Bitki Hastalıklarının Tespiti için Ön İşlemli Görsel Dönüştürücü Tabanlı bir Yaklaşım

Abstract

İnsanlığın ihtiyaç duyduğu gıda miktarı, dünya nüfusuna paralel olarak artmalıdır. Gıda yetiştiriciliğinin en önemli noktası sağlıklı yetişen bitkilerdir. Bu çalışma, tarımsal verimliliği ve sürdürülebilirliği artırmak için gerekli olan bitki hastalıklarının tespitinin kritik konusunu ele almaktadır. Çalışma, bitki hastalıklarını yüksek doğrulukla tespit etmek için derin öğrenme modelleri ve bölütlemeye dayalı Vision Transformer (Vit 16B) modeli ile birleştirilmiş görüntü işleme tekniklerini kullanan yeni bir yöntem sunmaktadır. Modelin akıllı tarımda uygulanması, daha iyi hastalık yönetimine ve ekonomik faydalar sağlayacağı ortaya koymuştur. Çalışmada aynı zamanda önerilen modelin performansını, 8 farklı derin öğrenme mimarileriyle karşılaştırarak önerilen modelin başarımı ortaya konmuştur. Önerilen model, derin öğrenme modellerinden daha iyi performans gösterdiği ve %99,87'lik etkileyici bir doğruluk elde edildiği saptanmıştır. Sonuçlar, her sınıf için hassasiyet, hatırlama ve F1 puanları gibi ayrıntılı ölçümlerle desteklenmiştir.

Keywords

• Derin Öğrenme
• Görüntü Dönüştürücü
• Görüntü İşleme
• Akıllı Tarım
• Tarımsal Verimlilik
• Bitki Hastalıkları

A Pre-Processed Visual Transformer Based Approach for Plant Disease Detection

Abstract

The amount of food needed by humanity is increasing along with the world population. For healthier and higher yields, plants need to grow healthy. Diseases that occur in plants reduce the yield in crop cultivation. This study addresses the detection of plant diseases, which is necessary to increase agricultural productivity and sustainability. The study presents a new method that uses image processing techniques combined with deep learning models and segmentation-based Vision Transformer (Vit 16B) model to detect plant diseases with high accuracy. The aim of the model is to use it in smart agriculture, to enable early and accurate plant disease detection and to obtain high economic efficiency. In the study, the performance of the proposed model was compared with 8 different deep learning (AlexNet, SqueezeNet, ResNet18, ResNet50, ResNet101, GoogleNet, Vgg16, Vgg19) models and its success was demonstrated. It was determined that the proposed model outperformed the deep learning models and achieved an accuracy of 99.87%. For each class, the performances are demonstrated with the evaluation metrics of precision, recall and F1 scores.

Keywords

• Deep Learning
• Vision Transformer
• Image Processing
• Smart Agriculture
• Agricultural Productivity
• Plant Disease

References

1. Eren, M. V., "Nüfus Artişi ile Kalkinma Arasindakİ İlişki: Sahra-Alti Afrika Ülkeleri Üzerine Ampirik Bir Analİz," Uluslararası İktisadi ve İdari İncelemeler Dergisi, no. 27, 2020, pp. 141-158, doi: https://doi.org/10.18092/ulikidince.586948.
2. Kılavuz, E. and Erdem, İ., "Dünyada tarım 4.0 uygulamaları ve Türk tarımının dönüşümü," Social Sciences, vol. 14, no. 4, 2019, pp. 133-157.
3. Gövez, E., "Tarim Sektörüne Yenilikçi Bir Bakiş Açisi: Tarim 4.0," Sosyal Sorunlar (Teoriler, Politikalar, Uygulamalar), 2023, p. 87.
4. Doğan, F. and Türkoğlu, İ., "Derin öğrenme modelleri ve uygulama alanlarına ilişkin bir derleme," Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, vol. 10, no. 2, 2019, pp. 409-445, doi: https://doi.org/10.24012/dumf.411130.
5. Bayram, C. A., "The Effects of Mycorrhiza and Seaweed Applications on Seedling Growth Parameters: Tomato and Pepper," Communications in Soil Science and Plant Analysis, vol. 55, no. 10, 2024, pp. 1375-1389, doi: https://doi.org/10.1080/00103624.2024.2305844.
6. YILDIZ, H., İlker, E., and YILDIRIM, A., "Bazı silajlık mısır (Zea mays) çeşit ve çeşit adaylarının verim ve kalite özelliklerinin belirlenmesi," Ziraat Fakültesi Dergisi, vol. 12, no. 2, 2017, pp. 81-89.
7. Büyük, G., Bayram, C. A., İnan, M., and Kırpık, M., "The effect of organic and inorganic fertilizers on plant nutrient content and agronomic performance of stevia," Journal of Plant Nutrition, vol. 45, no. 15, 2022, pp. 2303-2314, doi: https://doi.org/10.1080/01904167.2022.2063739.
8. Özdemir, R. and Demirbaş, N., "Meyve ve sebze üretiminde ortaya çıkan kayıplar üzerinde etkili olan faktörler: İzmir ili örneği," Mediterranean Agricultural Sciences, vol. 33, no. 1, 2020, pp. 85-91, doi: https://doi.org/10.29136/mediterranean.659011.

