Tomato (Solanum lycopersicum L.) leaf disease detection using computer vision
Detección de enfermedades en las hojas del tomate (Solanum lycopersicum L.) mediante visión por computadora
DOI:
https://doi.org/10.15446/rfnam.v78n3.116493Keywords:
Deep learning, Object detection, Plant pathology, PlantVillage dataset, Precision agriculture (en)Aprendizaje profundo, Detección de objetos, Fitopatología, PlantVillage dataset, Agricultura de precisión (es)
Tomato cultivation is a key component of global agriculture, but is significantly threatened by pests and diseases that impact yield and trade. To address this, the present study investigates the application of YOLOv9, a state-of-the-art object detection model, for automated disease detection in tomato leaves. Using a dataset of 4,323 images with 15,135 annotations and a modified PlantVillage dataset, YOLOv9 models were trained and evaluated. Among the evaluated models, YOLOv9e yielded the highest mean average precision (mAP) at 0.964, establishing a benchmark for accuracy. In contrast, the YOLOv9t model provided an optimal balance for practical applications, achieving a competitive mAP of 0.95 with a rapid inference time of 8.8 ms. Furthermore, this work contributes a public version of the PlantVillage dataset with bounding box annotations, providing a valuable resource for object detection research and extending the use of the original classification-focused dataset. The results indicate that YOLOv9 models are effective for real-time and accurate detection of various diseases in complex agricultural settings.
El cultivo de tomate es un componente clave de la agricultura mundial, pero se ve amenazado significativamente por plagas y enfermedades que impactan el rendimiento y el comercio. Para abordar esto, el presente estudio investiga la aplicación de YOLOv9, un modelo de detección de objetos de última generación, para la detección automatizada de enfermedades en las hojas de tomate. Utilizando un conjunto de datos de 4.323 imágenes con 15.135 anotaciones y un conjunto de datos PlantVillage modificado, se entrenaron y evaluaron los modelos YOLOv9. Entre los modelos evaluados, YOLOv9e arrojó la precisión media promedio (mAP) más alta con 0,964, estableciendo un punto de referencia para la exactitud. En contraste, el modelo YOLOv9t proporcionó un equilibrio óptimo para aplicaciones prácticas, logrando un mAP competitivo de 0,95 con un tiempo de inferencia rápido de 8,8 ms. Además, este trabajo aporta una versión pública del conjunto de datos PlantVillage con anotaciones de cuadros delimitadores, proporcionando un recurso valioso para la investigación en detección de objetos y extendiendo el uso del conjunto de datos original enfocado en la clasificación. Los resultados indican que los modelos YOLOv9 son eficaces para la detección precisa y en tiempo real de diversas enfermedades en entornos agrícolas complejos.
References
Abbas A, Jain S, Gour M and Vankudothu S (2021) Tomato plant disease detection using transfer learning with C-GAN synthetic images. Comput Electron Agric 187. https://doi.org/10.1016/j.compag.2021.106279
Chai AYH, Lee SH, Tay FS et al (2024) Beyond supervision: Harnessing self-supervised learning in unseen plant disease recognition. Neurocomputing 610:128608. https://doi.org/10.1016/j.neucom.2024.128608
Chairma Lakshmi KR, Praveena B, Sahaana G et al (2023) Yolo for Detecting Plant Diseases. In: Proceedings of the 3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023. Institute of Electrical and Electronics Engineers Inc., pp 1029–1034. DOI: https://doi.org/10.1109/ICAIS56108.2023.10073875
Durmus H, Gunes EO and Kirci M (2017) Disease detection on the leaves of the tomato plants by using deep learning. In: 2017 6th International Conference on Agro-Geoinformatics. IEEE, pp 1–5. DOI: https://doi.org/10.1109/Agro-Geoinformatics.2017.8047016
dyploma (2024) Tomato Leaf Diseases Dataset. Roboflow Universe.
FAO - Food and Agriculture Organization of the United Nations (2024) FAOSTAT. In: FAOSTAT. https://www.fao.org/faostat/en/#data/QCL
FAO - Food and Agriculture Organization of the United Nations (2021) World Food and Agriculture – Statistical Yearbook 2021. FAO, Rome.
