Having the advantages of speed, suitability and high accuracy, computer vision has been effectively utilized as a non-destructive approach to automatically recognize and classify fruits and vegetables, to meet the increased demand for food quality-sensing devices. Primarily, this study focused on classifying apple varieties using machine learning techniques. Firstly, to discern how different convolutional neural network (CNN) architectures handle different apple varieties, transfer learning approaches, using popular seven CNN architectures (VGG16, VGG19, InceptionV3, MobileNet, Xception, ResNet150V2 and DenseNet201), were adopted, taking advantage of the pre-trained models, and it was found that DenseNet201 had the highest (97.48%) classification accuracy. Secondly, using the DenseNet201, deep features were extracted and traditional Machine Learning (ML) models: support vector machine (SVM), multi-layer perceptron (MLP), random forest classifier (RFC) and K-nearest neighbor (KNN) were trained. It was observed that the classification accuracies were significantly improved and the best classification performance of 98.28% was obtained using SVM algorithms. Finally, the effect of dimensionality reduction in classification performance, deep features, principal component analysis (PCA) and ML models was investigated. MLP achieved an accuracy of 99.77%, outperforming SVM (99.08%), RFC (99.54%) and KNN (91.63%). Based on the performance measurement values obtained, our study achieved success in classifying apple varieties. Further investigation is needed to broaden the scope and usability of this technique, for an increased number of varieties, by increasing the size of the training data and the number of apple varieties.

It is critically necessary to maximize the efficiency of agricultural methods while concurrently reducing the cost of production. Varieties, types, and fruit classification grades are crucial to fruit production. High expenditure, inconsistent subjectivity, and tedious labor characterize traditional and manual varieties classification. This study developed machine learning (ML) models to classify ten apple varieties, extracting the histogram of oriented gradient (HOG) and color moments from RGB apple images. Support vector machine (SVM), random forest classifier (RFC), multilayer perceptron (MLP), and K-nearest neighbor (KNN) classification models were trained with 10-fold stratified cross-validation (Skfold) by using the textural and color features, and a GridSearch was implemented to fine-tune the hyperparameters. The trained models, SVM, RFC, MLP, and KNN were tested with separate test data and performed well, having an accuracy of 98.17%, 96.67%, 98.62%, and 91.28%, respectively. Having the top results, the MLP and SVM models demonstrated the potential of applying HOG and color moments to train ML models for classifying apple varieties. This study suggests conducting further research to thoroughly examine additional image features and determine the impact of combining features and utilizing different classifiers.

Salt stress poses a substantial threat to fruit cultivation in arid and semi-arid regions. An essential aspect of mitigating this challenge involves understanding the adaptive changes in plants under salinity conditions. In this study, salinity stress (0, 20, 40, and 80 mM) induced in Ankara and Deveci pear varieties grafted onto OH×F 97, OH×F 333, and BA 29 rootstocks. Plant height and diameter, stomatal conductance, photosynthetic pigments and K⁺/Na⁺ ratio exhibited a decreasing trend, indicating the impact of salt stress. Conversely, the salt stress index and the activities of antioxidant enzymes including superoxide dismutase, catalase, and ascorbate peroxidase showed an increasing trend, highlighting the plant’s defense mechanisms against oxidative stress. In our comprehensive evaluation, the Deveci × OH×F 97 demonstrated a higher level of tolerance to sodium chloride stress compared to other combinations. Notably, combinations involving the BA 29, particularly Ankara × BA 29, exhibited more pronounced damage under NaCl stress. An intriguing finding was the announced response of enzymatic antioxidants, where despite a higher increase in SOD activity in the Deveci × OH×F 97, CAT and APX activities were generally higher in the Ankara × BA 29. This suggests the effective operation of enzymatic antioxidants in ameliorating oxidative damage in cells exposed to NaCl stress, irrespective of the overall stress tolerance of the plant, within the Pyrus. This study contributes valuable insights into the complex interplay between pear varieties, rootstocks, and NaCl stress, providing a foundation for informed decision-making in orchard management practices to enhance the resilience of pear cultivation in challenging environmental conditions.

Kuraklık stresi, birçok ürün grubunda olduğu gibi bahçe bitkilerinde de yetiştiriciliği kısıtlamaktadır. Yetiştiriciliği sınırlanan türler arasında armut (Pyrus ssp.) gelmektedir. Bitkiler stres faktörlerini dışsal uygulamalar ile kısmen yönetilebilmektedir. Önemli bir ozmolit olan glisin betain, kuraklık stresi gibi olumsuz çevre koşullarında osmotik basıncın düzenlenmesinde katkı sağlamaktadır. Yapılan çalışmada 18lt’lik saksılardaki bir yaşlı Ankara/BA 29 ve Deveci/BA 29 fidanlarına tarla kapasitesinin %50’si (orta stres) ve %25’i (ağır stres) kadar kısıtlı sulama suyu uygulanarak stres oluşturulmuştur. Stres uygulamalarının başında (0. gün) yapraktan 0 mM (kontrol) ve 10 mM glisin betain (GB) uygulamaları yapılmış, bazı morfolojik ve fizyolojik parametreler değerlendirilmiştir. Buna göre zararlanma derecesi stres sonucunda artmış ancak GB uygulamaları daha düşük puanlara sahip olmuşlardır. Membran stabilitesi kontrole kıyasla 10 mM GB uygulamalarında önemli şekilde artmıştır. İlaveten membran stabilitesi üzerine GB konsantrasyonu x stres şiddeti interaksiyonu önemli bulunmuştur. Sonuçlar yapraktan uygulanan glisin betainin kısıtlı su stresi altındaki Avrupa armutlarında oluşan stresi hafifletebileceğini göstermektedir.