Tea Classification using Fourier Transform Infrared Spectroscopy

Kumar, S and Panchariya, PC and Prasad, PB and Sharma, AL (2014) Tea Classification using Fourier Transform Infrared Spectroscopy. In: International Conference on Agriculture, Forestry, Horticulture, Aquaculture, Animal Sciences, Food Technology, Biodiversity & Climate Change Sustainable Approaches (AFHAFBC-2014), August 30-31,2014, JawaharLal Nehru University. (Submitted)

Preview

PDF Download (1203Kb) | Preview

Abstract

This paper deals with the classification of commercially available Indian teas using the Fourier Transform Infrared (FTIR) spectroscopy method in conjugation with pattern analysis techniques. In this work, two sample preparation approaches i.e. liquid as well as powdered solid sample were investigated. The FTIR spectra of 8 varieties of Indian teas were recorded in the range of 400cm-1 to 4000cm-1 in absorbance mode at room temperature (25ºC) using FTIR Spectrometer. The obtained spectra were preprocessed using standard preprocessing methods i.e. normalization and Standard Normal Variate (SNV). The feature extraction step was carried out using principal component analysis (PCA). The PCA integrated with Linear Discriminant analysis (LDA) was adopted for classification task. PCA-LDA was successfully classified all varieties of tea samples in liquid form as well as in powdered solid form. The FTIR measurements coupled with suitable pattern recognition methods can be used as a key measurement tool for analysis of quality of teas.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Infrared Spectra, Sample Process, Classification, Pattern Recognition
Subjects:	Electronic Systems > Digital Systems
Divisions:	Electronic Systems
Depositing User:	Mr. Rohit Singh
Date Deposited:	11 Jan 2017 09:50
Last Modified:	11 Jan 2017 09:50
URI:	http://ceeri.csircentral.net/id/eprint/256

Actions (login required)

View Item