ROI – Enhancing Detection of Citrus Disease Based on YOLOv10
Main Article Content
Abstract
One of the most important fruit crops in the world is citrus. However, some citrus diseases spread rapidly, which is why early detection at an accurate stage is important for timely intervention. YOLO-based object detection models, such as the latest YOLOv10, where small lesions are difficult to identify among noisy backgrounds, have recently been developed, yet their accuracy tends to degrade. Therefore, we proposed a citrus disease detection model by integrating the region of interest (ROI) for object segmentation with the YOLOv10 model, thus addressing the issues of low detection accuracy and slow inference time. The proposed model was trained on an annotated dataset of three major citrus pathologies: anthracnose, citrus canker, and leaf miner infestation. Results showed significant improvements in the performance of our proposed model, which incorporates the ROI mechanism into YOLOv10. Specifically, the ROI-YOLOv10 model achieved high mAP scores, reaching 0.99 and 0.985 during training and validation, respectively, and maintaining high generalization capabilities with a test mAP of 0.984. Precision and recall metrics similarly underline the enhanced accuracy and robustness of ROI-YOLOv10. Compared with previous YOLO-based studies, our model exhibits enhanced accuracy and faster inference times. The incorporation of ROI techniques into the YOLOv10 framework is a highly effective approach for improving agricultural productivity by facilitating early and precise detection of plant disease.
Article Details
Issue
Section

This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
[1] X. Wu, F. Feng, and H. Zhang, “A Huanglongbing Detection Method for Orange Trees Based on Deep Neural Networks and Transfer Learning,” Sensors, vol. 24, no. 14, p. 4448, 2024.
[2] A. Moussaid, S. E. Fkihi, and Y. Zennayi, “Citrus yield prediction using deep learning techniques: A combination of field and satellite data,” J. Open Innov. Technol. Mark. Complex., vol. 9, p. 100075, 2023.
[3] A. A. A. A. El-Mahdy, M. A. El-Azab, and M. A. El-Bakry, “A Systematic Review of Citrus Disease Perceptions and Fruit Grading Using Machine Vision,” Procedia Computer Science, vol. 216, pp. 1174–1183, 2023.
[4] W. Zhang, J. Wang, Y. Liu, K. Chen, H. Li, Y. Duan, W. Wu, Y. Shi, and W. Guo, “Deep learning based in field citrus fruit detection and tracking,” Horticulture Research, vol. 9, Feb. 11 2022, doi: 10.1093/hr/uhac003.
[5] X. Wu, F. Feng, and H. Zhang, “Citrus Yellow Shoot Disease Detection based on YOLOv5,” Journal of Horticultural Science & Biotechnology, vol. 98, no. 3, pp. 1–10, 2023.
[6] A. Wang, H. Chen, L. Liu, K. Chen, Z. Lin, J. Han, and G. Ding, “YOLOv10: Real-Time End-to-End Object Detection,” , May 2024.
[7] Y. Wu, X. Xiong, G. Pan, Z. Zhang, and Z. Wang, "Citrus Disease Detection Using a Convolutional Neural Network with PCA Selected Hyperspectral Bands," Computers and Electronics in Agriculture, vol. 182, p. 106006, Apr. 2023.
[8] N. Butt, M. M. Iqbal, I. Ahmad, H. Akbar, and U. Khadam, “Citrus Diseases Detection using Deep Learning,” Journal of Computing & Biomedical Informatics, vol. 6, no. 2, pp. 23–33, Mar. 2024.
[9] Z. Naureen, H. Afzal, T. Al Shehari, M. Al Razgan, N. Iltaf, M. Zakria, M. J. Hyder, and R. Nawaz, “Detection and Classification of Temporal Changes for Citrus Canker Growth Rate Using Deep Learning,” IEEE Access, vol. 11, pp. 127637–127650, Nov. 9, 2023, doi: 10.1109/ACCESS.2023.3331735.
[10] U. Ali, M. A. I. 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, Jun. 2024, doi: 10.33093/jiwe.2024.3.2.15.
[11] P. K. Yadav, T. Burks, Q. Frederick, J. Qin, M. Kim, and T. Burks, “Citrus disease detection using convolution neural network generated features and softmax classifier on hyperspectral image data,” Frontiers in Plant Science, vol. 13, article 1043712, pp. 1–25, 2022, doi: 10.3389/fpls.2022.1043712.
[12] A. Wang, H. Chen, L. Liu, K. Chen, Z. Lin, J. Han, and G. Ding, “YOLOv10: Real-Time End-to-End Object Detection,” May 2024.
[13] H. Mo and L. Wei, “Lightweight citrus leaf disease detection model based on ARMS and cross-domain dynamic attention,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 7, p. 102133, 2024.
[14] P. W. Chin, K. W. Ng, and N. Palanichamy, “Plant disease detection and classification using deep learning methods: a comparison study,” Journal of Informatics and Web Engineering, vol. 3, no. 1, pp. 155–168, 2024, doi: 10.33093/jiwe.2024.3.1.10
[15] Y. Jamtsho, P. Riyamongkol, and R. Waranusast, “Real-time license plate detection for non-helmeted motorcyclist using YOLO,” ICT Express, vol. 7, no. 1, pp. 104–109, Mar. 2021, doi: 10.1016/j.icte.2020.06.002.
[16] X. Zhang , Y. Xun , and Y. Chen, “Automated identification of citrus diseases in orchards using deep learning,” Computers and Electronics in Agriculture, vol. 190, p. 106418, 2022.