Fuentes A, Yoon S, Kim S and Park D (2017) A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition. Sensors 17: 2022. https://doi.org/10.3390/s17092022
Geetharamani G and Arun Pandian J (2019) Identification of plant leaf diseases using a nine-layer deep convolutional neural network. Computers & Electrical Engineering Journal 76: 323–338. https://doi.org/10.1016/j.compeleceng.2019.04.011
IPPC Secretariat (2021) International year of plant health – Final report. FAO, Rome.
Jocher G, Munawar MR and Vina A (2024) YOLO Métricas de Rendimiento. YOLO Métricas de rendimiento - Ultralytics YOLOv8 Docs.
Liu J and Wang X (2020) Tomato Diseases and pests detection based on improved Yolo V3 Convolutional Neural Network. Front Plant Sci 11: 521544. https://doi.org/10.3389/fpls.2020.00898
Mahlein A-K (2016) Plant disease detection by imaging sensors – parallels and specific demands for precision agriculture and plant phenotyping. Plant Diseases 100: 241–251. https://doi.org/10.1094/PDIS-03-15-0340-FE
Mathew MP and Mahesh TY (2022) Leaf-based disease detection in bell pepper plant using YOLO v5. Signal Image Video Process 16: 841–847. https://doi.org/10.1007/s11760-021-02024-y
Mohanty SP, Hughes DP and Salathé M (2016) Using deep learning for image-based plant disease detection. Front Plant Sci 7. https://doi.org/10.3389/fpls.2016.01419
Nawaz M, Nazir T, Javed A et al (2022) A robust deep learning approach for tomato plant leaf disease localization and classification. Sci Rep 12. https://doi.org/10.1038/s41598-022-21498-5
Palacio S (2024a) Tomato leaf diseases dataset for object detection. https://www.kaggle.com/dsv/9270440
Palacio S (2024b) PlantVillage for object detection YOLO. https://www.kaggle.com/ds/5363572
Sajitha P, Diana Andrushia A, Anand N and Naser MZ (2024) A review on machine learning and deep learning image-based plant disease classification for industrial farming systems. J Ind Inf Integr 100572. https://doi.org/10.1016/j.jii.2024.100572
Singh A, Sreenivasu S, Mahalaxmi U et al (2022) Hybrid FeatureBased disease detection in plant leaf using convolutional neural network, bayesian optimized SVM, and random forest classifier. J Food Qual 2022: 16. https://doi.org/10.1155/2022/2845320
Tan L, Lu J and Jiang H (2021) Tomato leaf diseases classification based on leaf images: A comparison between classical machine learning and deep learning methods. AgriEngineering 3: 542–558. https://doi.org/10.3390/agriengineering3030035
Tang Z, He X, Zhou G et al (2023) A precise image-based tomato leaf disease detection approach using PLPNet. Plant Phenomics 5:0042. https://doi.org/10.34133/plantphenomics.0042
Wang CY, Yeh I-H and Liao HYM (2024) YOLOv9: Learning what you want to learn using programmable gradient information. DOI: https://doi.org/10.1007/978-3-031-72751-1_1
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2025 Revista Facultad Nacional de Agronomía Medellín

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The journal allows the author(s) to maintain the exploitation rights (copyright) of their articles without restrictions. The author(s) accept the distribution of their articles on the web and in paper support (25 copies per issue) under open access at local, regional, and international levels. The full paper will be included and disseminated through the Portal of Journals and Institutional Repository of the Universidad Nacional de Colombia, and in all the specialized databases that the journal considers pertinent for its indexation, to provide visibility and positioning to the article. All articles must comply with Colombian and international legislation, related to copyright.
Author Commitments
The author(s) undertake to assign the rights of printing and reprinting of the material published to the journal Revista Facultad Nacional de Agronomía Medellín. Any quotation of the articles published in the journal should be made given the respective credits to the journal and its content. In case content duplication of the journal or its partial or total publication in another language, there must be written permission of the Director.
Content Responsibility
The Faculty of Agricultural Sciences and the journal are not necessarily responsible or in solidarity with the concepts issued in the published articles, whose responsibility will be entirely the author or the authors.






