A short note on deep contextual spatial and spectral information fusion for hyperspectral image processing: Case of pork belly properties prediction

Puneet Mishra*, Michela Albano-Gaglio, Maria Font-i-Furnols

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

This study demonstrates a new approach to process hyperspectral images where both the contextual spatial information as well as the spectral information are used to predict sample properties. The deep contextual spatial information is extracted using the deep feature extraction from pretrained resnet-18 deep learning architecture, while the spectral information was readily available as the average pixel values. To fuse the information in a complementary way, a multiblock modeling approach called sequential orthogonalized partial least squares was used. The sequential model guarantees that the information learned is complementary from spatial and spectral domains. The potential of the approach is demonstrated to predict several physical and chemical properties in pork bellies.

Original languageEnglish
Article numbere3552
JournalJournal of Chemometrics
Volume38
Issue number8
Early online date18 Apr 2024
DOIs
Publication statusPublished - 2024

Keywords

  • artificial intelligence
  • data fusion
  • multivariate
  • spectroscopy
  • transfer learning

Fingerprint

Dive into the research topics of 'A short note on deep contextual spatial and spectral information fusion for hyperspectral image processing: Case of pork belly properties prediction'. Together they form a unique fingerprint.

Cite this