Near-infrared hyperspectral circular polarization imaging and object classification with machine learning
Masato Suzuki, Kimitaka Doi, Moritsugu Sakamoto, Kohei Noda, Tomoyuki Sasaki, Nobuhiro Kawatsuki, Hiroshi Ono
Abstract
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.