1. MMC
  2. All Volumes and Issues
  3. Volume 11, Number 4, 2024
  4. Advanced YOLO models for real-time detection of tomato leaf diseases

Advanced YOLO models for real-time detection of tomato leaf diseases

MMC.
2024;
Volume 11, Number 4
: pp. 1198–1210
https://doi.org/10.23939/mmc2024.04.1198
Received: May 01, 2024
Revised: December 03, 2024
Accepted: December 04, 2024

Bellout A., Zarboubi M., Dliou A., Latif R., Saddik A.  Advanced YOLO models for real-time detection of tomato leaf diseases.  Mathematical Modeling and Computing. Vol. 11, No. 4, pp. 1198–1210 (2024)

Authors:
  1. A. Bellout
  2. M. Zarboubi
  3. A. Dliou
  4. R. Latif
  5. A. Saddik
1
LISTI, National School of Applied Sciences, Ibn Zohr University, Agadir, Morocco
2
LISAD, National School of Applied Sciences, Ibn Zohr University, Agadir, Morocco
3
LISTI, National School of Applied Sciences, Ibn Zohr University, Agadir, Morocco; IMIS, Faculty of Applied Sciences, Ibn Zohr University, Agadir, Morocco
4
LISTI, National School of Applied Sciences, Ibn Zohr University, Agadir, Morocco
5
LISTI, National School of Applied Sciences, Ibn Zohr University, Agadir, Morocco; IMIS, Faculty of Applied Sciences, Ibn Zohr University, Agadir, Morocco

The increasing focus on smart agriculture in the last decade can be attributed to various factors, including the adverse effects of climate change, frequent extreme weather events, increasing population, the necessity for food security, and the scarcity of natural resources.  The government of Morocco adopts preventative measures to combat plant illnesses, specifically focusing on tomatoes.  Tomatoes are widely acknowledged as one of the most important vegetable crops, but they are highly vulnerable to several diseases that significantly decrease their productivity.  Deep learning algorithms are increasingly being used to identify tomato leaf diseases.  In this study, we thoroughly examine different deep learning methodologies, with a specific emphasis on Convolutional Neural Network (CNN) models. Our study aims at identifying the optimal approach for detecting diseases that impact tomato leaves by combining two publicly accessible datasets, PlantDoc and PlantVillage.  We focused on finding a strategy that is effective and efficient in accurately identifying these diseases.  This study investigates the feasibility of employing state-of-the-art deep learning methods that are based on YOLO models.  We have chosen five models, specifically YOLOv5, YOLOX, YOLOv7, YOLOv8, and YOLO-NAS, which belong to the category of "One-stage detectors."  These models are widely recognized for their rapid inference speed and outstanding accuracy.  According to the experimental results, YOLOv5 has the highest level of accuracy, reaching a mean average precision (mAP) of 93.1% after adjusting the hyperparameters.  The final model is developed as a smartphone application to improve user-friendliness.

