Sigatoka and xanthomonas Banana leaf disease detection via transfer learning

Genet, Yordanos Hailu; Sinshaw, Natnael Tilahun; Assefa, Beakal Gizachew; Mohapatra, Sudhir Kumar

doi:10.24200/sci.2024.62306.7766

Sigatoka and xanthomonas Banana leaf disease detection via transfer learning

Document Type : Article

Authors

¹ Department of Software Engineering, CoE for HPC and BDA, AASTU, Addis Ababa, Ethiopia

² School of Information Technology and Engineering, AAiT, Addis Ababa, Ethiopia

³ Faculty of Emerging Technologies, Sri Sri University, Cuttack, Odisha, India

10.24200/sci.2024.62306.7766

Abstract

Plant diseases are a signi cant concern in agriculture, contributing to as much as 16% of global agricultural losses. This poses serious threats to food security, especially for crops like bananas, which are highly vulnerable to diseases such as Xanthomonas Wilt and Sigatoka leaf spot. These diseases have the potential to cause complete yield losses, reaching up to 100%. Addressing these challenges is crucial, and this study aims to do so by developing a robust disease detection model. Leveraging Convolutional Neural Network (CNN) algorithms, we have created a sophisticated system capable of accurately identifying and categorizing diseases in banana plants. To train our model e ectively, we have gathered a meticulously curated dataset of banana plant leaf images from regions heavily a ected by these diseases. This dataset has been carefully categorized into three groups: Healthy, Xanthomonas Wilt infected, and Sigatoka leaf spot infected. Employing advanced techniques such as data augmentation and transfer learning, we have netuned our model using various architectures including MobileNet, EcientNet, VGG16, VGG19, and InceptionV3. Our research ndings highlight the exceptional performance of the VGG16 model, achieving an impressive classi cation accuracy of 81.53% during rigorous
testing with independent datasets. Looking to the future, we recognize the need for further improvements in model performance. This includes acquiring a more diverse and expansive dataset and implementing automatic hyperparameter selection methods.

Keywords

Main Subjects

Computer Engineering

References

References:

