Aktarımlı Öğrenme Yöntemleri ile Üzüm Bitkisi Yaprağından Hastalık Tespiti

Abstract

Günümüzde tarım sektörü, nüfus artışı ve kaynakların sınırlı olması gibi zorluklardan etkilenmektedir. Tarım sektörü için verimliliği artırmak ve kayıpları en aza indirmek büyük önem taşımaktadır. Bu nedenle, teknolojinin getirdiği yeniliklerden yararlanmak, özellikle sürdürülebilir tarım uygulamalarının geliştirilmesinde kritik bir rol oynamaktadır. Yapay zekâ, bu yeniliklerin başında gelmekte olup, tarımsal üretime katkı sağlama potansiyeline sahiptir. Bu çalışmanın temel amacı, bitki sağlığı konusunda çiftçilere hızlı ve doğru bilgiler sağlayarak, hastalıkların yayılmasını önlemek ve tarımsal üretimi optimize etmektir. Bu hedef doğrultusunda, yapay zekâ tabanlı görüntü işleme tekniklerinden yararlanılmıştır. Bu kapsamda, üzüm bitkisi yaprağı üzerinden bağ küllemesi ($Erysiphe$ $necator$), mildiyö ($Plasmopara$ $viticola$) ve bağ uyuzu ($Eriophyes$ $vitis$) hastalıklarının yapay zekâ ile tespiti sağlanmıştır. Hastalık tespiti için yaprak görüntüleri kullanılmış ve bu görüntüler üzerinden sınıflandırma gerçekleştirilmiştir. Çalışma kapsamında, bir kısmı hazır olarak temin edilen, bir kısmı ise bağ, tarla, bahçe gibi ortamlardan cep telefonu kamerası ile manuel olarak elde edilen çeşitli ve dengeli örneklerden oluşan bir karma veri seti oluşturulmuştur. Oluşturulan bu karma veri seti, CNN tabanlı aktarımlı öğrenme yöntemlerinden AlexNet, DarkNet53, Inception-ResNet-V2, Inception-V3, MobileNet-V3, ResNet50, ResNet101, VGG16 ve VGG19 mimarileri üzerinde eğitilmiştir. Eğitim ve test işlemleri sonucunda; %97.45 doğruluk, %8.19 eğitim kaybı, %93.00 test doğruluğu ve %20.60 test kaybı değerleri ile en başarılı model olarak Inception-ResNet-V2 belirlenmiştir. Bu sonuç, modelin hem eğitim hem de test verilerinde üzüm bitkisi yaprağı üzerinden hastalık tespiti için yüksek performans gösterdiğini ortaya koymaktadır.

Keywords

• Yapay zekâ
• Transfer öğrenmesi
• Bitki hastalığı tespiti
• Üzüm yaprağı hastalıkları
• Evrişimli sinir ağları.

Disease Detection from Grape Plant Leaves Using Transfer Learning Methods

Abstract

Today, the agricultural sector faces significant challenges due to population growth and limited resources. Enhancing productivity and minimizing losses is of great importance for the sustainability of agriculture. Therefore, leveraging technological advancements plays a critical role, particularly in the development of sustainable farming practices. Among these advancements, artificial intelligence (AI) stands out with its potential to contribute significantly to agricultural production. The primary objective of this study is to provide farmers with fast and accurate information regarding plant health, thereby preventing the spread of diseases and optimizing agricultural output. In line with this goal, AI-based image processing techniques were employed. Specifically, this study focuses on detecting grapevine leaf diseases namely powdery mildew ($Erysiphe$ $necator$), downy mildew ($Plasmopara$ $viticola$), and grapevine rust mite ($Eriophyes$ $vitis$) using AI. Disease detection was carried out using leaf images, which were then used for classification. A hybrid dataset was constructed using a combination of publicly available images and manually collected samples captured via smartphone cameras in vineyards, fields, and gardens. This diverse and balanced dataset was used to train several CNN-based transfer learning models, including AlexNet, DarkNet53, Inception-ResNet-V2, Inception-V3, MobileNet-V3, ResNet50, ResNet101, VGG16, and VGG19 architectures. Among these, Inception-ResNet-V2 achieved the best performance with an accuracy of 97.45%, a training loss of 8.19%, a test accuracy of 93.00%, and a test loss of 20.60%. These results demonstrate that the model performs well in detecting diseases from grapevine leaves during both training and testing phases.

Keywords

• Artificial intelligence
• Transfer learning
• Plant disease detection
• Grape leaf diseases
• Convolutional neural networks.

References

1. Gai, Y., & Wang, H. (2024). Plant disease: A growing threat to global food security. Agronomy, 14(8), 1615. https://doi.org/10.3390/agronomy14081615
2. Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70-90. https://doi.org/10.1016/j.compag.2018.02.016
3. Pertot, I., Caffi, T., Rossi, V., Mugnai, L., Hoffmann, C., Grando, M. S., Gary, C., Lafond, D., Duso, C., Thiery, D., Mazzoni, V., & Anfora, G. (2017). A critical review of plant protection tools for reducing pesticide use on grapevine and new perspectives for the implementation of IPM in viticulture. Crop Protection, 97, 70-84. https://doi.org/10.1016/j.cropro.2016.11.025
4. Ferentinos, K. P. (2018) Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311-318. https://doi.org/10.1016/j.compag.2018.01.009
5. Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for ımage-based plant disease detection. Frontiers in Plant Science, 7, 1419. https://doi.org/10.3389/fpls.2016.01419
6. Prashanthi, B., Praveen Krishna, A. V., & Mallikarjuna Rao, C. (2025). A comparative study of fine-tuning deep learning models for leaf disease ıdentification and classification. Engineering, Technology & Applied Science Research, 15(1), 19661-19669.
7. Mishra, A., Mishra, A., Tewari, A. K., & Gangrade, J. (2023, December). Deep Transfer Learning for Tomato Leaf Diseases Detection and Classification using Pre-trained Models. 2023 9th International Conference on Signal Processing and Communication (ICSC), Noida, India. https://ieeexplore.ieee.org/document/10441215
8. Fang, T., Chen, P., Zhang, J., & Wang, B. (2019, July). Identification of apple leaf diseases based on convolutional neural network. In International Conference on Intelligent Computing (pp. 553-564). Cham: Springer International Publishing.

