Detecting Maturity in Fresh Lycium barbarum L. Fruit Using Color Information

The accurate quantitative maturity detection of fresh Lycium barbarum L. (L. barbarum) fruit is the key to determine whether are suitable for harvesting or not and can also be helpful improve quality post-harvest processing. To achieve this goal, abnormal samples were eliminated by Mahalanobis Distance (MD), nine components (i.e., R, G, B, H, S, V, L, a, b) ripe fruit, half-ripe unripe extracted, firstly. Then, significant component combinations three fruits beneficial extraction their areas determined. Through binary processing, morphology other image processing methods, a model was established based on support vector machine (SVM) model. On basis, field experiments conducted verify compare relationship between prediction results picking forces fruit. Field showed that accuracies both training set 100% consistent with Findings provided theoretical basis