Improved Yolov5-Based Tomato Disease Detection Combined With Yolov8
DOI:
https://doi.org/10.29284/zndg8h10Keywords:
tomato disease detection; Roboflow; YOLOv5; YOLOv8; accuracy.Abstract
Targeting four major categories—healthy, blossom end rot, splitting rotation, as well as sun-scaled rotation—this study investigates the application of deep learning algorithms for precise tomato disease identification. Using a specially created tomato disease dataset, the study assesses the effectiveness of two light object identification algorithms, YOLOv5l and YOLOv8l. To establish a baseline for comparison, both models were first trained without data augmentation. Roboflow was used to apply a number of data augmentation techniques that effectively expanded and diversified the dataset in order to increase model generalization. These augmentations were designed to make the models more resilient to changes in lighting, plant orientation, and background conditions. After applying data augmentation, the models were retrained, and a thorough evaluation of their performance was conducted across all illness categories. The findings showed that both models' detection accuracy had significantly increased, confirming the importance of augmentation in enhancing model reliability. Overall, YOLOv8l consistently outperformed YOLOv5l by a small margin, especially when background images were excluded from the evaluation.
References
1. Y. Gulzar, "Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique," Sustainability, vol. 15, no. 3, Jan. 2023, Art. no. 1906, https://doi.org/10.3390/su15031906.
2. M. Afonso et al., "Tomato Fruit Detection and Counting in Greenhouses Using Deep Learning," Frontiers in Plant Science, vol. 11, Nov. 2020, https://doi.org/10.3389/fpls.2020.571299.
3. G. Moreira, S. A. Magalhães, T. Pinho, F. N. dos Santos, and M. Cunha, "Benchmark of Deep Learning and a Proposed HSV Colour Space Models for the Detection and Classification of Greenhouse Tomato," Agronomy, vol. 12, no. 2, Feb. 2022, Art. no. 356, https://doi.org/ 10.3390/agronomy12020356.
4. Y. Mu, T.-S. Chen, S. Ninomiya, and W. Guo, "Intact Detection of Highly Occluded Immature Tomatoes on Plants Using Deep Learning Techniques," Sensors, vol. 20, no. 10, Jan. 2020, Art. no. 2984, https://doi.org/10.3390/s20102984.
5. S. A. Magalhães et al., "Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse," Sensors, vol. 21, no. 10, Jan. 2021, Art. no. 3569, https://doi.org/10.3390/s21103569.
6. F. Zeng, Y. Liu, Y. Ye, J. Zhou, and X. Liu, "A detection method of Edge Coherent Mode based on improved SSD," Fusion Engineering and Design, vol. 179, Jun. 2022, Art. no. 113141, https://doi.org/10.1016/ j.fusengdes.2022.113141.
7. H. Peng et al., "General improved SSD model for picking object recognition of multiple fruits in natural environment.," Transactions of the Chinese Society of Agricultural Engineering, vol. 34, no. 16, pp. 155–162, 2018.
8. P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, "A Review of Yolo Algorithm Developments," Procedia Computer Science, vol. 199, pp. 1066–1073, Jan. 2022, https://doi.org/10.1016/j.procs.2022.01.135.
9. J. Wu, Z. Kuang, L. Wang, W. Zhang, and G. Wu, "Context-Aware RCNN: A Baseline for Action Detection in Videos," in Computer Vision – ECCV 2020, Glasgow, UK, 2020, pp. 440–456, https://doi.org/ 10.1007/978-3-030-58595-2_27.
10. G. Liu, J. C. Nouaze, P. L. Touko Mbouembe, and J. H. Kim, "YOLO-Tomato: A Robust Algorithm for Tomato Detection Based on YOLOv3," Sensors, vol. 20, no. 7, Jan. 2020, Art. no. 2145, https://doi.org/10.3390/s20072145.
11. B. Hu and J. Wang, "Detection of PCB Surface Defects With Improved Faster-RCNN and Feature Pyramid Network," IEEE Access, vol. 8, pp. 108335–108345, 2020, https://doi.org/10.1109/ACCESS.2020.3001349.
12. Y. Yang, J. Li, J. Nie, S. Yang, and J. Tang, "Cotton Stubble Detection Based on Improved YOLOv3," Agronomy, vol. 13, no. 5, May 2023, Art. no. 1271, https://doi.org/10.3390/agronomy13051271.
