = "Twelfth International Conference on Information Optics and Photonics, CIOP 2021",

address = "United States",

}

Zhang, J, Xu, T, Qin, Q & Zhang, Y 2021, Spectral reconstruction with model-based neural network for liquid crystal modulator devices. in Y Yang (ed.), Twelfth International Conference on Information Optics and Photonics, CIOP 2021., 120570U, Proceedings of SPIE - The International Society for Optical Engineering, vol. 12057, SPIE, 12th International Conference on Information Optics and Photonics, CIOP 2021, Xi'an, China, 23/07/21. https://doi.org/10.1117/12.2604353

Spectral reconstruction with model-based neural network for liquid crystal modulator devices. / Zhang, Jizhou; Xu, Tingfa; Qin, Qingwang et al.
Twelfth International Conference on Information Optics and Photonics, CIOP 2021. ed. / Yue Yang. SPIE, 2021. 120570U (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12057).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Spectral reconstruction with model-based neural network for liquid crystal modulator devices

AU - Zhang, Jizhou

AU - Xu, Tingfa

AU - Qin, Qingwang

AU - Zhang, Yuhan

PY - 2021

Y1 - 2021

N2 - The liquid crystal modulator devices (LCMD) have become an important technique in the field of hyperspectral imaging. However, the spectral resolution and accuracy of LCMD-based imaging spectrometers are limited due to their principle. To break this limitation and promote the application of LCMD, we propose a spectral reconstruction method using model-based neural networks. The calibrated spectral transmittance of LCMD and a carefully designed loss function are used to constraint the calculation. Experiments on reconstructing both substance spectra and spectral image cubes have validated the effectiveness and superiority of the proposed method.

AB - The liquid crystal modulator devices (LCMD) have become an important technique in the field of hyperspectral imaging. However, the spectral resolution and accuracy of LCMD-based imaging spectrometers are limited due to their principle. To break this limitation and promote the application of LCMD, we propose a spectral reconstruction method using model-based neural networks. The calibrated spectral transmittance of LCMD and a carefully designed loss function are used to constraint the calculation. Experiments on reconstructing both substance spectra and spectral image cubes have validated the effectiveness and superiority of the proposed method.

KW - LCMD

KW - Model-based neural network

KW - Spectral reconstruction

UR - http://www.scopus.com/inward/record.url?scp=85121533084&partnerID=8YFLogxK

U2 - 10.1117/12.2604353

DO - 10.1117/12.2604353

M3 - Conference contribution

AN - SCOPUS:85121533084

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Twelfth International Conference on Information Optics and Photonics, CIOP 2021

A2 - Yang, Yue

PB - SPIE

T2 - 12th International Conference on Information Optics and Photonics, CIOP 2021

Y2 - 23 July 2021 through 26 July 2021

ER -

Spectral reconstruction with model-based neural network for liquid crystal modulator devices

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this