Evaluation of the postharvest quality of lacto-fermented radish using innovative discriminative models based on textures of images

Fermentation is one of the ways of preservation of fruit and vegetables. The objective of this study was to evaluate the changes in the textures of slice images of radish subjected to lacto-fermentation after harvesting. The effect of postharvest processing on the radish quality was evaluated using the innovative discriminative models built based on sets of selected textures of images acquired with the use of a digital camera and converted to color channels R, G, B, L, a, b, U, V, X, Y, Z. The models were developed for individual color channels and color spaces RGB, Lab, YUV, XYZ using discriminative classifiers, and were used to distinguish between fresh and lacto-fermented radishes. The accuracies of discrimination for fresh and lacto-fermented radishes, average accuracies for both samples, as well as TP Rate (True Positive Rate), Precision, F-Measure, ROC Area (Area Receiver Operating Characteristic Area) and PRC Area (Precision-Recall Area), were determined. The high values of these metrics indicated large changes in textures of lacto-fermented radishes compared to non-processed samples. The correctness of discrimination reached 100% in the case of models built for each color space and color channels R, B, b, U for selected classifiers (Logistic, Multi Class Classifier). In these cases, the values of TP Rate, Precision, F-Measure, ROC Area and PRC Area were equal to 1.000. The results demonstrated the effect of lacto-fermentation on the radish quality expressed in the changes in textures of images. The usefulness of image analysis for the evaluation of the postharvest processing of radish was also proven.