Skip to main content
Log in

Potato Leaf Disease Classification Using Transfer Learning and Reweighting-Based Training with Imbalanced Data

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Potatoes are an essential global staple, but their susceptibility to various diseases poses a major threat to agricultural productivity. Thus, it is imperative to detect these diseases in good time to implement effective management strategies. In this study, we propose a reliable approach for the early detection of potato leaf diseases, which is based on transfer learning using the MobileNetV2 pre-trained model as a basis. In fact, by fine-tuning MobileNetV2’s architecture, we are adapting it to the specific task of classifying potato leaf diseases. This process has been closely monitored using eXplainable AI (XAI), which facilitated the identification of significant regions within the potato leaf images essential for accurate classification. Moreover, to mitigate potential overfitting without compromising performance, rigorous model training protocols are implemented, emphasizing convergence criteria that maximize predictive accuracy. Addressing the challenge of imbalanced dataset distributions inherent in disease classification tasks, we implement data augmentation techniques to enhance model generalization capabilities. Additionally, we propose a reweighting-based technique to account for class imbalance, thereby ensuring equitable representation across disease categories. The evaluation of the proposed approach on the PlantVillage dataset, a widely accepted reference in the field, showed a notable classification accuracy of 98.61%, underlining its effectiveness in disease identification. Furthermore, comprehensive analysis of recall, precision, and F1-score metrics reveals consistent performance across disease classes, indicative of the model’s robustness and reliability. This research enhances the current techniques for identifying potato diseases, benefiting the overall agricultural sustainability and protection of crops. Indeed, promising advancements in disease management could protect potato crops globally and guarantee food security for people worldwide.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Data Availibility

For all the data described in this paper, we have provided references to the original dataset sources. Please note that the availability of these datasets may be subject to certain restrictions or usage terms imposed by the original data providers.

References

  1. Agarwal M, Gupta SK, Biswas KK (2019) Grape disease identification using convolution neural network. In: 2019 23rd International Computer Science and Engineering Conference (ICSEC), IEEE, 224–229

  2. Agarwal M, Singh A, Arjaria S, et al. Toled: Tomato leaf disease detection using convolution neural network. Proc Comput Sci. 2020;167:293–301.

    Article  Google Scholar 

  3. Ahmad M, Abdullah M, Moon H, et al. Plant disease detection in imbalanced datasets using efficient convolutional neural networks with stepwise transfer learning. IEEE Access. 2021;9:140565–80.

    Article  Google Scholar 

  4. Ahmed I, Yadav PK. A systematic analysis of machine learning and deep learning based approaches for identifying and diagnosing plant diseases. Sustain Oper Comput. 2023;4:96–104.

    Article  Google Scholar 

  5. Alberto LR, Ardila CEC, Ortiz FAP. A computer vision system for early detection of anthracnose in sugar mango (mangifera indica) based on uv-a illumination. Inform Process Agricult. 2023;10(2):204–15.

    Article  Google Scholar 

  6. Barman U, Sahu D, Barman GG, et al. (2020) Comparative assessment of deep learning to detect the leaf diseases of potato based on data augmentation. In: 2020 International Conference on Computational Performance Evaluation (ComPE), IEEE, 682–687

  7. Chen J, Zhang D, Suzauddola M, et al. Identification of plant disease images via a squeeze-and-excitation mobilenet model and twice transfer learning. IET Image Process. 2021;15(5):1115–27.

    Article  Google Scholar 

  8. Chen J, Deng X, Wen Y, et al. Weakly-supervised learning method for the recognition of potato leaf diseases. Artificial Intell Rev. 2023;56(8):7985–8002.

    Article  Google Scholar 

  9. Datta S, Gupta N. A novel approach for the detection of tea leaf disease using deep neural network. Proc Comput Sci. 2023;218:2273–86.

    Article  Google Scholar 

  10. Dhaware CG, Wanjale K (2017) A modern approach for plant leaf disease classification which depends on leaf image processing. In: 2017 International Conference on Computer Communication and Informatics (ICCCI), IEEE, 1–4

  11. Elaoud A, Barhoumi W, Zagrouba E (2023) Multi-view-based apple maturity classification using similarity network fusion versus classical machine learning classifiers. In: 2023 IEEE International Conference on Fuzzy Systems (FUZZ), IEEE, 1–6

  12. Ganatra N, Patel A. A multiclass plant leaf disease detection using image processing and machine learning techniques. Int J Emerging Technol. 2020;11(2):1082–6.

    Google Scholar 

  13. Gayathri S, Wise DJW, Shamini PB, et al. (2020) Image analysis and detection of tea leaf disease using deep learning. In: 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), IEEE, 398–403

  14. Ghazouani H, Barhoumi W, Chakroun E, et al. Dealing with unbalanced data in leaf disease detection: a comparative study of hierarchical classification, clustering-based undersampling and reweighting-based approaches. Proc Comput Sci. 2023;225:4891–900.

