Postharvest authentication of potato cultivars using machine learning to provide high-quality products

The potato cultivars may differ in chemical, physical, sensory and functional properties. Therefore, the correct identification of potato cultivars is of great importance for both processing and cultivation. The application of machine learning enables the non-destructive, objective, repeatability and inexpensive quality evaluation. The objective of this study was to discriminate potato cultivars using models developed based on textures of tuber images. The potatoes belonging to cultivars ‘Irga’, ‘Riviera’ and ‘Colomba’ were harvested from fields located in Poland. The washed, cleaned and air-dried tubers of each cultivar were imaged using a digital camera in one hundred repetitions. The acquired images were converted to color channels R, G, B, L, a, b, X, Y, Z, U, V. In the case of each potato tuber image, about two thousand texture features were calculated and were used to build discriminative models. The most successful model included 29 selected attributes (1 from color channel R, 2 from channel G, 1 from channel B, 7 from channel a, 2 from channel b, 1 from channel X, 3 from channel Z, 2 from channel U, 10 from channel V). The highest accuracies of cultivar identification of potato tubers reached 99% for the IBk classifier from the group of Lazy, 98% for Multilayer Perceptron (Functions), 97% for Logistic (Functions), PART (Rules) and J48, LMT, Random Forest (Decision Trees), 96% for Bayes Net (Bayes), 95% for Logit Boost (Meta), 94% for Naive Bayes (Bayes). The developed models can be used to avoid mixing potato cultivars. Postharvest cultivar authentication can contribute to providing consumers with high-quality products.