The Analysis of Architectural YOLOv5 Convolutional Neural Networks for Detecting Apple Leaf Diseases

##plugins.themes.academic_pro.article.sidebar##

Published Feb 25, 2025
https://doi.org/10.55043/jaast.v9i1.251
Download
PDF
Statistic
Vol. 9 No. 1 (2025): Journal of Applied Agricultural Science and Technology

##plugins.themes.academic_pro.article.main##

Moh. Erkamim
Universitas Tunas Pembangunan
Muhammad Zidni Subarkah
Universitas Sebelas Maret
R. Soelistijono
Universitas Tunas Pembangunan

Abstract

Apple cultivation is crucial to agricultural economies, particularly in regions with sub-tropical climates, such as Indonesia, where apple farming is expanding rapidly. However, managing diseases and pests is essential for maintaining optimal crop yields, as they can significantly reduce production. Among the common diseases affecting apple trees are Scab, Black Rot, and Cedar Apple Rust, which primarily impact leaves and threaten the total health of the plant. Therefore, this research aimed to develop an effective model for detecting apple leaf diseases using the architectural YOLOv5 Convolutional Neural Networks (CNNs). The analysis was conducted between November 2022 and February 2023 at the Smart City Information System (SIKC) laboratory, including 120 apple leaf samples collected from Tawangmangu. Additionally, secondary data containing 30 images for each disease category, consisting of Healthy, Scab, Black Rot, and Cedar Apple Rust, were used as a benchmark. The performance of YOLOv5 was evaluated based on several metrics, including Precision, Recall, mAP@0.5, and mAP@0.5:0.95. The results showed that Cedar Apple Rust was the most prevalent disease identified among the samples. YOLOv5 performed exceptionally well in detecting disease symptoms, achieving a Precision score of 0.810, Recall of 0.981, mAP@0.5 of 0.950, and mAP@0.5:0.95 of 0.765 on the test dataset. These results showed that the proposed model was highly accurate and reliable for the early detection of apple leaf diseases, offering significant potential for improving disease management strategies and increasing the efficiency of apple production.

##plugins.themes.academic_pro.article.details##

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author Biographies

Moh. Erkamim, Universitas Tunas Pembangunan

Department of Engineering Faculty

R. Soelistijono, Universitas Tunas Pembangunan

Department of Engineering Faculty

How to Cite
1.
Erkamim M, Subarkah MZ, Soelistijono R. The Analysis of Architectural YOLOv5 Convolutional Neural Networks for Detecting Apple Leaf Diseases. J. appl. agricultural sci. technol. [Internet]. 2025Feb.25 [cited 2025Apr.26];9(1):40-52. Available from: http://jaast.org/index.php/jaast/article/view/251