9. ERTAŞ, B., "Tarım 4.0 ile sürdürülebilir bir gelecek," Icontech International Journal, vol. 4, no. 1, 2020, pp. 1-12, doi: https://doi.org/10.46291/ICONTECHvol4iss1pp1-12.
10. Doğan, F. and Türkoğlu, İ., "Derin öğrenme algoritmalarının yaprak sınıflandırma başarımlarının karşılaştırılması," Sakarya University Journal of Computer and Information Sciences, vol. 1, no. 1, 2018, pp. 10-21.
11. Tay, Y., Dehghani, M., Bahri, D., and Metzler, D., "Efficient transformers: A survey," ACM Computing Surveys, vol. 55, no. 6, 2022, pp. 1-28.
12. Solak, M., "Moleküler Biyoloji ve Genetik: Sağlık Alanında ve Biyoteknolojide İleri Uygulamalar," ed: Türkiye Bilimler Akademisi, 2023.
13. Koçak, R., "Beşinci sanayi devrimi toplum 5.0 ve yapay zekâ kültürü," Uluslararası Halkbilimi Araştırmaları Dergisi, vol. 3, no. 5, 2020, pp. 1-17.
14. Güzel, B. and Okatan, E., "Tarim Ve Yapay Zekâ," Yapay Zekânin Değiştirdiği Dinamikler, 2022, p. 199.
15. Doğan, F., Oyucu, S., Bicer, E., and Aksoz, A., "Deep learning models for damage type detection in wind turbines," PeerJ Computer Science, vol. 11, 2025, p. e3163, doi: https://doi.org/10.7717/peerj-cs.3163.
16. Doğan, F., Aktaş, M., and Gürsoy, M. İ., "Classification of Skin Diseases with Different Deep Learning Models and Comparison of the Performances of the Models," Türk Doğa ve Fen Dergisi, vol. 13, no. 3, 2024, pp. 117-123, doi: https://doi.org/10.46810/tdfd.1502471.
17. Sam, S. M., Kamardin, K., Sjarif, N. N. A., and Mohamed, N., "Offline signature verification using deep learning convolutional neural network (CNN) architectures GoogLeNet inception-v1 and inception-v3," Procedia Computer Science, vol. 161, 2019, pp. 475-483, doi: https://doi.org/10.1016/j.procs.2019.11.147.
18. Vaswani, A. et al., "Attention is all you need," Advances in neural information processing systems, vol. 30, 2017.
19. Dosovitskiy, A. et al., "An image is worth 16x16 words: Transformers for image recognition at scale," arXiv preprint arXiv:2010.11929, 2020.
20. Zhou, L., Xiao, Q., Taha, M. F., Xu, C., and Zhang, C., "Phenotypic analysis of diseased plant leaves using supervised and weakly supervised deep learning," Plant Phenomics, vol. 5, 2023, p. 0022, doi: https://doi.org/10.34133/plantphenomics.0022.
21. Pavithra, A. and Kalpana, G., "Automated Leaf Disease Identification and Analysis in Precision Agriculture based on Deep Learning," in 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), 2023: IEEE, pp. 1363-1367, doi: 10.1109/ICSSIT55814.2023.10061149.
22. Agarwal, M., Gill, K. S., Upadhyay, D., and Devliyal, S., "From Pixels to Insights: Harnessing Deep Learning for Accurate Plant Pathology Diagnosis," in 2024 International Conference on Intelligent Systems for Cybersecurity (ISCS), 2024: IEEE, pp. 1-5, doi: https://doi.org/10.1109/ISCS61804.2024.10581100.
23. Eunice, J., Popescu, D. E., Chowdary, M. K., and Hemanth, J., "Deep learning-based leaf disease detection in crops using images for agricultural applications," Agronomy, vol. 12, no. 10, 2022, p. 2395, doi: https://doi.org/10.3390/agronomy12102395.
24. Tran-Anh, D., Nguyen Huu, Q., Nguyen Thi Phuong, T., and Dao Thi Thuy, Q., "Leaf disease classification with Multiple-model deep learning," Journal of Intelligent & Fuzzy Systems, no. Preprint, 2024, pp. 1-13, doi: https://doi.org/10.3233/JIFS-235940.
