Discrimination of tea varieties based on FTIR spectroscopy and an adaptive improved possibilistic c-means clustering

In order to identify tea varieties quickly, efficiently, and nondestructively, an adaptive improved possibilistic c-means (AIPCM) clustering with the fuzzy Mahalanobis distance was proposed to classify the Fourier transform infrared reflectance (FTIR) spectra of tea samples. Three varieties of tea samples were scanned and FTIR spectra were acquired for 96 tea samples of different geographical origins using the FTIR-7600 infrared spectrometer. Multiple scatter correction was employed to eliminate light scattering of FTIR spectral data. After that, principal component analysis and linear discriminant analysis were applied to reduce the dimensionality of FTIR spectra and extract the discriminant information, respectively. Then, the data were clustered by several fuzzy clustering algorithms. AIPCM had the highest clustering accuracy and its accuracy achieved up to 98.5%. The experimental results showed that FTIR spectroscopy coupled with AIPCM clustering was superior in classification of tea varieties. Practical applications Tea is a popular healthy drink, but there are counterfeit tea products for lack of the effective detection and classification methods in the markets. For this reason, FTIR technique coupled with an AIPCM clustering was applied to the identification of tea varieties, and this method has the advantages of nondestructive, fast, and high accuracy. This study can provide an effective classification method for other foods.