Potato Leaf Disease Detection Using Faster R-CNN and YOLO Models

Abstract

Potato is one of the most important food crops globally in terms of total food production, significantly impacting the global economy. Infected potato plants show visible symptoms on their leaves, which drastically simplifies the process of early detection, disease prevention, and minimizing the risk to uninfected plants. Smart farming and new advanced technologies incorporate different tools for real-time monitoring and analysis. Most of the models used for potato leaf disease detection are based on Deep Learning architectures, most commonly on Convolutional Neural Network (CNN) architecture, which is suitable for computer vision and image recognition. This paper depicts and compares the performances of the YOLOv11 Object Detection (Fast) model, YOLOv11s model, and Faster R-CNN X101-FPN model. These models were trained on a dataset developed for object detection in Roboflow. This dataset consists of 1200 images and 1500 annotations. A single object was labeled as one of the six classes: Pest, Bacteria, Fungi, Healthy, Phytophthora, and Nematode. Performance metrics show that these models achieve reputable results without excessive training time, making them suitable for real-time monitoring systems. YOLOv11 Object Detection (Fast), YOLOv11s, and Faster R-CNN X101-FPN achieved mAP50 scores of 95.1%, 97.6%, and 92.62%, respectively.

Keywords

• YOLO models
• Faster R-CNN model
• Roboflow
• object detection
• potato leaf disesase

Faster R-CNN ve YOLO Modelleri Kullanılarak Patates Yaprağı Hastalığı Tespiti

Abstract

Patates, toplam gıda üretimi açısından küresel olarak en önemli tarım ürünlerinden biridir ve küresel ekonomi üzerinde önemli bir etkiye sahiptir. Enfekte olmuş patates bitkileri, yapraklarında görülebilir semptomlar gösterir, bu da erken tespit, hastalık önleme ve enfekte olmamış bitkiler için riskin azaltılması sürecini büyük ölçüde kolaylaştırır. Akıllı tarım ve yeni ileri teknolojiler, gerçek zamanlı izleme ve analiz için farklı araçlar içermektedir. Patates yaprağı hastalığı tespiti için kullanılan modellerin çoğu, genellikle Bilgisayarlı Görü ve görüntü tanıma için uygun olan Derin Öğrenme mimarilerine, en yaygın olarak Konvolüsyonel Sinir Ağı (CNN) mimarisine dayanmaktadır. Bu makale, YOLOv11 Nesne Tespiti (Hızlı) modeli, YOLOv11s modeli ve Faster R-CNN X101-FPN modelinin performanslarını tasvir etmekte ve karşılaştırmaktadır. Bu modeller, Roboflow'da nesne tespiti için geliştirilmiş bir veri seti üzerinde eğitilmiştir. Bu veri seti, 1200 görüntü ve 1500 anotasyondan oluşmaktadır. Tek bir nesne, altı sınıftan biri olarak etiketlenmiştir: Zararlı, Bakteri, Mantar, Sağlıklı, Phytophthora ve Nematod. Performans metrikleri, bu modellerin aşırı eğitim süresine ihtiyaç duymadan itibarlı sonuçlar elde ettiğini ve bunları gerçek zamanlı izleme sistemleri için uygun hale getirdiğini göstermektedir. YOLOv11 Nesne Tespiti (Hızlı), YOLOv11s ve Faster R-CNN X101-FPN sırasıyla %95,1, %97,6 ve %92,62 mAP50 skorlarına ulaşmıştır.

Keywords

• YOLO modelleri
• Faster R-CNN modeli
• Roboflow
• nesne tespiti
• patates yaprağı hastalığı

References

1. [1] Y. P. S. Bajaj, Potato, vol 3. Springer Science & Business Media, 2013.
2. [2] (2024) Food and Agriculture Organization of the united Nations. [Online]. Available: https://www.fao.org/faostat/en/#search/potato
3. [3] (2024) Potato Market Size- ndustry Report on Share, Growth Trends & Forecasts Analysis (2024-2029) on Mordor Intelligence [Online]. Available:https://www.mordorintelligence.com/industry-reports/ potato-market
4. [4] S. M. Dong, S.Q. Zhou,“ Potato late blight caused by Phytophthora infestans: From molecular interactions to integrated management strategies,” Journal of Integrative Agricultur, vol. 21, pp. 3456--3466, Dec. 2022.
5. [5] S. M. Metev and V. P. Veiko, Laser Assisted Microtechnology, 2nd ed., R. M. Osgood, Jr., Ed. Berlin, Germany: Springer-Verlag, 1998.
6. [6] W. J.Hooker., Compendium of potato diseases. International Potato Center, International Potato Center, 1981.
7. [7] A. Charkowski, K. Sharma, M. L. Parker, G. A. Secor and J. Elphinstone, “Bacterial Diseases of Potato” The potato crop: its agricultural, nutritional and social contribution to humankind, pp. 351--388, Dec. 2019.
8. [8] M. Sun, S. Chen and J. E. Kurle, “Interactive effects of soybean cyst nematode, arbuscular-mycorrhizal fungi, and soil pH on chlorophyll content and plant growth of soybean“ Phytobiomes Journal., vol. 6, pp. 95--105, Jan. 2022.