25. Balamurugan, M., Srividhya, N., Indhumathi, G., Arul, V., and Kalaiarasi, K., "Deep Learning Innovations for Improved Plant Leaf Disease Detection in Smart Agriculture," in 2024 Second International Conference on Data Science and Information System (ICDSIS), 2024: IEEE, pp. 1-6, doi: https://doi.org/10.1109/ICDSIS61070.2024.10594188.
26. Singh, G. and Yogi, K. K., "Performance evaluation of plant leaf disease detection using deep learning models," Archives of Phytopathology and Plant Protection, vol. 56, no. 3, 2023, pp. 209-233, doi: https://doi.org/10.1080/03235408.2023.2183792.
27. Sucharitha, G., Sirisha, M., Pravalika, K., and Gayathri, K. N., "A Study on the Performance of Deep Learning Models for Leaf Disease Detection," EAI Endorsed Transactions on Internet of Things, vol. 10, 2024.
28. Mohanty, S. P., Hughes, D. P., and Salathé, M., "Using deep learning for image-based plant disease detection," Frontiers in plant science, vol. 7, 2016, p. 1419, doi: https://doi.org/10.3389/fpls.2016.01419.
29. Siddharth, S. C., Singh, U., Kaul, A., and Jain, S., "A database of leaf images: practice towards plant conservation with plant pathology," Mendeley Data, 2019.
30. Kour, V. P. and Arora, S., "Plantaek: A leaf database of native plants of jammu and kashmir," in Recent Innovations in Computing: Proceedings of ICRIC 2021, Volume 1: Springer, 2022, pp. 359-368.
31. Singh, D., Jain, N., Jain, P., Kayal, P., Kumawat, S., and Batra, N., "PlantDoc: A dataset for visual plant disease detection," in Proceedings of the 7th ACM IKDD CoDS and 25th COMAD, 2020, pp. 249-253.
32. Durieux, A. "Plant Pathology 2021 - FGVC8." Kaggle Competition. https://www.kaggle.com/c/plant-pathology-2021-fgvc8/overview (accessed 2021).
33. Wiesner-Hanks, T. et al., "Image set for deep learning: field images of maize annotated with disease symptoms," BMC research notes, vol. 11, 2018, pp. 1-3, doi: https://doi.org/10.1186/s13104-018-3548-6.
34. Rauf, H. T., Saleem, B. A., Lali, M. I. U., Khan, M. A., Sharif, M., and Bukhari, S. A. C., "A citrus fruits and leaves dataset for detection and classification of citrus diseases through machine learning," Data in brief, vol. 26, 2019, p. 104340, doi: https://doi.org/10.1016/j.dib.2019.104340.
35. Sethy, P. K., Barpanda, N. K., Rath, A. K., and Behera, S. K., "Deep feature based rice leaf disease identification using support vector machine," Computers and Electronics in Agriculture, vol. 175, 2020, p. 105527, doi: https://doi.org/10.1016/j.compag.2020.105527.
36. Jepkoech, J., Mugo, D. M., Kenduiywo, B. K., and Too, E. C., "Arabica coffee leaf images dataset for coffee leaf disease detection and classification," Data in brief, vol. 36, 2021, p. 107142.
37. Mwebaze, E., Gebru, T., Frome, A., Nsumba, S., and Tusubira, J., "iCassava 2019 fine-grained visual categorization challenge," arXiv preprint arXiv:1908.02900, 2019, doi: https://doi.org/10.48550/arXiv.1908.02900.
38. Prajapati, H. B., Shah, J. P., and Dabhi, V. K., "Detection and classification of rice plant diseases," Intelligent Decision Technologies, vol. 11, no. 3, 2017, pp. 357-373, doi: https://doi.org/10.3233/IDT-170301.
