TOMATO DISEASES CLASSIFICATION BASED ON LEAF IMAGES  USING MOBILENET V2

Nguyễn Thị Thanh Nhàn

doi:10.34238/tnu-jst.12722

TOMATO DISEASES CLASSIFICATION BASED ON LEAF IMAGES USING MOBILENET V2

About this article

Received: 05/05/25 Revised: 26/06/25 Published: 28/06/25

Authors

Nguyen Thi Thanh Nhan , TNU - University of Information and Communication Technology

Abstract

Tomato is one of the most valuable and widely consumed vegetable crops in the world. Tomato plants are frequently attacked by various pathogens, leading to reduced yield and fruit quality. Therefore, early detection of leaf disease symptoms in the early stages will help farmers promptly apply preventive measures, limit the spread and minimize agricultural losses. This paper proposes the application of a lightweight deep learning architecture, MobileNet V2, for the classification of tomato leaf diseases. The model is trained using transfer learning, with several configurations of hyperparameters, data splitting strategies, and data balancing techniques. The program is designed to classify ten categories: nine classes corresponding to different tomato leaf diseases and one class representing healthy plants, using images from the PlantVillage dataset. The results show that MobileNet V2 can classify diseases with the best accuracy of 95.73%, opening up the direction of deploying an automatic tomato disease monitoring system on mobile devices with fast inference speed and low computational cost.

Keywords

MobileNet V2; Convolutional neural network; Tomato leaf disease; Fine tuning; Plant disease identification

Full Text:

PDF (Tiếng Việt)

References

[1] S. Z. M. Zaki, M. A. Zulkifley, M. M. Stofa, N. A. M. Kamari, and N. A. Mohamed, “Classification of tomato leaf diseases using MobileNet v2,” IJ-AI, vol. 9, no. 2, pp. 290-296, Jun. 2020, doi: 10.11591/ijai.v9.i2.pp290-296.

[2] J. Yao, S. N. Tran, S. Garg, and S. Sawyer, “Deep Learning for Plant Identification and Disease Classification from Leaf Images: Multi-prediction Approaches,” arXiv: arXiv:2310.16273, Oct. 25, 2023, doi: 10.48550/arXiv.2310.16273.

[3] L. Li, S. Zhang, and B. Wang, “Plant Disease Detection and Classification by Deep Learning—A Review,” IEEE Access, vol. 9, pp. 56683–56698, 2021, doi: 10.1109/ACCESS.2021.3069646.

[4] C. Szegedy et al., “Going deeper with convolutions,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA: IEEE, Jun. 2015, pp. 1–9, doi: 10.1109/CVPR.2015.7298594.

[5] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA: IEEE, Jun. 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.

[6] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, May 2017, doi: 10.1145/3065386.

[7] A. Batool, S. B. Hyder, A. Rahim, N. Waheed, M. A. Asghar, and Fawad, “Classification and Identification of Tomato Leaf Disease Using Deep Neural Network,” in 2020 International Conference on Engineering and Emerging Technologies (ICEET), Lahore, Pakistan: IEEE, Feb. 2020, pp. 1–6, doi: 10.1109/ICEET48479.2020.9048207.

[8] M. Agarwal, A. Singh, S. Arjaria, A. Sinha, and S. Gupta, “ToLeD: Tomato Leaf Disease Detection using Convolution Neural Network,” Procedia Computer Science, vol. 167, pp. 293–301, 2020, doi: 10.1016/j.procs.2020.03.225.

[9] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT: IEEE, Jun. 2018, pp. 4510–4520, doi: 10.1109/CVPR.2018.00474.

[10] A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” arXiv: arXiv:1704.04861, Apr. 17, 2017, doi: 10.48550/arXiv.1704.04861.

[11] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Front. Plant Sci., vol. 7, pp.1-10, Sep. 2016, doi: 10.3389/fpls.2016.01419.

DOI: https://doi.org/10.34238/tnu-jst.12722

Refbacks

There are currently no refbacks.



Remember me