    Article  Google Scholar 

  15. Hazell P, Wood S. Drivers of change in global agriculture. Philosophical Trans R Soc B. 2008;363(1491):495–515.

    Article  Google Scholar 

  16. Hossain E, Hossain MF, Rahaman MA. A color and texture based approach for the detection and classification of plant leaf disease using knn classifier. In: 2019 International Conference on Electrical. IEEE: Computer and Communication Engineering (ECCE); 2019. p. 1–6.

    Google Scholar 

  17. Hughes D, Salathé M, et al. (2015) An open access repository of images on plant health to enable the development of mobile disease diagnostics. arXiv preprint arXiv:1511.08060

  18. Kang H, Wang X, Chen C. Accurate fruit localisation using high resolution lidar-camera fusion and instance segmentation. Comput Electron Agricult. 2022;203: 107450.

    Article  Google Scholar 

  19. Kumar A, Patel VK (2023) Classification and identification of disease in potato leaf using hierarchical based deep learning convolutional neural network. Multimedia Tools and Applications 1–27

  20. Liu X, Min W, Mei S, et al. Plant disease recognition: a large-scale benchmark dataset and a visual region and loss reweighting approach. IEEE Trans Image Process. 2021;30:2003–15.

    Article  Google Scholar 

  21. Mahum R, Munir H, Mughal ZUN, et al. A novel framework for potato leaf disease detection using an efficient deep learning model. Hum Ecol Risk Assessment. 2023;29(2):303–26.

    Article  Google Scholar 

  22. Mathew A, Antony A, Mahadeshwar Y, et al. Plant disease detection using glcm feature extractor and voting classification approach. Mater Today. 2022;58:407–15.

    Google Scholar 

  23. Naik BN, Malmathanraj R, Palanisamy P. Detection and classification of chilli leaf disease using a squeeze-and-excitation-based cnn model. Ecol Inform. 2022;69: 101663.

    Article  Google Scholar 

  24. Nanehkaran Y, Zhang D, Chen J, et al. (2020) Recognition of plant leaf diseases based on computer vision. Journal of Ambient Intelligence and Humanized Computing 1–18

  25. Ojo MO, Zahid A. Improving deep learning classifiers performance via preprocessing and class imbalance approaches in a plant disease detection pipeline. Agronomy. 2023;13(3):887.

    Article  Google Scholar 

  26. Pooja V, Das R, Kanchana V (2017) Identification of plant leaf diseases using image processing techniques. In: 2017 IEEE Technological Innovations in ICT for Agriculture and Rural Development (TIAR), IEEE, 130–133

  27. Sanida T, Sideris A, Sanida MV, et al. Tomato leaf disease identification via two-stage transfer learning approach. Smart Agricult Technol. 2023;5: 100275.

    Article  Google Scholar 

  28. Singh A, Kaur H (2021) Potato plant leaves disease detection and classification using machine learning methodologies. In: IOP Conference Series: Materials Science and Engineering, IOP Publishing, 012121

  29. Thakur PS, Khanna P, Sheorey T, et al. (2022) Explainable vision transformer enabled convolutional neural network for plant disease identification: Plantxvit. arXiv preprint arXiv:2207.07919

  30. Thakur PS, Chaturvedi S, Khanna P, et al. Vision transformer meets convolutional neural network for plant disease classification. Ecol Inform. 2023;77: 102245.

    Article  Google Scholar 

  31. Tiwari D, Ashish M, Gangwar N, et al. (2020) Potato leaf diseases detection using deep learning. In: 2020 4th international conference on intelligent computing and control systems (ICICCS), IEEE, 461–466

  32. Vyas S, Mukhija MK, Alaria SK (2023) An efficient approach for plant leaf species identification based on svm and smo and performance improvement. In: Intelligent Systems and Applications: Select Proceedings of ICISA 2022. Springer, 3–15

  33. Yogeshwari M, Thailambal G. Automatic feature extraction and detection of plant leaf disease using glcm features and convolutional neural networks. Materials Today: Proceedings. 2023;81:530–6. https://doi.org/10.1016/j.matpr.2021.03.700, international Virtual Conference on Sustainable Materials (IVCSM-2k20).

Download references

Funding

This research did not receive any funding.

Author information

Authors and Affiliations

Authors

Contributions

All authors contributed equally to all aspects of this work.

Corresponding author

Correspondence to Amani Elaoud.

Ethics declarations

Conflict of Interest

All authors declare that they have no Conflict of interest.

Research Involving Human and/or Animals

Not Applicable.

Informed Consent

Not Applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jlassi, A., Elaoud, A., Ghazouani, H. et al. Potato Leaf Disease Classification Using Transfer Learning and Reweighting-Based Training with Imbalanced Data. SN COMPUT. SCI. 5, 987 (2024). https://doi.org/10.1007/s42979-024-03334-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-024-03334-x

Keywords

Navigation