Detection of Glycoalkaloids and Chlorophyll in Potatoes (Solanum tuberosum L.) by Hyperspectral Imaging

The purpose of the study was to investigate the use of hyperspectral imaging (HSI) to detect and quantify chlorophyll (Chl) and total glycoalkaloid concentrations (TGA) in potatoes. To create a set of tubers with different concentrations of Chl and TGA, potatoes of four varieties were wounded or treated with red, blue, red/blue, UV-a, UV-b or UV-c light. HSI analyses were performed with a reflection based setup implemented in an industrial potato sorting machine. After hyperspectral analyses, the peel was sampled, and concentrations of Chl and total TGA were determined. Results showed that the HSI system predicted the concentrations of Chl with a relatively high degree of accuracy, and a prediction R-2 value of 0.92. Prediction of TGA concentrations performed to a much lesser extent, and the overall prediction R-2 value was only 0.21. Moderate soil covers only affected the prediction powers to a minor degree.