Research Article
BibTex RIS Cite

Gelişmiş Yaprak Hastalığı Tespiti: Hassas Tarım için YOLOv9'un Transfer Öğrenme ile Entegre Edilmesi

Year 2025, Volume: 9 Issue: 1, 12 - 31
https://doi.org/10.31200/makuubd.1570013

Abstract

Yaprak hastalıkları, ürün sağlığını ve verimini tehdit ederek tarım için önemli bir zorluk oluşturmaktadır. Bu hastalıkların etkili bir şekilde tespiti ve yönetimi, sürdürülebilir tarım için kritik öneme sahiptir. Bu çalışma, YOLOv9 modelini ve transfer öğrenimini kullanarak tarımsal görüntülerde yaprak hastalıklarını tespit etmek için yeni bir yöntem sunmaktadır. YOLOv9'u çeşitli derin öğrenme kütüphaneleriyle entegre ederek, yaklaşımımız %98'lik bir sınıflandırma doğruluğuna ulaşmaktadır. Bu başarının üzerine inşa ederek, eğitilmiş modeli kullanarak gerçek zamanlı hastalık tespiti sağlayan bir mobil uygulama geliştirdik. Bu yöntemin temel gücü, hastalık etiketleri ve sınırlayıcı kutularla açıklanan düzenlenmiş veri setinde yatmaktadır. Bu veri seti, modelin sağlamlığını ve çok yönlülüğünü garanti ederek çeşitli ürünleri ve çevre
koşullarını kapsamaktadır. Kapsamlı deneyler, yaklaşımımızın hem doğruluk hem de verimlilik açısından geleneksel yöntemlerden daha iyi performans gösterdiğini göstermektedir. Ortaya çıkan mobil uygulama, çiftçilere ve tarımsal paydaşlara proaktif hastalık yönetimi için kullanıcı dostu bir araç sunmaktadır. Canlı kamera yayını aracılığıyla yaprak hastalıklarının gerçek zamanlı olarak tanımlanmasını sağlayarak zamanında müdahaleleri ve ürün korumasını kolaylaştırır. Yüksek doğruluğu gerçek zamanlı tespitle birleştirerek, bu yöntem mahsul verimliliğini önemli ölçüde artırabilir ve sürdürülebilir tarım uygulamalarına katkıda bulunabilir.