9. Yaman, O., & Tuncer, T. (2022). Bitkilerdeki yaprak hastalığı tespiti için derin özellik çıkarma ve makine ögrenmesi yöntemi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 34(1), 123-132. https://doi.org/10.35234/fumbd.982348
10. Sladojevic S, Arsenovic M, Anderla A, Culibrk D, & Stefanovic D. (2016). Deep neural networks-based recognition of plant diseases by leaf image classification. Computational Intelligence and Neuroscience, 2016, 3289801. https://doi.org/10.1155/2016/3289801
11. Wagle, S. A., Sampe, J., Mohammad, F., & Ali, S. H. M. (2021). Effect of data augmentation in the classification and validation of tomato plant disease with deep learning methods. Traitement du Signal, 38(6), 1657-1670. https://doi.org/10.18280/ts.380609
12. Rao, U. S., Swathi, R., Sanjana, V., Arpitha, L., Chandrasekhar, K., & Naik, P. K. (2021). Deep learning precision farming: grapes and mango leaf disease detection by transfer learning. Global Transitions Proceedings, 2(2), 535-544. https://doi.org/10.1016/j.gltp.2021.08.002
13. Ajra, H., Majid, M. A., Shohidul Islam, Md., & Abdullah, D. (2025). Leaf disease detection in plant care using CNN architecture: AlexNet and resnet-50 models. International Journal on Advanced Science, Engineering and Information Technology (IJASEIT), 15(1), 283–292. https://doi.org/10.18517/ijaseit.15.1.19944
14. Nader, A., Khafagy, M. H., & Hussien, S. A. (2022). Grape leaves diseases classification using ensemble learning and transfer learning. International Journal of Advanced Computer Science and Applications, 3(7), 563-571. https://doi.org/10.14569/IJACSA.2022.0130767
15. Ananya Giliyal, A. (2022). Grape Disease Identification -Resnet50. [Dataset]. Kaggle. Grape_disease. Access Date: May,12, 2025. https://www.kaggle.com/datasets/pushpalama/grape-disease
16. Roboflow. (2023). Grape Leaf Disease Computer Vision Project. [Dataset]. https://universe.roboflow.com/tru-projects-cqcql/grape-leaf-disease-dataset
17. Hidiat. (2022). Grape Leaf Disease Classification with InceptionV3. [Dataset]. Kaggle. https://www.kaggle.com/code/yemi99/grape-leaf-disease-classification-with-inceptionv3/input
18. Uygun, T. (2024). Vineyard Leaf Scab (Eriophyes vitis Pagst.) Damage. [Dataset]. Mendeley Data. V1, doi: 10.17632/79f2wmdpmr.1
19. Akinci, T. C., Ekici, S., Kabir, M., & Martinez-Morales, A. A. (2024). HybridPlantNet23: A Scientific Insight into the Power of Ensemble Modelling using VGG16 and Darknet53 for Plant Disease Classification. Preprints. https://doi.org/10.20944/preprints202407.0556.v1
20. Suksukont, A. (2025). Integration of InceptionResNetV2 with VGG19 for sugarcane leaf disease recognition. RMUTSB Academic Journal, 13(1), 99–109. https://doi.org/10.64989/rmutsbj.2025.266380
21. Ataman, F., & Eroğlu, H. (2024). Comparative ınvestigation of deep convolutional networks in detection of plant diseases. Turkish Journal of Nature and Science, 13(3), 37-49. https://doi.org/10.46810/tdfd.1477476
22. Chai, M. X., Fam, Y. D., Octaviano, Q. N., Pee, C.-Y., Wong, L. K., Mohd Hilmi Tan, M. I. S., & See, J. (2024, December). Improved Cassava Plant Disease Classification with Leaf Detection, 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Macau, Macao. https://ieeexplore.ieee.org/document/10849031
23. Terven, J., Cordova-Esparza, D. M., Ramirez-Pedraza, A. Chavez-Urbiola, E. A., & Romero-González J. A. (2025). A comprehensive survey of loss functions and metrics in deep learning. Artificial Intelligence Review, 58(195). https://doi.org/10.1007/s10462-025-11198-7.
24. Ghojogh, B., & Crowley, M. (2019). The theory behind overfitting, cross validation, regularization, bagging, and boosting: tutorial. arXiv. https://doi.org/10.48550/arXiv.1905.12787
25. Bozuyla, M., & Özçift, A. (2022). Developing a fake news identification model with advanced deep language transformers for Turkish COVID-19 misinformation data. Turkish Journal of Electrical Engineering and Computer Sciences, 30(3), 908-926. https://doi.org/10.3906/elk-2106-55
26. Karasulu, B., Yücalar, F., & Borandağ, E. (2022). A hybrid approach based on deep learning for gender recognition using human ear images. Journal of the Faculty of Engineering and Architecture of Gazi University, 37(3), 1579-1594. https://doi.org/10.17341/gazimmfd.945188