References

  1. Mayalekshmi KM, Ranjan A, Machavaram R. In-field Chilli Crop Disease Detection Using YOLOv5 Deep Learning Technique. 2023 IEEE 8th International Conference for Convergence in Technology (I2CT), Lonavla, India: IEEE; 2023, p. 1–6. https://doi.org/10.1109/I2CT57861.2023.10126468.
  2. Harper LJ, Deaton BJ, Driskel JA. Pangan, gizi dan pertanian. Jakarta: UI-Press; 1986. https://lontar.ui.ac.id/detail?id=20470775
  3. Gaffar HD, Hasan YTN, Aprilia N. The Effectiveness of Rome Beauty Apple Peel Extract (Malus sylvestris Mill) on the Growth of Salmonella Typhi. Open Access Maced J Med Sci 2022;10:848–53. https://doi.org/10.3889/oamjms.2022.8820.
  4. Tardío J, Arnal A, Lázaro A. Ethnobotany of the crab apple tree (Malus sylvestris (L.) Mill., Rosaceae) in Spain. Genet Resour Crop Evol 2021;68:795–808. https://doi.org/10.1007/s10722-020-01026-y.
  5. Kumari M. Biology and feeding potential Episyrphus balteatus De Geer (Diptera: Syrphidae) on green apple aphid Aphis pomi De Geer (order Hemiptera: Aphididae) in Hills of Shimla, (H.P.), India. Environ Conserv J 2020;21:147–50. https://doi.org/10.36953/ECJ.2020.211218.
  6. Sever Z, Ivić D, Kos T, Miličević T. Identification of Fusarium Species Isolated From Stored Apple Fruit in Croatia / Identifikacija Vrsta Roda Fusarium Izoliranih S Plodova Jabuke Nakon Skladištenja. Archives of Industrial Hygiene and Toxicology 2012;63:463–70. https://doi.org/10.2478/10004-1254-63-2012-2227.
  7. Mannai S, Horrigue-Raouani N, Boughalleb-M’Hamdi N. Characterization of Fusarium species associated with apple decline in Tunisian nurseries. Journal of Biological Studies 2018;1:14–34. https://onlinejbs.com/index.php/jbs/article/view/7/7
  8. Ratnawati L, Sulistyaningrum DR. Penerapan Random Forest untuk Mengukur Tingkat Keparahan Penyakit pada Daun Apel. Jurnal Sains Dan Seni ITS 2020;8. https://doi.org/10.12962/j23373520.v8i2.48517.
  9. Soriano JM, Joshi SG, van Kaauwen M, Noordijk Y, Groenwold R, Henken B, et al. Identification and mapping of the novel apple scab resistance gene Vd3. Tree Genet Genomes 2009;5:475–82. https://doi.org/10.1007/s11295-009-0201-5.
  10. Xuan G, Gao C, Shao Y, Zhang M, Wang Y, Zhong J, et al. Apple Detection in Natural Environment Using Deep Learning Algorithms. IEEE Access 2020;8:216772–80. https://doi.org/10.1109/ACCESS.2020.3040423.
  11. Rocafort M, Bowen JK, Hassing B, Cox MP, McGreal B, de la Rosa S, et al. The Venturia inaequalis effector repertoire is dominated by expanded families with predicted structural similarity, but unrelated sequence, to avirulence proteins from other plant-pathogenic fungi. BMC Biol 2022;20:246. https://doi.org/10.1186/s12915-022-01442-9.
  12. Yu H, Cheng X, Chen C, Heidari AA, Liu J, Cai Z, et al. Apple leaf disease recognition method with improved residual network. Multimed Tools Appl 2022;81:7759–82. https://doi.org/10.1007/s11042-022-11915-2.
  13. Beer M, Brockamp L, Weber RWS. Control of sooty blotch and black rot of apple through removal of fruit mummies. Folia Horticulturae 2015;27:43–51. https://doi.org/10.1515/fhort-2015-0013.
  14. Kuznetsova A, Maleva T, Soloviev V. YOLOv5 versus YOLOv3 for Apple Detection. Cyber-Physical Systems: Modelling and Intelligent Control, 2021, p. 349–58. https://doi.org/10.1007/978-3-030-66077-2_28.
  15. Mathew MP, Mahesh TY. Leaf-based disease detection in bell pepper plant using YOLO v5. Signal Image Video Process 2022;16:841–7. https://doi.org/10.1007/s11760-021-02024-y.
  16. Xue Z, Xu R, Bai D, Lin H. YOLO-Tea: A Tea Disease Detection Model Improved by YOLOv5. Forests 2023;14:415. https://doi.org/10.3390/f14020415.
  17. Zhong Y, Zhao M. Research on deep learning in apple leaf disease recognition. Comput Electron Agric 2020;168:105146. https://doi.org/10.1016/j.compag.2019.105146.
  18. Ahmed MR, Ahmed SR, Duru AD, Uçan ON, Bayat O. An Expert System to Predict Eye Disorder Using Deep Convolutional Neural Network. Academic Platform Journal of Engineering and Science 2021;9:47–52. https://doi.org/10.21541/apjes.741194.
  19. Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE; 2017, p. 6517–25. https://doi.org/10.1109/CVPR.2017.690.
  20. Yadav SS, Jadhav SM. Deep convolutional neural network based medical image classification for disease diagnosis. J Big Data 2019;6:113. https://doi.org/10.1186/s40537-019-0276-2.
  21. Iswantoro D, Un DH. Klasifikasi Penyakit Tanaman Jagung Menggunakan Metode Convolutional Neural Network (CNN). Jurnal Ilmiah Universitas Batanghari Jambi 2022;22:900. https://doi.org/10.33087/jiubj.v22i2.2065.
  22. Wicaksono G, Andryana S, Benrahman. Aplikasi Pendeteksi Penyakit Pada Daun Tanaman Apel Dengan Metode Convolutional Neural Network. JOINTECS (Journal of Information Technology and Computer Science) 2020;5:9. https://doi.org/10.31328/jointecs.v5i1.1221.
  23. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM 2017;60:84–90. https://doi.org/10.1145/3065386.
  24. Jupiyandi S, Saniputra FR, Pratama Y, Dharmawan MR, Cholissodin I. Pengembangan Deteksi Citra Mobil untuk Mengetahui Jumlah Tempat Parkir Menggunakan CUDA dan Modified YOLO. Jurnal Teknologi Informasi Dan Ilmu Komputer 2019;6:413. https://doi.org/10.25126/jtiik.2019641275.
  25. Sarosa M, Muna N. Implementasi Algoritma You Only Look Once (YOLO) untuk Deteksi Korban Bencana Alam. Jurnal Teknologi Informasi Dan Ilmu Komputer 2021;8:787–92. https://doi.org/10.25126/jtiik.2021844407.
  26. Redmon J, Farhadi A. YOLOv3: An Incremental Improvement. Computer Vision and Pattern Recognition 2018. http://arxiv.org/abs/1804.02767
  27. Liu J, Wang X, Zhu Q, Miao W. Tomato brown rot disease detection using improved YOLOv5 with attention mechanism. Front Plant Sci 2023;14. https://doi.org/10.3389/fpls.2023.1289464.
  28. Chen Z, Wu R, Lin Y, Li C, Chen S, Yuan Z, et al. Plant Disease Recognition Model Based on Improved YOLOv5. Agronomy 2022;12:365. https://doi.org/10.3390/agronomy12020365.
  29. Kumar VS, Jaganathan M, Viswanathan A, Umamaheswari M, Vignesh J. Rice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 model. Environ Res Commun 2023;5:065014. https://doi.org/10.1088/2515-7620/acdece.
  30. Li J, Qiao Y, Liu S, Zhang J, Yang Z, Wang M. An improved YOLOv5-based vegetable disease detection method. Comput Electron Agric 2022;202:107345. https://doi.org/10.1016/j.compag.2022.107345.
  31. Shurtleff MC, Pelczar MJ, Kelman A, Pelczar RM. Plant Disease. Britannica; 2023. https://www.britannica.com/science/plant-disease/Definitions-of-plant-disease
  32. Petruzzello M. Apple Scab. Britanica; 2024. https://www.britannica.com/science/apple-scab
  33. Utami GC, Widiawati CR, Subarkah P. Detection of Indonesian Food to Estimate Nutritional Information Using YOLOv5 Teknika 2023;12:158–165. https://doi.org/10.34148/teknika.v12i2.636.