Potato leaf disease classification using Vision Transformers
DOI:
https://doi.org/10.37135/ns.01.15.06Keywords:
precision agriculture, deep learning, image classification, potato diseases, vision transformer (ViT)Abstract
Disease detection and classification in crops is crucial for the development and growth of the agricultural sector. Traditional techniques and the low technical level applied to crop control generate significant losses for farmers. Computer vision offers solutions in this field; however, current research focuses on using convolutional neural networks (CNNs), which cannot accurately locate the most relevant features in an image. To overcome these limitations, this study proposes a deep learning model based on the Vision Transformers (ViT) architecture to detect and classify early and late blight diseases in potato leaves. This research demonstrates how data augmentation, fine-tuning, and transfer learning techniques can improve the model's performance. The dataset for training and testing was taken from the PlantVillage platform. The report of the proposed model's evaluation metrics reaches an accuracy of 99.18% and an F1 score of 98.7%. The results demonstrate a high level of prediction in potato foliar diseases and evidence of the efficiency of attention mechanisms. It is concluded that the model is an innovative and functional tool for farmers.
Downloads
References
Arshad, F., Mateen, M., Hayat, S., Wardah, M., Al-Huda, Z., Gu, Y. H., & Al-antari, M. A. (2023). PLDPNet: End-to-end hybrid deep learning framework for potato leaf disease prediction. Alexandria Engineering Journal, 78, 406-418. https://doi.org/10.1016/J.AEJ.2023.07.076
Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer Normalization. Statistics – Machine Learning. https://doi.org/10.48550/arXiv.1607.06450
Barman, U., Sarma, P., Rahman, M., Deka, V., Lahkar, S., Sharma, V., & Saikia, M. J. (2024). ViT-SmartAgri: Vision Transformer and Smartphone-Based Plant Disease Detection for Smart Agriculture. Agronomy, 14(2), 327. https://doi.org/10.3390/AGRONOMY14020327
Barrera, V., Escudero, L., Norton, G. W., & Sherwood, S. (2002). Validación y difusión de modelos de manejo integrado de plagas y enfermedades en el cultivo de la papa: Una experiencia de capacitación participativa en la Provincia del Carchi, Ecuador. Revista Informativa INIAP, 16, 25-28. http://repositorio.iniap.gob.ec/handle/41000/1493
Comisión Económica para América Latina y el Caribe [CEPAL], Organización de las Naciones Unidas para la Agricultura y la Alimentación [FAO], & Instituto Interamericano de Cooperación para la Agricultura [IICA]. (2021). Perspectivas de la Agricultura y del Desarrollo Rural en las Américas: una mirada hacia América Latina y el Caribe 2021-2022. IICA. https://hdl.handle.net/11362/47208
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L., (2009). ImageNet: A large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition, FL, USA. https://doi.org/10.1109/CVPR.2009.5206848
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, G., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Computer Vision and Pattern Recognition. https://doi.org/10.48550/arXiv.2010.11929
Elngar, A. A., Arafa, M., Fathy, A., Moustafa, B., Mahmoud, O., Shaban, M., & Fawzy, N. (2021). Image Classification Based On CNN: A Survey. Journal of Cybersecurity and Information Management (JCIM), 6(1), 18-50. https://doi.org/10.54216/JCIM.060102
Ihme, M., Chung, W. T., & Mishra, A. A. (2022). Combustion machine learning: Principles, progress and prospects. Progress in Energy and Combustion Science, 91. https://doi.org/10.1016/j.pecs.2022.101010
Khan, A., Rauf, Z., Sohail, A., Rehman, A., Asif, H., Asif, A., & Farooq, U. (2023). A survey of the vision transformers and their CNN-transformer based variants. Artificial Intelligence Review, 56, 2917-2970. https://doi.org/10.1007/s10462-023-10595-0
Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436-444. https://doi.org/10.1038/nature14539
López Calvajar, G. A., López Fernández, R. C., & León González, J. L. (2017). Análisis de la influencia de factores climatológicos en la pérdida de superficie sembrada de cultivos transitorios en el Ecuador. Revista Científica Agroecosistemas, 5(3), 176-183. https://aes.ucf.edu.cu/index.php/aes/article/view/155
Lozada-Portilla, W. A., Suarez-Barón, M. J., & Avendaño-Fernández, E. (2021). Aplicación de redes neuronales convolucionales para la detección del tizón tardío Phytophthora infestans en papa Solanum tuberosum. Revista U.D.C.A Actualidad & Divulgación Científica, 24(2), e1917. https://doi.org/10.31910/rudca.v24.n2.2021.1917
Mahum, R., Munir, H., Mughal, Z. U. N., Awais, M., Sher Khan, F., Saqlain, M., Mahamad, S., & Tlili, I. (2022). A novel framework for potato leaf disease detection using an efficient deep learning model. Human and Ecological Risk Assessment: An International Journal, 29(2), 303–326. https://doi.org/10.1080/10807039.2022.2064814
Ministerio de Agricultura y Ganadería. (2022). Boletín situacional cultivo de papa. https://sipa.agricultura.gob.ec/index.php/papa/boletines-situacionales-papa-ecuador
Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419. https://doi.org/10.3389/fpls.2016.01419
Paucar Buñay, D. J. (2016). Factores que influyen en el nivel de conocimientos ancestrales en el manejo del cultivo de papa (Solanum tuberosum) en dos sectores de la provincia de Tungurahua [Tesis de grado, Universidad Técnica de Ambato]. Repositorio Universidad Técnica de Ambato. https://repositorio.uta.edu.ec:8443/jspui/handle/123456789/24431
Pavel, M. I., Rumi, R. I., Fairooz, F., Jahan, S., & Hossain, M. A. (2021). Deep Residual Learning Approach for Plant Disease Recognition. International Conference on Mobile Computing and Sustainable Informatics, 511-521. https://doi.org/10.1007/978-3-030-49795-8_49
Pérez, W., & Forbes, G. (2016). Guía de identificación de plagas que afectan a la papa en la zona andina- Lima (Perú). Centro Internacional de la Papa (CIP). https://doi.org/10.4160/9789290604020
Pintelas, E., Liaskos, M., Livieris, I. E., Kotsiantis, S., & Pintelas, P. (2020). Explainable machine learning framework for image classification problems: Case study on glioma cancer prediction. Journal of Imaging, 6(6), 37. https://doi.org/10.3390/JIMAGING6060037
Sakkarvarthi, G., Sathianesan, G. W., Murugan, V. S., Reddy, A. J., Jayagopal, P., & Elsisi, M. (2022). Detection and Classification of Tomato Crop Disease Using Convolutional Neural Network. Electronics, 11(21), 3618. https://doi.org/10.3390/electronics11213618
Sen, P. C., Hajra, M., & Ghosh, M. (2020). Supervised Classification Algorithms in Machine Learning: A Survey and Review. Advances in Intelligent Systems and Computing, 937, 99-111. https://doi.org/10.1007/978-981-13-7403-6_11
Shaheed, K., Qureshi, I., Abbas, F., Jabbar, S., Abbas, Q., Ahmad, H., & Sajid, M. Z. (2023). EfficientRMT-Net—An Efficient ResNet-50 and Vision Transformers Approach for Classifying Potato Plant Leaf Diseases. Sensors, 23(23), 9516. https://doi.org/10.3390/S23239516
Shirahatti, J., Patil, R., & Akulwar, P. (2018). A Survey Paper on Plant Disease Identification Using Machine Learning Approach. Proceedings of the 3rd International Conference on Communication and Electronics Systems, ICCES, 1171-1174. https://doi.org/10.1109/CESYS.2018.8723881
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017). Revisiting Unreasonable Effectiveness of Data in Deep Learning Era. Computer Vision and Pattern Recognition. https://doi.org/10.48550/arXiv.1707.02968
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Lukasz, K., & Polosukhin, I. (2017). Attention Is All You Need. Computation and Language. https://doi.org/10.48550/arXiv.1706.03762