1. Saranya, N., Pavithra, L., Kanthimathi, N., et al. "Detection of banana leaf and fruit diseases using neural networks", 2nd Int. Conf. on Inve. Res. Com., App., 202, pp. 493-499 (2020). DOI: 10.1109/ICIRCA48905.2020.9183006.
2. Amara, J., Bouaziz, B., and Algergawy, A. "A deep learning-based approach for banana leaf diseases classification", Datenbanksysteme fur Business, Technologie und Web (BTW 2017) - Workshopband. Bonn: Gesellschaft fur Informatik e.V.. PISSN: 1617- 5468, ISBN: 978-3-88579-660-2. pp. 79-88. Workshop Big (and small) Data in Science and Humanities (BigDS17). Stuttgart. 6.-10. Marz 2017.
3. Sinshaw, N.T., Assefa, B.G., Mohapatra, S.K., et al. "Applications of computer vision on automatic potato plant disease detection: A systematic literature review", Computational Intelligence and Neuroscience, 2022(1) (2022): Article ID 7186687. https://doi.org/10.1155/2022/7186687.
4. Sinshaw, N.T., Assefa, B.G., and Mohapatra, S.K. "Transfer learning and data augmentation based CNN model for potato late blight disease detection", Inter. Conf. on. Info. and. Comm. Tech. for. Deve. for. Afri. (2021). http://dx.doi.org/10.1109/ICT4DA53266.2021.9672243.
5. Eunice, J., Popescu, D.E., Chowdary, M.K., et al. "Deep learning-based leaf disease detection in crops using Images for agricultural applications", Agro., 12, p. 2395 (2022). https://doi.org/10.3390/agronomy12102395.
6. Li, L., Zhang, S., and Wang, B. "Plant disease detection and classification by deep learning-A review", IEEE. Acc., 9, pp. 56683-56698 (2021). http://dx.doi.org/10.1109/ACCESS.2021.3069646.
7. Liu, S., Qiao, Y,. Li, J., et al. "An improved lightweight network for real-time detection of apple leaf diseases in natural scenes", Agro., 12, p. 2363 (2022). https://doi.org/10.3390/agronomy12102363.
8. De Silva, M. and Brown, D. "Multispectral plant disease detection with vision transformer-convolutional neural network hybrid approaches", Sens., 23(20), p. 8531 (2023). https://doi.org/10.3390/s23208531.
9. Aggarwal, M., Khullar, V., Goyal, N., et al. "Federated transfer learning for rice-leaf disease classification across multiclient crosssilo datasets", Agro., 13(10), p. 2483 (2023) http://dx.doi.org/10.3390/agronomy13102483.
10. Simhadri, C.G. and Kondaveeti, H.K. "Automatic recognition of rice leaf diseases using transfer learning", Agro., 13(4), p. 961 (2023). http://dx.doi.org/10.3390/agronomy13040961.
11. Elbasi, E., Zaki, C., Topcu, A.E., et al. "Crop prediction model using machine learning algorithms", App. Sci., 13(16), p. 9288 (2023). http://dx.doi.org/10.3390/app13169288.
12. Domingues, T., Brand~ao, T. and Ferreira, J.C. "Machine learning for detection and prediction of crop diseases and pests: A comprehensive survey", Agri., 12(9), p. 1350 (2022). http://dx.doi.org/10.3390/agriculture12091350.
13. Ferentinos, K.P. "Deep learning models for plant disease detection and diagnosis", Comp. and Elec. in Agri., 145, pp. 311-318 (2018). http://dx.doi.org/10.1016/j.compag.2018.01.009.
14. Chollet, F. "Deep learning mit python und keras: das praxis-handbuch vom entwickler der keras-bibliothek", MITP.Ver. GmbH. and Co. KG., (2018).
15. Teow, M.Y. "Understanding convolutional neural networks using a minimal model for handwritten digit recognition", 2nd. Inter. Conf. on Auto. Cont. and Inte. Syst., pp. 167-172 (2017). http://dx.doi.org/10.1109/I2CACIS.2017.8239052.
16. Patil, A. and Rane, M. "Convolutional neural networks: An overview and its applications in pattern recognition", Inter. Conf. on Infor. and Comm. Tech. for Inte. Sys. Sprin., pp. 21-30 (2020). http://dx.doi.org/10.1007/978-981-15-7078-0-3.
17. Khan, A., Sohail, A., Zahoora, U., et al. "A survey of the recent architectures of deep convolutional neural networks", Artif. Intel. Rev., 53(8), pp. 5455-5516 (2020). http://dx.doi.org/10.1007/s10462-020-09825-6.
18. Feurer, M. and Hutter, F. "Hyperparameter optimization", In Automated Machine Learning: Methods, Systems, Challenges, pp. 3-33 (2019). https://doi.org/10.1007/978-3-030- 05318-5 1.
19. Li, L., Jamieson, K., DeSalvo, G., et al. "Hyperband: A novel bandit-based approach to hyperparameter optimization", J. of Mach. L. Res., 18(185), pp. 1-52 (2017).
20. Bergstra, J., Bardenet, R., Bengio, Y., et al. "Algorithms for hyper-parameter optimization", Advances in Neural Information Processing Systems, 24, pp. 2546-2554 (2011). https://proceedings.neurips. cc/paper/2011.
21. Nguyen, V., Gupta, S., Rana, S., et al. "Filtering bayesian optimization approach in weakly specified search space", K. and Info. Sys., 60, pp. 385-413 (2019). http://dx.doi.org/10.1007/s10115- 018-1238-2.
22. Shahriari, B., Bouchard-Cote, A., and Freitas, N. "Unbounded bayesian optimization via regularization", In Arti. Intel. and St., pp. 1168-1176 (2016).
23. O'Malley, T., Bursztein, E., Long, Chollet.F., et al., "Kerastuner," (2019). https://github.com/kerasteam/ keras -tuner. (2019).