precision agriculture
tomato plant disease
deep learning
computer vision
object detection
Yolo
  1. Lin G., Tang Y., Zou X., Xiong J., Fang Y.  Color-, depth-, and shape-based 3D fruit detection.  Precision Agriculture.  21 (1), 1–17 (2020).
  2. Buja I., Sabella E., Monteduro A. G., ChiriacГІ M. S., De Bellis L., Luvisi A., Maruccio G.  Advances in Plant Disease Detection and Monitoring: From Traditional Assays to In-Field Diagnostics.  Sensors.  21 (6), 2129 (2021).
  3. Wang C., Tang Y., Zou X., Luo L., Chen X.  Recognition and Matching of Clustered Mature Litchi Fruits Using Binocular Charge-Coupled Device (CCD) Color Cameras.  Sensors.  17 (11), 2564 (2017).
  4. Li J., Tang Y., Zou X., Lin G., Wang H.  Detection of Fruit-Bearing Branches and Localization of Litchi Clusters for Vision-Based Harvesting Robots.  IEEE Access.  8, 117746–117758 (2020).
  5. Gui J., Fei J., Wu Z., Fu X., Diakite A.  Grading method of soybean mosaic disease based on hyperspectral imaging technology.  Information Processing in Agriculture.  8 (3), 380–385 (2021).
  6. Appeltans S., Pieters J. G., Mouazen A. M.  Detection of leek white tip disease under field conditions using hyperspectral proximal sensing and supervised machine learning.  Computers and Electronics in Agriculture.  190, 106453 (2021).
  7. Phadikar S., Sil J., Das A. K.  Rice diseases classification using feature selection and rule generation techniques.  Computers and Electronics in Agriculture.  90, 76–85 (2013).
  8. Singh S., Gupta S., Tanta A., Gupta R.  Extraction of Multiple Diseases in Apple Leaf Using Machine Learning.  International Journal of Image and Graphics.  22 (03), 2140009 (2022).
  9. Almadhor A., Rauf H. T., Lali M. I. U., Damaševičius R., Alouffi B., Alharbi A.  AI-Driven Framework for Recognition of Guava Plant Diseases through Machine Learning from DSLR Camera Sensor Based High Resolution Imagery.  Sensors.  21 (11), 3830 (2021).
  10. Bellout A., Dliou A., Latif R., Saddik A.  Deep Learning technique for predicting tomato leaf disease.  2023 IEEE International Conference on Advances in Data-Driven Analytics and Intelligent Systems (ADACIS). 1–6 (2023).
  11. Zarboubi M., Chabaa S., Dliou A.  Advancing Precision Agriculture with Deep Learning and IoT Integration for Effective Tomato Pest Management.  2023 IEEE International Conference on Advances in Data-Driven Analytics And Intelligent Systems (ADACIS). 1–6 (2023).
  12. Fujita E., Kawasaki Y., Uga H., Kagiwada S., Iyatomi H.  Basic Investigation on a Robust and Practical Plant Diagnostic System.  2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).  989–992 (2016).
  13. Brahimi M., Boukhalfa K., Moussaoui A.  Deep Learning for Tomato Diseases: Classification and Symptoms Visualization.  Applied Artificial Intelligence.  31 (4), 299–315 (2017).
  14. Rangarajan A. K., Purushothaman R., Ramesh A.  Tomato crop disease classification using pre-trained deep learning algorithm.  Procedia Computer Science.  133, 1040–1047 (2018).
  15. Wang Q., Qi F., Sun M., Qu J., Xue J.  Identification of Tomato Disease Types and Detection of Infected Areas Based on Deep Convolutional Neural Networks and Object Detection Techniques.  Computational Intelligence and Neuroscience.  2019, 9142753 (2019).
  16. Terven J., Cordova-Esparza D.  A Comprehensive Review of YOLO: From YOLOv1 and Beyond.  Preprint ArXiv:2304.00501 (2023).
  17. Huang Y., Kruyer A., Syed S., Kayasandik C. B., Papadakis M., Labate D.  Automated detection of GFAP-labeled astrocytes in micrographs using YOLOv5.  Scientific Reports.  12 (1), 22263 (2022).
  18. Ge Z., Liu S., Wang F., Li Z., Sun J.  YOLOX: Exceeding YOLO Series in 2021.  Preprint ArXiv:2107.08430 (2021).
  19. Peng H., Tan X.  Improved YOLOX's Anchor-Free SAR Image Ship Target Detection.  IEEE Access.  10, 7001–70015 (2022).
  20. Wang C. Y., Bochkovskiy A., Liao H. Y. M.  YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors.  Preprint ArXiv:2207.02696 (2022).
  21. Jocher G., Chaurasia A., Qiu J.  YOLO by Ultralytics. https://github.com/ultralytics/ultralytics  Version 8.0.0; AGPL-3.0 (January 2023).
  22. Research Team.  YOLO-NAS by Deci Achieves State-of-the-Art Performance on Object Detection Using Neural Architecture Search. 2023. https://deci.ai/blog/yolo-nas-object-detection-foundation-model/  (accessed on 12 May 2023).