Deep generative neural networks for spectral image processing

Puneet Mishra*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

8 Citations (Scopus)

Abstract

An artificial intelligence approach based on deep generative neural networks for spectral imaging processing was proposed. The key idea was to treat different spectral image processing operations such as segmentation, regression, and classification as image-to-image translation tasks. For the image-to-image translation, the conditional generative adversarial networks were used. As a baseline comparison, the traditional chemometric approach based on pixels wise modelling was demonstrated. The analysis was presented with two real data sets related to fruit property prediction and kernel and shell classification of walnuts. The presented artificial intelligence approach for spectral image processing can provide benefits for any field of science where spectral imaging and processing is widely performed.

Original languageEnglish
Article number339308
JournalAnalytica Chimica Acta
Volume1191
Early online date21 Nov 2021
DOIs
Publication statusPublished - 25 Jan 2022

Keywords

  • Generative models
  • Neural networks
  • Spatial-spectral
  • Spectroscopy

Fingerprint

Dive into the research topics of 'Deep generative neural networks for spectral image processing'. Together they form a unique fingerprint.

Cite this