References

  • Oerke, E. C. (2006). Crop losses to pests. The Journal of Agricultural Science, 144(1), 31-43.
  • Savary, S., Ficke, A., Aubertot, J. N., & Hollier, C. (2012). Crop losses due to diseases and their implications for global food production losses and food security. Food Security, 4(4), 519-537.
  • Singh, A., Ganapathysubramanian, B., Sarkar, S., & Singh, A. K. (2016). Deep learning for plant stress phenotyping: Trends and future perspectives. Trends in Plant Science, 21(6), 558-568.
  • Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.
  • Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767.
  • Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359.
  • Xie, J., Wang, M., Zhu, T., Liu, Y., & Wong, T. T. (2015). A deep convolutional neural network for classification of crop types using multitemporal remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 54(1), 552-566.
  • Horvat, M., & Gledec, G. (2022, September). A comparative study of the YOLOv5 model's performance for image localization and classification. In 33rd Central European Conference on Information and Intelligent Systems (CECIIS) (p. 349).
  • Fan, J., Cui, L., & Fei, S. (2023). Waste detection system based on data augmentation and YOLO_EC. Sensors, 23(7), 3646. https://doi.org/10.3390/s23073646
  • Pan, S. J., Liu, J., & Chen, D. (2023). Research on license plate detection and recognition system based on YOLOv7 and LPRNet. Academic Journal of Science and Technology, 4(2), 62-68. https://doi.org/10.54097/ajst.v4i2.3971
  • Khan, M. U., Dil, M., Misbah, F. A., & Orakazi, M. (2023). Deep learning empowered fast and accurate multiclass UAV detection in challenging weather conditions. Preprints.org. https://doi.org/10.20944/preprints202212.0049.v1
  • Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779-788). https://doi.org/10.1109/CVPR.2016.91
  • Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, faster, stronger. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 6517-6525). https://doi.org/10.1109/CVPR.2017.690
  • Redmon, J., & Farhadi, A. (2018). YOLOv3. Technical Report, 1-6. https://pjreddie.com/media/files/papers/YOLOv3.pdf
  • Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv Preprint. https://arxiv.org/abs/2004.10934
  • Jocher, G., et al. (2022). Ultralytics/yolov5: v7.0-yolov5 SOTA realtime instance segmentation. Zenodo. https://doi.org/10.5281/zenodo.7347926
  • Li, C., et al. (2022). YOLOv6: A single-stage object detection framework for industrial applications. arXiv Preprint. https://arxiv.org/abs/2209.02976
  • Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of- the-art for real-time object detectors. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7464-7475).
  • Li, Y., Fan, Q., Huang, H., Han, Z., & Gu, Q. (2023). A modified YOLOv8 detection network for UAV aerial image recognition. Drones, 7(5), 304. https://doi.org/10.3390/drones7050304
  • Reis, D., Kupec, J., Hong, J., & Daoudi, A. (2023). Real-time flying object detection with YOLOv8. arXiv Preprint. https://doi.org/10.48550/arXiv.2305.09972
  • Lou, H., et al. (2023). DC-YOLOv8: Small-size object detection algorithm based on camera sensor. Electronics, 12(10), 2323. https://doi.org/10.3390/electronics12102323
  • Li, L., Zhang, S., & Wang, B. (2021). Plant disease detection and classification by deep learning—a review. IEEE Access, 9, 56683-56698.
  • Elhalid, O. B., Işık, A. H., & Özmen, Ö. (n.d.). YOLOv8 tabanlı derin öğrenme teknikleri yoluyla Giardia intestinalis görüntü algılamanın geliştirilmesi. International Journal of Engineering and Innovative Research. https://doi.org/10.47933/ijeir.1403833

Advanced Leaf Disease Detection: Integrating YOLOv9 with Transfer Learning for Precision Agriculture

Year 2025, Volume: 9 Issue: 1, 12 - 31
https://doi.org/10.31200/makuubd.1570013

Abstract

Leaf diseases pose a significant challenge to agriculture, threatening crop health and yield. Effective detection and management of these diseases are critical for sustainable farming. This study introduces a novel method for detecting leaf diseases in agricultural images by leveraging the YOLOv9 model and transfer learning. By integrating YOLOv9 with various deep-learning libraries, our approach achieves a classification accuracy of 98%. Building on this success, we developed a mobile application that provides real-time disease detection using the trained model. A key strength of this method lies in the curated dataset, annotated with disease labels and bounding boxes. This dataset encompasses diverse crops and environmental conditions, ensuring the robustness and versatility of the model. Extensive experiments demonstrate that our approach outperforms conventional methods in both accuracy and efficiency. The resulting mobile application offers farmers and agricultural stakeholders a user-friendly tool for proactive disease management. It enables real-time identification of leaf diseases via a live camera feed, facilitating timely interventions and crop protection. By combining high accuracy with real-
time detection, this method can significantly enhance crop productivity and contribute to sustainable agricultural practices.

