The Use of Digital Color Imaging and Machine Learning for the Evaluation of the Effects of Shade Drying and Open-Air Sun Drying on Mint Leaf Quality

The objective of this study was to reveal the usefulness image processing and machine learning for non-destructive evaluation changes in mint leaves caused by two natural drying techniques. effects shade open-air sun on ventral side (upper surface) dorsal (lower were compared. Texture parameters extracted from digital color images converted channels R, G, B, L, a, b, X, Y, Z. Models based features selected individual built distinguishing terms techniques leaf using algorithms groups Lazy, Rules, Trees. In case classification fresh shade-dried leaves, an average accuracy 100% values Precision, Recall, F-Measure, MCC 1.000 obtained B (KStar J48 algorithms), a J48), b (KStar), Y (KStar). effect greater. Images sun-dried completely correctly distinguished (100% correctness) more algorithms, such as R G (J48), (KStar, JRip, X provided channel (KStar) J48). imaged classified at textures Z (J48). developed approach may be used practice monitor structure non-destructive, objective, cost-effective, fast manner without need damage leaves.