Near-infrared hyperspectral circular polarization imaging and object classification with machine learning
Optics Letters · 01.02.2024 · 49 (3) · 706
DOI: 10.1364/ol.515560 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Letters, online erschienen am 30.01.2024. Verfasst von Masato Suzuki und 6 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 18 Literaturangaben. Gefördert von: Japan Science and Technology Agency.
Abstract (Originalsprache)
We constructed a hyperspectral circular polarization ( S 3 ) imaging system in the near-infrared (NIR) region comprising a circularly polarized broadband light source, a polarization grating, and a commercial hyperspectral camera. With this system, we captured hyperspectral S 3 images of plastic samples. We then demonstrated the classification with machine learning and found that the hyperspectral S 3 images showed higher classification precision than the conventional NIR hyperspectral images. This result indicates that the hyperspectral S 3 imaging has potential for object classification even for samples with similar absorption spectra. This hyperspectral S 3 imaging system can be applied in garbage classification in recycling plants.
Förderung
- Japan Science and Technology Agency
Zitieren
APA
Suzuki, M., Doi, K., Sakamoto, M., Noda, K., Sasaki, T., Kawatsuki, N., & Ono, H. (2024). Near-infrared hyperspectral circular polarization imaging and object classification with machine learning. Optics Letters, 49(3), 706. https://doi.org/10.1364/ol.515560
Vancouver
Suzuki M, Doi K, Sakamoto M, Noda K, Sasaki T, Kawatsuki N, et al. Near-infrared hyperspectral circular polarization imaging and object classification with machine learning. Optics Letters. 2024;49(3):706. doi:10.1364/ol.515560
BibTeX
@article{Suzuki2024,
author = {Suzuki, Masato and Doi, Kimitaka and Sakamoto, Moritsugu and Noda, Kohei and Sasaki, Tomoyuki and Kawatsuki, Nobuhiro and Ono, Hiroshi},
title = {Near-infrared hyperspectral circular polarization imaging and object classification with machine learning},
journal = {Optics Letters},
year = {2024},
volume = {49},
number = {3},
pages = {706},
doi = {10.1364/ol.515560}
}
EUVIMED