Rapid classification of commercial Cheddar cheeses from different brands using PLSDA, LDA and SPA–LDA models built by hyperspectral data

Abstract

This study aimed to investigate the feasibility of using near-infrared hyperspectral imaging (NIR-HSI) technique for classifying commercial Cheddar cheeses from different brands. Three classification models including a probability based partial least squares discriminant analysis (PLSDA), linear discriminant analysis (LDA) and successive projections algorithm (SPA)–LDA were used to discriminate four brands of Cheddar cheeses. A simple sample ranking method was used to improve the performance of these models. The generalisation abilities of the PLSDA, LDA and SPA–LDA models for the classification of new batch cheeses were investigated. The optimal number of PLS components was 24 for PLSDA, while the optimal SPA selected wavelengths was 105 for SPA–LDA. The results showed that PLSDA built by hyperspectral data was the most suitable model for brands classification with correct classification rate of 86.67%, and SPA–LDA had better performance than LDA with corresponding correct classification rates of 83.33% and 76.67%, respectively. As a comparison, models built by physical data (texture and colour) achieved poor classification results (< 65% for test set). The current result revealed that HSI technique is better and faster than conventional cheese classification methods.