Effect Evalution of Xiulijing on Fruit Rust Control of Golden Delicious Apple

[Objectives]The paper was to evaluate the effectiveness of Xiulijing in the management of rust in Golden Delicious apple cultivation.[Methods]The Golden Delicious apple was utilized as the test material.During the young fruit stage,various dilutions of Xiulijing were applied,specifically at concentrations of 200,400,600,800,1000,and 2000 times.Additionally,both the application of a 3000-fold dilution of GA 4+7 and the practice of fruit bagging were designated as the control treatments,while a water spray was utilized as the blank control.The fruit rust index and the incidence of rust-infected fruits were evaluated to assess the effectiveness of control measures for fruit rust in Golden Delicious apple cultivation.[Results]The application of Xiulijing,with dilutions ranging from 200 to 2000 times,exhibited a significant impact on reducing both the fruit rust index and the incidence of rust-infected fruits in Golden Delicious apples.The application of a 1000-fold dilution of Xiulijing resulted in a statistically significant reduction in both the fruit rust index and the incidence of rust-infected fruits,with reduction rates of 21.1%and 31.5%,respectively.Among the various strategies for the prevention and control of apple rust,fruit bagging emerged as the most effective method.The other two technical measures demonstrated significant control effects;however,no substantial differences were observed between them.[Conclusions]The biological control agent Xiulijing is more deserving of promotion and application in practical production due to its significantly superior economic benefits,safety,and stability.

Computer vision-based apple grading for golden delicious apples based on surface features

In this paper,a computer vision-based algorithm for golden delicious apple grading is proposed which works in six steps.Non-apple pixels as background are firstly removed from input images.Then,stem end is detected by combination of morphological methods and Mahalanobis distant classifier.Calyx region is also detected by applying K-means clustering on the Cb component in YCbCr color space.After that,defects segmentation is achieved using Multi-Layer Perceptron(MLP)neural network.In the next step,stem end and calyx regions are removed from defected regions to refine and improve apple grading process.Then,statistical,textural and geometric features from refined defected regions are extracted.Finally,for apple grading,a comparison between performance of Support Vector Machine(SVM),MLP and K-Nearest Neighbor(KNN)classifiers is done.Classification is done in two manners which in the first one,an input apple is classified into two categories of healthy and defected.In the second manner,the input apple is classified into three categories of first rank,second rank and rejected ones.In both grading steps,SVM classifier works as the best one with recognition rate of 92.5%and 89.2%for two categories(healthy and defected)and three quality categories(first rank,second rank and rejected ones),among 120 different golden delicious apple images,respectively,considering K-folding with K=5.Moreover,the accuracy of the proposed segmentation algorithms including stem end detection and calyx detection are evaluated for two different apple image databases.