Classification of sugar using digital imaging and pattern recognition techniques

Abstract

This work presents a new analytical methodology based on the use of digital images and multivariate analysis for the classification of sugar samples based on their color. Two studies were evaluated. The first involved the discrimination of refined (RS) and unrefined sugar (US) samples. The second study involved the classification of sugar samples into three different classes: refined sugar for the external market (EMRS); refined sugar for retail (RRS); and US. The frequency distribution of color indices in the red, green, blue, hue, saturation, intensity, and grayscale channels were obtained from digital images. Classification models based on partial least squares discriminant analysis (PLS-DA) and linear discriminant analysis (LDA) were developed. The best results obtained for the studies with two (97.4 % accuracy) and three (95.7 % accuracy) classes were achieved by applying the genetic algorithm (GA) in association with the linear discriminant analysis (GA-LDA) on the datasets. The proposed method offers several advantages, including low cost, simplicity, absence of chemical reagents, and non-destructiveness of the sample.