Fast multispectral imaging via hybrid-encoded LED illumination and a lightweight deep-learning model
Optics Letters · 01.10.2025 · 50 (19) · 6177
DOI: 10.1364/ol.572715 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Letters, online erschienen am 26.09.2025. Verfasst von Yijia Zeng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 20 Literaturangaben. Gefördert von: Pioneer and Leading Goose” R&D Program of Zhejiang, National Natural Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Active LED-based spectral imaging systems provide flexibility and cost-efficiency but suffer from poor temporal resolution due to the need to individually activate LEDs with different light-emitting wavelengths. This work presents a fast spectral imaging scheme leveraging hybrid-encoded LED illumination and a lightweight deep-learning model, LiteSpectralNet (LSNet). It simultaneously activates multiple LEDs in each measurement, significantly enhancing the encoding efficiency compared to traditional sequential methods. LSNet, a one-dimensional convolutional neural network, effectively reconstructs spectra from these compressed measurements. Experimental results demonstrate an 8.2-fold reduction in total exposure time and a 54% reduction in data storage. This method offers 180.5-fold acceleration in reconstruction speed over traditional approaches, with comparable spectral imaging performance, providing an efficient solution for active multispectral imaging.
Förderung
- Pioneer and Leading Goose” R&D Program of Zhejiang
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Ningbo Science and Technology Project
- Science and Technology Plan Key Project of Taizhou City
- Ningbo Public Welfare Research Program Project
- Ningbo Top Medical and Health Research Program
- Special Development Fund of Shanghai Zhangjiang Science City
Zitieren
APA
Zeng, Y., Wang, X., Jiang, L., Qi, J. W., Lin, Z., Guo, T., & He, S. (2025). Fast multispectral imaging via hybrid-encoded LED illumination and a lightweight deep-learning model. Optics Letters, 50(19), 6177. https://doi.org/10.1364/ol.572715
Vancouver
Zeng Y, Wang X, Jiang L, Qi JW, Lin Z, Guo T, et al. Fast multispectral imaging via hybrid-encoded LED illumination and a lightweight deep-learning model. Optics Letters. 2025;50(19):6177. doi:10.1364/ol.572715
BibTeX
@article{Zeng2025,
author = {Zeng, Yijia and Wang, Xin and Jiang, Lihong and Qi, Jian-Wu and Lin, Zijian and Guo, Tingbiao and He, Sailing},
title = {Fast multispectral imaging via hybrid-encoded LED illumination and a lightweight deep-learning model},
journal = {Optics Letters},
year = {2025},
volume = {50},
number = {19},
pages = {6177},
doi = {10.1364/ol.572715}
}
EUVIMED