Classifying green teas with near infrared hyperspectral imaging

Puneet Mishra, Alison Nordon

Research output: Contribution to journalArticle

19 Downloads (Pure)

Abstract

Tea products analysis is currently limited to high-end analytical techniques such as high-performance liquid chromatography, gas chromatography and isotope analysis. However, these techniques are time-consuming, expensive, destructive and require trained experts to perform the experiments. In the present work, an application of near infrared hyperspectral imaging for the classification of similarly appearing green tea products is demonstrated. The tea products were classified based on their origin utilising a support vector machine classifier. Results showed good accuracy (96.36 ± 0.17%) for the classification of green tea products from seven different countries of origin.
Original languageEnglish
Number of pages4
JournalNIR News
Early online date21 Nov 2019
DOIs
Publication statusE-pub ahead of print - 21 Nov 2019

Keywords

  • quality
  • non-destructive
  • origin
  • multivariate

Fingerprint

Dive into the research topics of 'Classifying green teas with near infrared hyperspectral imaging'. Together they form a unique fingerprint.

Cite this