References

  • Oerke, E. C. (2006). Crop losses to pests. The Journal of Agricultural Science, 144(1), 31-43.
  • Savary, S., Ficke, A., Aubertot, J. N., & Hollier, C. (2012). Crop losses due to diseases and their implications for global food production losses and food security. Food Security, 4(4), 519-537.
  • Singh, A., Ganapathysubramanian, B., Sarkar, S., & Singh, A. K. (2016). Deep learning for plant stress phenotyping: Trends and future perspectives. Trends in Plant Science, 21(6), 558-568.
  • Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.
  • Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767.
  • Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359.
  • Xie, J., Wang, M., Zhu, T., Liu, Y., & Wong, T. T. (2015). A deep convolutional neural network for classification of crop types using multitemporal remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 54(1), 552-566.
  • Horvat, M., & Gledec, G. (2022, September). A comparative study of the YOLOv5 model's performance for image localization and classification. In 33rd Central European Conference on Information and Intelligent Systems (CECIIS) (p. 349).
  • Fan, J., Cui, L., & Fei, S. (2023). Waste detection system based on data augmentation and YOLO_EC. Sensors, 23(7), 3646. https://doi.org/10.3390/s23073646
  • Pan, S. J., Liu, J., & Chen, D. (2023). Research on license plate detection and recognition system based on YOLOv7 and LPRNet. Academic Journal of Science and Technology, 4(2), 62-68. https://doi.org/10.54097/ajst.v4i2.3971
  • Khan, M. U., Dil, M., Misbah, F. A., & Orakazi, M. (2023). Deep learning empowered fast and accurate multiclass UAV detection in challenging weather conditions. Preprints.org. https://doi.org/10.20944/preprints202212.0049.v1
  • Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779-788). https://doi.org/10.1109/CVPR.2016.91
  • Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, faster, stronger. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 6517-6525). https://doi.org/10.1109/CVPR.2017.690
  • Redmon, J., & Farhadi, A. (2018). YOLOv3. Technical Report, 1-6. https://pjreddie.com/media/files/papers/YOLOv3.pdf
  • Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv Preprint. https://arxiv.org/abs/2004.10934
  • Jocher, G., et al. (2022). Ultralytics/yolov5: v7.0-yolov5 SOTA realtime instance segmentation. Zenodo. https://doi.org/10.5281/zenodo.7347926
  • Li, C., et al. (2022). YOLOv6: A single-stage object detection framework for industrial applications. arXiv Preprint. https://arxiv.org/abs/2209.02976
  • Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of- the-art for real-time object detectors. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7464-7475).
  • Li, Y., Fan, Q., Huang, H., Han, Z., & Gu, Q. (2023). A modified YOLOv8 detection network for UAV aerial image recognition. Drones, 7(5), 304. https://doi.org/10.3390/drones7050304
  • Reis, D., Kupec, J., Hong, J., & Daoudi, A. (2023). Real-time flying object detection with YOLOv8. arXiv Preprint. https://doi.org/10.48550/arXiv.2305.09972
  • Lou, H., et al. (2023). DC-YOLOv8: Small-size object detection algorithm based on camera sensor. Electronics, 12(10), 2323. https://doi.org/10.3390/electronics12102323
  • Li, L., Zhang, S., & Wang, B. (2021). Plant disease detection and classification by deep learning—a review. IEEE Access, 9, 56683-56698.
  • Elhalid, O. B., Işık, A. H., & Özmen, Ö. (n.d.). YOLOv8 tabanlı derin öğrenme teknikleri yoluyla Giardia intestinalis görüntü algılamanın geliştirilmesi. International Journal of Engineering and Innovative Research. https://doi.org/10.47933/ijeir.1403833
There are 23 citations in total.

Details

Primary Language English
Subjects Information Modelling, Management and Ontologies, Decision Support and Group Support Systems, Information Systems (Other)
Journal Section Articles
Authors

Osama Burak Elhalid 0000-0002-8051-7813

Edin Dolićanin 0000-0002-9896-8575

Ali Hakan Isık 0000-0003-3561-9375

Early Pub Date March 27, 2025
Publication Date
Submission Date October 18, 2024
Acceptance Date January 7, 2025
Published in Issue Year 2025 Volume: 9 Issue: 1

Cite

APA Elhalid, O. B., Dolićanin, E., & Isık, A. H. (2025). Advanced Leaf Disease Detection: Integrating YOLOv9 with Transfer Learning for Precision Agriculture. Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi, 9(1), 12-31. https://doi.org/10.31200/makuubd.1570013


14292     14293      14295 14921