[17 ] U. Ali, M. A. Ismail, R. A. Ariyaluran Habeeb, and S. R. Ali Shah, “Performance evaluation of YOLO models in plant disease detection,” Journal of Informatics and Web Engineering, vol. 3, no. 2, pp. 1–10, 2024.
[18] X. Wu, F. Feng, and H. Zhang, “LSD-YOLO: Enhanced YOLOv8n Algorithm for Efficient Detection of Lemon Surface Diseases,” Plants, vol. 13, no. 15, p. 2069, 2024.
[19] X. Wu, F. Feng, and H. Zhang, “A Detection Algorithm for Citrus Huanglongbing Disease Based on an Improved YOLOv8n,” Sensors, vol. 24, no. 14, p. 4448, 2024.
[20] W. Chen, S. Lu, B. Liu, M. Chen, G. Li, and T. Qian, “CitrusYOLO: An algorithm for citrus detection under orchard environment based on YOLOv4,” Multimedia Tools and Applications, vol. 81, no. 22, pp. 31 363–31 389, 2022, doi: 10.1007/s11042-022-12687-5.
[21] X. WU, J. Liany, Y. Yang, Z. Li, X. Jia, H. Pu and P. Zhu, “SAW-YOLO: A Multi-Scale YOLO for Small Target Citrus Pests Detection” MDPI journals, vol. 14, Issue 7, 19 July 2024.
[22] X. Jiang, Y. Li, and Q. Zhao, “Deep learning-based detection of plant diseases: A survey,” Computers and Electronics in Agriculture, vol. 189, p. 106383, 2022.
[23] C. Ding and G. Taylor, “Automatic detection of plant diseases using deep learning,” Computers and Electronics in Agriculture, vol. 128, pp. 1–8, 2016.
[24] S. Ghosal, A. Blystone, and A. Singh, “An explainable deep learning framework for plant stress phenotyping,” Plant Methods, vol. 17, no. 1, p. 1, 2021.
[25] M. Shoaib, A. Sadeghi-Niaraki, F. Ali, I. Hussain, and S. Khalid, “Leveraging deep learning for plant disease and pest detection: a comprehensive review and future directions,” Frontiers in Plant Science, vol. 16, Art. no. 1538163, Feb. 2025, doi: 10.3389/fpls.2025.1538163.
[26] W. Gómez-Flores, J. J. Garza-Saldaña, and S. E. Varela-Fuentes, “CitrusUAT: A dataset of orange Citrus sinensis leaves for abnormality detection using image analysis techniques,” Data in Brief, vol. 52, p. 109908, Dec. 2023, doi: 10.1016/j.dib.2023.109908.
[27] Y. Tang, J. Yang, J. Zhuang, C. Hou, A. Miao, J. Ren, H. Huang, Z. Tan, and J. Paliwal, “Early detection of citrus anthracnose caused by Colletotrichum gloeosporioides using hyperspectral imaging,” Computers and Electronics in Agriculture, vol. 214, Art. no. 108348, 2023, doi: 10.1016/j.compag.2023.108348.
[28] M. Bagga and S. Goyal, “A comparative study of the deep learning based image segmentation techniques for fruit disease detection,” Reviews in Agricultural Science, vol. 13, no. 1, pp. 81–104, Mar. 2025, doi: 10.7831/ras.13.1_81.
[29] G.-Y. Moon and J.-O. Kim, “RoI-Attention Network for Small Disease Segmentation in Crop Images,” IEEE Access, vol. 12, pp. 63725–63735, May 2024, doi: 10.1109/ACCESS.2024.339330.
[30] M. A. R. Alif and M. Hussain, "YOLOv1 to YOLOv10: A Comprehensive Review of YOLO Variants and Their Application in the Agricultural Domain," Jun. 2024.
[31] T. Diwan, G. Anirudh, and J. V. Tembhurne, "Object Detection Using YOLO: Challenges, Architectural Successors, Datasets and Applications," Multimedia Tools and Applications, vol. 82, pp. 9243–9275, 2023.
[32] S. A. Preanto, M. T. Ahad, Y. R. Emon, S. Mustofa, and M. Alamin, "A Semantic Segmentation Approach on Sweet Orange Leaf Diseases Detection Utilizing YOLO," pp:2409.06671, Sep. 2024.
[33] R. Sapkota, Z. Meng, M. Churuvija, X. Du, Z. Ma, and M. Karkee, "Comprehensive Performance Evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments," , Jul. 2024. vol. 209, p. 107850, 2023.
[34] M. Hussain, “YOLOv5, YOLOv8 and YOLOv10: The Go To Detectors for Real time Vision,” Jul. 3, 2024.
[35] H. Luo, “Citrus Leaf Disease Dataset (Version v1),” Zenodo, May 8, 2024. https://doi.org/10.5281/zenodo.11148332
[36] E. Moupojou, F. Retraint, H. Tapamo, M. Nkenlifack, C. Kacfah, and A. Tagne, “Segment Anything Model and Fully Convolutional Data Description for Plant Multi-Disease Detection on Field Images,” IEEE Access, vol. 12, pp. 102592–102605, Aug. 2024, doi: 10.1109/ACCESS.2024.343349
[37] I. Haider, M. A. Khan, M. Nazir, T. Kim, and J.-H. Cha, “An artificial intelligence-based framework for fruits disease recognition using deep learning,” Computer Systems Science and Engineering, vol. 48, no. 2, pp. 529–554, Mar. 2024, doi: 10.32604/csse.2023.042080
[38] M. Padilla, S. L. Netto, and E. A. B. da Silva, “A survey on performance metrics for object-detection algorithms,” Proceedings of the International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 237–242, 2020.