Near-infrared hyperspectral circular polarization imaging and object classification with machine learning.

We constructed a hyperspectral circular polarization (S) 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 images of plastic samples. We then demonstrated the classification with machine learning and found that the hyperspectral S images showed higher classification precision than the conventional NIR hyperspectral images. This result indicates that the hyperspectral S imaging has potential for object classification even for samples with similar absorption spectra. This hyperspectral S imaging system can be applied in garbage classification in recycling plants.