Journal of Spectral Imaging,   Volume 10   Article ID a2   (2021)

Peer reviewed Paper

1D conditional generative adversarial network for spectrum-to-spectrum translation of simulated chemical reflectance signatures

  • Cara P. Murphy  
  • John Kerekes
Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Dr., Rochester, NY 14623, USA
[email protected]
 https://orcid.org/0000-0002-0754-8170
 Search for papers by this author
 Corresponding Author
Systems & Technology Research, 600 West Cummings Park, Woburn, MA 01801, USA and Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Dr., Rochester, NY 14623, USA
[email protected]
 https://orcid.org/0000-0002-8595-8941
 Search for papers by this author

The classification of trace chemical residues through active spectroscopic sensing is challenging due to the lack of physics-based models that can accurately predict spectra. To overcome this challenge, we leveraged the field of domain adaptation to translate data from the simulated to the measured domain for training a classifier. We developed the first 1D conditional generative adversarial network (GAN) to perform spectrum-to-spectrum translation of reflectance signatures. We applied the 1D conditional GAN to a library of simulated spectra and quantified the improvement in classification accuracy on real data using the translated spectra for training the classifier. Using the GAN-translated library, the average classification accuracy increased from 0.622 to 0.723 on real chemical reflectance data, including data from chemicals not included in the GAN training set.

Keywords: active spectroscopy, chemical detection, spectral imaging, domain adaptation, conditional GAN, data translation

Metrics

Downloads:

865

Abstract Views:

3,559