39. Pacal, I., "Enhancing crop productivity and sustainability through disease identification in maize leaves: Exploiting a large dataset with an advanced vision transformer model," Expert Systems with Applications, vol. 238, 2024, p. 122099, doi: https://doi.org/10.1016/j.eswa.2023.122099.
40. Li, L.-H. and Tanone, R., "Disease identification in potato leaves using swin transformer," in 2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM), 2023: IEEE, pp. 1-5, doi: https://doi.org/10.1109/IMCOM56909.2023.10035609.
41. Bhowmik, A. C., Ahad, M. T., Emon, Y. R., Ahmed, F., Song, B., and Li, Y., "A customised Vision Transformer for accurate detection and classification of Java Plum leaf disease," Smart Agricultural Technology, vol. 8, 2024, p. 100500, doi: https://doi.org/10.1016/j.atech.2024.100500.
42. Zhu, W., Sun, J., Wang, S., Shen, J., Yang, K., and Zhou, X., "Identifying field crop diseases using transformer-embedded convolutional neural network," Agriculture, vol. 12, no. 8, 2022, p. 1083, doi: https://doi.org/10.3390/agriculture12081083.
43. Hossain, S., Tanzim Reza, M., Chakrabarty, A., and Jung, Y. J., "Aggregating different scales of attention on feature variants for tomato leaf disease diagnosis from image data: a transformer driven study," Sensors, vol. 23, no. 7, 2023, p. 3751, doi: https://doi.org/10.3390/s23073751.
44. Ali, M., Salma, M., El Haji, M., and Jamal, B., "Plant disease detection using vision transformers," International Journal of Electrical and Computer Engineering (IJECE), vol. 15, no. 2, 2025, pp. 2334-2344, doi: http://doi.org/10.11591/ijece.v15i2.pp2334-2344.
45. Hemalatha, S. and Jayachandran, J. J. B., "A multitask learning-based vision transformer for plant disease localization and classification," International Journal of Computational Intelligence Systems, vol. 17, no. 1, 2024, p. 188.
46. De Silva, M. and Brown, D., "Plant disease detection using vision transformers on multispectral natural environment images," in 2023 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD), 2023: IEEE, pp. 1-6, doi: https://doi.org/10.1109/icABCD59051.2023.10220517.
47. Thakur, P. S., Chaturvedi, S., Khanna, P., Sheorey, T., and Ojha, A., "Vision transformer meets convolutional neural network for plant disease classification," Ecological Informatics, vol. 77, 2023, p. 102245, doi: https://doi.org/10.1016/j.ecoinf.2023.102245.
48. Hughes, D. and Salathé, M., "An open access repository of images on plant health to enable the development of mobile disease diagnostics," arXiv preprint arXiv:1511.08060, 2015, doi: https://doi.org/10.48550/arXiv.1511.08060.
49. Krizhevsky, A., Sutskever, I., and Hinton, G. E., "ImageNet classification with deep convolutional neural networks," Communications of the ACM, vol. 60, no. 6, 2017, pp. 84-90.
50. Simonyan, K. and Zisserman, A., "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
51. Iandola, F. N., "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size," arXiv preprint arXiv:1602.07360, 2016.
52. He, K., Zhang, X., Ren, S., and Sun, J., "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
53. Szegedy, C. et al., "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9.
54. Doğan, F. and Türkoğlu, İ., "Comparison of deep learning models in terms of multiple object detection on satellite images," Journal of Engineering Research, vol. 10, no. 3, 2022, pp. 89-108, doi: https://doi.org/10.36909/jer.12843.