9. [9] M. Dhanaraju, P. Chenniappan, Poongodi, K. Ramalingam, S. Pazhanivelan, R. Kaliaperumal, “Smart farming: Internet of Things (IoT)-based sustainable agriculture” ,Agriculture, vol. 12, pp. 1745 , Sep. 2022.
10. [10] (2024) Subsets of Artificial Intelligence on Free Learning Platform for Better Future. [Online]. Available: https://tinyurl.com/2azettr3
11. [11] C. R. Arias, “An introduction to artificial” AI, Faith, and the Future: An Interdisciplinary Approach., pp. 12, Jun. 2022.
12. [12] L. Deng, Y. Dong, “Deep learning: methods and applications.” Foundations and trends® in signal processing., vol. 7, pp. 197--387 , 2014.
13. [13] (2024) R-CNN – Region-Based Convolutional Neural Networks on GeeksforGeeks. [Online]. Available: https://www.geeksforgeeks.org/r-cnn-region-based-cnns/
14. [14] (2024) Different types of CNN models on Opengenus. [Online]. Available: https://iq.opengenus.org/different-types-of-cnn-models/
15. [15] (2024) Ultralytics YOLO11. [Online]. Available: https://docs.ultralytics.com/models/yolo11/
16. [16] M. Islam, A. Dinh, K. Wahid, P. Bhowmik, Detection of potato diseases using image segmentation and multiclass support vector machine., 2017 IEEE 30th canadian conference on electrical and computer engineering (CCECE), 2017 .
17. [17] M. Ashikuzzaman, K. Roy, A. Lamon, S. Abedin, Potato Leaf Disease Detection By Deep Learning: A Comparative Study., 2024 6th International Conference on Electrical Engineering and Information \& Communication Technology (ICEEICT), 2024 .
18. [18] Y. Zarrouk, M. Yandouzi, M. Grari, M. Bourhaleb, M. Rahmoune, K. Hachami., “Revolutionizing Potato Late Blight Surveillance: uav-driven Object Detection Innovations, Journal of Theoretical and Applied Information Technology., vol. 102, Apr. 2024.
19. [19] D. Kothari, H. Mishra, M. Gharat, V. Pandey, M. Gharat, R. Thakur, “Potato leaf disease detection using deep learning” Int. J. Eng. Res. Technol, vol. 1, pp. 569–571, Nov. 2022.
20. [20] (2023) Potato Leaf Disease Dataset in Uncontrolled Environment on mendeley data. [Online]. Available: https://data.mendeley.com/ datasets/ptz377bwb8/1
21. [21] (2024) Potato_leaf_disease Computer Vision Project dataset on Roboflow. [Online]. Available: https://universe.roboflow.com/potato-leaf-diseases/potato_leaf_disease
22. [22] (2024) What is deep learning? on IBM. [Online]. Available: https://www.ibm.com/topics/deep-learning
23. [23] (2024) Difference between Shallow and Deep Neural Networkson on GeeksforGeeks [Online]. Available: https://www.geeksforgeeks.org/ difference-between-shallow-and-deep-neural-networks/
24. [24] (2024) Convolutional Neural Network (CNN) on TensorFlow [Online]. Available: https://www.tensorflow.org/tutorials/images/cnn
25. [25] R. Yamashita, M. Nishio, R. K. G. Do, K. Togashi, “Convolutional neural networks: an overview and application in radiology” Insights into imaging, vol. 9, pp. 611--629, Jun. 2018.
26. [26] (2024) What are convolutional neural networks? on IBM. [Online]. Available:https://www.ibm.com/topics/convolutional-neural-networks
27. [27] (2019) Object Detection: Architectures, Models, and Use Cases on The Random Walk Blog. [Online]. Available: https://randomwalk.ai/ blog/object-detection-architectures-models-and-use-cases/
28. [28] (2024) What is object detection? on IBM. [Online]. Available: https://www.ibm.com/topics/object-detection
29. [29] G. Jocher, J. Qiu (2024), Ultralytics YOLO11, version = 11.0.0, year = {2024}, [Online].Available:https://github.com/ultralytics/ ultralytics
30. [30] H. Vedoveli (2013) Metrics Matter: A Deep Dive into Object Detection Evaluation.[Online].Available:https://medium.com/@henriquevedoveli/metrics-matter-a-deep-dive-into-object-detection-evaluationef01385 ec62
31. [31] J. Solawetz, P. Guerrie.(2022). What to Think About When Choosing Model Sizes. Roboflow Blog: https://blog.roboflow.com/ computer-vision-model-tradeoff/
32. [32] (2024) R-CNN – Region-Based Convolutional Neural NetworksNetworkson on GeeksforGeeks [Online]. Available: https://www.geeksforgeeks.org/r-cnn-region-based-cnns/
33. [33] (2019) Y. Wu, A. Kirillov, F. Massa, et al. Detectron2.[Online]. Available: https://github.com/facebookresearch/detectron2