Deteksi dan Klasifikasi Penyakit Daun Jeruk Menggunakan Model You Only Look Once
DOI:
https://doi.org/10.30872/1j3yfm81Keywords:
CCL'20, Daun Jeruk, Deteksi Penyakit, Deep Learning, YOLOAbstract
Identifikasi penyakit daun jeruk secara cepat diperlukan untuk mendukung pengendalian penyakit sebelum gejala berkembang lebih luas. Penelitian ini mengevaluasi YOLOv8n, YOLOv9t, YOLOv10n, dan YOLO11n pada dataset Citrus Common Leaf 2020 (CCL'20) yang terdiri atas 2.684 citra dan 10.332 anotasi. Tiga kelas penyakit, yaitu Anthracnose, Bacterial Brown Spot, dan Melanose, dievaluasi pada level objek, sedangkan 427 citra Healthy diperlakukan sebagai citra latar dan dianalisis bersama ketiga kelas penyakit pada level citra. Pengujian menggunakan tiga rasio pembagian data, yaitu 80:10:10, 70:15:15, dan 60:20:20. Pada skenario 80:10:10, YOLOv10n memperoleh mAP50-95 sebesar 0,9373 dan YOLOv9t sebesar 0,9368. Kedua nilai tersebut tergolong tinggi dan kompetitif dalam konteks benchmark CCL'20 karena melampaui YOLOv7 (0,9260), walaupun masih di bawah YOLOv8s teroptimasi (0,9610) pada studi lain; perbandingan ini bersifat kontekstual karena konfigurasi eksperimen berbeda. YOLOv9t menunjukkan rentang performa paling kecil pada tiga skenario, sedangkan YOLOv10n mencapai 151,7 FPS dengan waktu inferensi 6,59 ms per citra. Evaluasi level citra menghasilkan akurasi 85,13%, dengan seluruh citra Healthy teridentifikasi secara tepat. Hasil penelitian menunjukkan bahwa peningkatan generasi YOLO tidak selalu menghasilkan peningkatan akurasi yang konsisten, sehingga pemilihan model perlu mempertimbangkan akurasi, kestabilan, dan efisiensi komputasi secara bersamaan.
References
S. Dananjayan, Y. Tang, J. Zhuang, C. Hou, and S. Luo, "Assessment of state-of-the-art deep learning based citrus disease detection techniques using annotated optical leaf images," Comput. Electron. Agric., vol. 193, art. no. 106658, 2022. https://doi.org/10.1016/j.compag.2021.106658.
X. Qiu et al., "Detection of citrus diseases in complex backgrounds based on image-text multimodal fusion and knowledge assistance," Front. Plant Sci., vol. 14, art. no. 1280365, 2023. https://doi.org/10.3389/fpls.2023.1280365.
M. Shoaib et al., "An advanced deep learning models-based plant disease detection: A review of recent research," Front. Plant Sci., vol. 14, art. no. 1158933, 2023. https://doi.org/10.3389/fpls.2023.1158933.
I. Pacal et al., "A systematic review of deep learning techniques for plant diseases," Artif. Intell. Rev., vol. 57, art. no. 304, 2024. https://doi.org/10.1007/s10462-024-10944-7.
J. Li, Y. Qiao, S. Liu, J. Zhang, Z. Yang, and M. Wang, "An improved YOLOv5-based vegetable disease detection method," Comput. Electron. Agric., vol. 202, art. no. 107345, 2022. https://doi.org/10.1016/j.compag.2022.107345.
Y. Wang, Y. Wang, and J. Zhao, "MGA-YOLO: A lightweight one-stage network for apple leaf disease detection," Front. Plant Sci., vol. 13, art. no. 927424, 2022. https://doi.org/10.3389/fpls.2022.927424.
Z. Zhang, Y. Qiao, Y. Guo, and D. He, "Deep learning based automatic grape downy mildew detection," Front. Plant Sci., vol. 13, art. no. 872107, 2022. https://doi.org/10.3389/fpls.2022.872107.
Y. Peng and Y. Wang, "Leaf disease image retrieval with object detection and deep metric learning," Front. Plant Sci., vol. 13, art. no. 963302, 2022. https://doi.org/10.3389/fpls.2022.963302.
M. J. A. Soeb et al., "Tea leaf disease detection and identification based on YOLOv7 (YOLO-T)," Sci. Rep., vol. 13, art. no. 6078, 2023. https://doi.org/10.1038/s41598-023-33270-4.
S. Zhu, W. Ma, J. Wang, M. Yang, Y. Wang, and C. Wang, "EADD-YOLO: An efficient and accurate disease detector for apple leaf using improved lightweight YOLOv5," Front. Plant Sci., vol. 14, art. no. 1120724, 2023. https://doi.org/10.3389/fpls.2023.1120724.
W. Xu and R. Wang, "ALAD-YOLO: An lightweight and accurate detector for apple leaf diseases," Front. Plant Sci., vol. 14, art. no. 1204569, 2023. https://doi.org/10.3389/fpls.2023.1204569.
X. Wang and J. Liu, "Vegetable disease detection using an improved YOLOv8 algorithm in the greenhouse plant environment," Sci. Rep., vol. 14, art. no. 4261, 2024. https://doi.org/10.1038/s41598-024-54540-9.
Y. Wang, P. Zhang, and S. Tian, "Tomato leaf disease detection based on attention mechanism and multi-scale feature fusion," Front. Plant Sci., vol. 15, art. no. 1382802, 2024. https://doi.org/10.3389/fpls.2024.1382802.
T. Li, L. Zhang, and J. Lin, "Precision agriculture with YOLO-Leaf: Advanced methods for detecting apple leaf diseases," Front. Plant Sci., vol. 15, art. no. 1452502, 2024. https://doi.org/10.3389/fpls.2024.1452502.
J. Li et al., "Potato late blight leaf detection in complex environments," Sci. Rep., vol. 14, art. no. 31046, 2024. https://doi.org/10.1038/s41598-024-82272-3.
W. Feng, J. Liu, Z. Li, and S. Lyu, "YOLO-Citrus: A lightweight and efficient model for citrus leaf disease detection in complex agricultural environments," Front. Plant Sci., vol. 16, art. no. 1668036, 2025. https://doi.org/10.3389/fpls.2025.1668036.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," arXiv:2207.02696, 2022. https://arxiv.org/abs/2207.02696.
G. Jocher, A. Chaurasia, and J. Qiu, "Ultralytics YOLOv8," software, ver. 8.0.0, 2023. https://docs.ultralytics.com/models/yolov8/.
C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, "YOLOv9: Learning what you want to learn using programmable gradient information," arXiv:2402.13616, 2024. https://arxiv.org/abs/2402.13616.
A. Wang et al., "YOLOv10: Real-time end-to-end object detection," arXiv:2405.14458, 2024. https://arxiv.org/abs/2405.14458.
G. Jocher and J. Qiu, "Ultralytics YOLO11," software, ver. 11.0.0, 2024. https://docs.ultralytics.com/models/yolo11/.
U. Ali, M. A. Ismail, R. A. A. Habeeb, and S. R. A. Shah, "Performance evaluation of YOLO models in plant disease detection," J. Informatics Web Eng., vol. 3, no. 2, pp. 199-211, 2024. https://doi.org/10.33093/jiwe.2024.3.2.15.
B. Yang et al., "A novel plant type, leaf disease and severity identification framework using CNN and transformer with multi-label method," Sci. Rep., vol. 14, art. no. 11664, 2024. https://doi.org/10.1038/s41598-024-62452-x.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jurnal Rekayasa Teknologi Informasi (JURTI)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
