An overview of regression methods in hyperspectral and multispectral imaging

Irina Torres, José Manuel Amigo*

*Corresponding author for this work
5 Citations (Scopus)

Abstract

Pixel-wise and bulk-wise quantitation of compounds in surfaces of different nature using hyperspectral and multispectral images is of a major interest, especially in fields like food and pharmaceutical production. This chapter revises the most common linear methods together with a brief overview of nonlinear methods applied in the regression framework from a practical point of view. The main benefits and drawbacks are discussed focused on applications in food and pharmaceutical production. Moreover, precise guidelines are given to develop calibration/regression models.

Original languageEnglish
Title of host publicationHyperspectral Imaging
EditorsJosé Manuel Amigo
Number of pages26
PublisherElsevier
Publication date2020
Pages205-230
Chapter2.8
ISBN (Print)978-0-444-63977-6
DOIs
Publication statusPublished - 2020
SeriesData Handling in Science and Technology
Volume32
ISSN0922-3487

Keywords

  • ANN
  • Food
  • MLR
  • PCR
  • Pharma
  • PLS
  • SVM
  • Validation

Fingerprint

Dive into the research topics of 'An overview of regression methods in hyperspectral and multispectral imaging'. Together they form a unique fingerprint.

Cite this