13. R. Gai, N. Chen, and H. Yuan, "A detection algorithm for cherry fruits based on the improved YOLO-v4 model," Neural Computing and Applications, vol. 35, no. 19, pp. 13895–13906, Jul. 2023, https://doi.org/10.1007/s00521-021-06029-z.
14. T. Saidani, R. Ghodhbani, A. Alhomoud, A. Alshammari, H. Zayani, and M. B. Ammar, "Hardware Acceleration for Object Detection using YOLOv5 Deep Learning Algorithm on Xilinx Zynq FPGA Platform," Engineering, Technology & Applied Science Research, vol. 14, no. 1,
15. pp. 13066–13071, Feb. 2024, https://doi.org/10.48084/etasr.6761.
16. R. Rajamohanan and B. C. Latha, "An Optimized YOLO v5 Model for Tomato Leaf Disease Classification with Field Dataset," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12033–12038, Dec. 2023, https://doi.org/10.48084/etasr.6377.
17. T. Saidani, "Deep Learning Approach: YOLOv5-based Custom Object Detection," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12158–12163, Dec. 2023, https://doi.org/10.48084/ etasr.6397.
18. J. Zhou, Y. Zhang, and J. Wang, "RDE-YOLOv7: An Improved Model Based on YOLOv7 for Better Performance in Detecting Dragon Fruits," Agronomy, vol. 13, no. 4, Apr. 2023, Art. no. 1042, https://doi.org/ 10.3390/agronomy13041042.
19. N. C. Eli-Chukwu, "Applications of Artificial Intelligence in Agriculture: A Review," Engineering, Technology & Applied Science Research, vol. 9, no. 4, pp. 4377–4383, Aug. 2019, https://doi.org/10.48084/etasr.2756.
20. A. Abbas, U. Maqsood, S. U. Rehman, K. Mahmood, T. AlSaedi, and
21. M. Kundi, "An Artificial Intelligence Framework for Disease Detection in Potato Plants," Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12628–12635, Feb. 2024, https://doi.org/10.48084/ etasr.6456.
22. S. Alqethami, B. Almtanni, W. Alzhrani, and M. Alghamdi, "Disease Detection in Apple Leaves Using Image Processing Techniques," Engineering, Technology & Applied Science Research, vol. 12, no. 2,
23. pp. 8335–8341, Apr. 2022, https://doi.org/10.48084/etasr.4721.
24. S. L. Sanga, D. Machuve, and K. Jomanga, "Mobile-based Deep Learning Models for Banana Disease Detection," Engineering, Technology & Applied Science Research, vol. 10, no. 3, pp. 5674–5677, Jun. 2020, https://doi.org/10.48084/etasr.3452.
25. L. Loyani and D. Machuve, "A Deep Learning-based Mobile Application for Segmenting Tuta Absoluta’s Damage on Tomato Plants," Engineering, Technology & Applied Science Research, vol. 11, no. 5, pp. 7730–7737, Oct. 2021, https://doi.org/10.48084/etasr.4355.
26. M. J. A. Soeb et al., "Tea leaf disease detection and identification based on YOLOv7 (YOLO-T)," Scientific Reports, vol. 13, no. 1, Apr. 2023, Art. no. 6078, https://doi.org/10.1038/s41598-023-33270-4.
27. G. Yang, J. Wang, Z. Nie, H. Yang, and S. Yu, "A Lightweight YOLOv8 Tomato Detection Algorithm Combining Feature Enhancement and Attention," Agronomy, vol. 13, no. 7, Jul. 2023, Art. no. 1824, https://doi.org/10.3390/agronomy13071824.
28. Q. H. Phan, V. T. Nguyen, C. H. Lien, T. P. Duong, M. T. K. Hou, and
29. N. B. Le, "Classification of Tomato Fruit Using Yolov5 and Convolutional Neural Network Models," Plants, vol. 12, no. 4, Jan. 2023, Art. no. 790, https://doi.org/10.3390/plants12040790.
30. "deseaseTomato Image Dataset." Feb. 17, 2024, [Online]. Available: https://universe.roboflow.com/datasetsnbu/deseasetomato/dataset/8.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
