(49-3) 09 * << * >> * Russian * English * Content * All Issues

Bidirectional Encoder representation from Image Transformers for recognizing sunflower diseases from photographs
V.A. Baboshina 1, P.A. Lyakhov 1,2, U.A. Lyakhova 2, V.A. Pismennyy 2

1 North-Caucasus Center for Mathematical Research, North-Caucasus Federal University,
Pushkin Str. 1, 355017, Stavropol, Russia;
2 Department of Mathematical Modeling, North-Caucasus Federal University,
Pushkin Str. 1, 355017, Stavropol, Russia

 PDF, 2846 kB

DOI: 10.18287/2412-6179-CO-1514

Pages: 435-442.

Full text of article: English language.

Abstract:
This paper proposes a modern system for recognizing sunflower diseases based on Bidirectional Encoder representation from Image Transformers (BEIT). The proposed system is capable of recognizing various sunflower diseases with high accuracy. The presented research results demonstrate the advantages of the proposed system compared to known methods and contemporary neural networks. The proposed visual diagnostic system for sunflower diseases achieved 99.57 % accuracy on the sunflower disease dataset, which is higher than that of known methods. The approach described in the work can serve as an auxiliary tool for farmers, assisting them in promptly identifying diseases and pests and taking timely measures to treat plants. This, in turn, helps in preserving and enhancing the yield. This work can have a significant impact on the development of agriculture and the fight against the global food shortage problem.

Keywords:
image transformer, neural network recognition, image processing, sunflower diseases, bidirectional encoder.

Citation:
Baboshina VA, Lyakhov PA, Lyakhova UA, Pismennyy VA. Bidirectional Encoder representation from Image Transformers for recognizing sunflower diseases from photographs. Computer Optics 2025; 49(3): 435-442. DOI: 10.18287/2412-6179-CO-1514.

Acknowledgements:
The authors express their gratitude to NCFU for the support of small scientific groups and individual scientists. Research was conducted with the support of the Russian Science Foundation (project No. 23-71-10013).

References:
  1. Population, United Nations. 2024. Source: <https://www.un.org/en/global-issues/population>.
  2. The state of food security and nutrition in the world. Food and Agriculture Organization of the United Nations. 2023. Source: <https://www.fao.org/publications/home/fao-flagship-publications/the-state-of-food-security-and-nutrition-in-the-world/en>.
  3. The plants that feed the world: Baseline data and metrics to inform strategies for the conservation and use of plant genetic resources for food and agriculture. Ninth Session of the Governing Body, New Delhi, India. 2022. Source: <https://openknowledge.fao.org/server/api/core/bitstreams/3f79e42f-0fd2-45cb-98a9-099b3748547c/content>.
  4. Adeleke BS, Babalola OO. Oilseed crop sunflower (Helianthus annuus) as a source of food: Nutritional and health benefits. Food Sci Nutr 2020; 8: 4666-4684. DOI: https://doi.org/10.1002/fsn3.1783
  5. Kottapalli B, Nguyen SPV, Dawson K, Casulli K, Knockenhauer C, Schaffner DW. Evaluating the risk of salmonellosis from dry roasted sunflower seeds. J Food Prot 2020; 83(1): 17-27. DOI: 10.4315/0362-028x.jfp-19-171.
  6. da Rocha-Filho PA, Maruno M, Ferrari M, Topan JF. Liquid crystal formation from sunflower oil: Long term stability studies. Molecules 2016; 21(6): 680. DOI: 10.3390/molecules21060680.
  7. Savary S. Plant health and food security. J Plant Pathol 2020; 102: 605-607. DOI: 10.1007/s42161-020-00611-5.
  8. Agrawal M, Agrawal S. Rice plant diseases detection using convolutional neural networks. Int J Eng Syst Model Simul 2023; 14(1): 30-42. DOI: 10.1504/IJESMS.2023.127396.
  9. Umapathi R, Ghoreishian SM, Sonwal S, Rani GM, Huh YS. Portable electrochemical sensing methodologies for on-site detection of pesticide residues in fruits and vegetables. Coord Chem Rev 2022; 453: 214305. DOI: 10.1016/j.ccr.2021.214305.
  10. Sara U, Rajbongshi A, Shakil R, Akter B, Sazzad S, Uddin MS. An extensive sunflower dataset representation for successful identification and classification of sunflower diseases. Data Brief 2022; 42: 108043. DOI: 10.1016/j.dib.2022.108043.
  11. Gulzar Y, Ünal Z, Aktaş H, Mir MS. Harnessing the power of transfer learning in sunflower disease detection: A comparative study. Agriculture 2023; 13(8): 1479. DOI: 10.3390/agriculture13081479.
  12. Liu J, Lv F, Penghui D. Identification of sunflower leaf diseases based on random forest algorithm. 2019 Int Conf on Intelligent Computing, Automation and Systems (ICICAS) 2019: 459-463. DOI: 10.1109/ICICAS48597.2019.00102.
  13. Sathi TA, Hasan MA, Alam MJ. SunNet: A deep learning approach to detect sunflower disease. 7th Int Conf on Trends in Electronics and Informatics (ICOEI) 2023: 1210-1216. DOI: 10.1109/ICOEI56765.2023.10125676.
  14. Zhong Y, Tong MJ. TeenyNet: A novel lightweight attention model for sunflower disease detection. Meas Sci Technol 2023; 35(3): 035701. DOI: 10.1088/1361-6501/ad1152.
  15. Thilagavathi T, Arockiam L. Segmentation of sunflower leaf disease using improved YOLO network with IDMO model. Int J Intell Syst Appl Eng 2024; 12(125): 600-611.
  16. Dai G, Tian Z, Fan J, Sunil CK, Dewi C. DFN-PSAN: Multi-level deep information feature fusion extraction network for interpretable plant disease classification. Comput Electron Agric 2024; 216: 108481. DOI: 10.1016/j.compag.2023.108481.
  17. Sun C, Zhou X, Zhang M, Qin A. SE-VisionTransformer: Hybrid network for diagnosing sugarcane leaf diseases based on attention mechanism. Sensors 2023; 23(20): 8529. DOI: 10.3390/s23208529.
  18. Sodikov B, Rakhmonov U, Khamiraev U, Akbarov M. Fungal diseases of sunflower and measures against them. PalArch’s Journal of Archaeology of Egypt/Egyptology 2020; 17(6): 3268-3279.
  19. Devlin J, Chang M-W, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv Preprint. 2019. Source: <https://arxiv.org/abs/1810.04805>. DOI: 10.48550/arXiv.1810.04805.
  20. Ramesh A, Pavlov M, Goh G, Gray S, Voss C, Radford A, Chen M, Sutskever I. Zero-shot text-to-image generation. arXiv Preprint. 2021. Source: <https://arxiv.org/abs/2102.12092>. DOI: 10.48550/arXiv.2102.12092.
  21. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. 31st Conf on Neural Information Processing Systems (NIPS 2017) 2017: 6000-6010.
  22. Bao H, Dong L, Piao S, Wei F. BEiT: BERT pre-training of image transformers. The Tenth Int Conf on Learning Representations (ICLR) 2022: 1-18.
  23. Zhu H, Chen B, Yang C. Understanding why ViT trains badly on small datasets: An intuitive perspective. arXiv Preprint. 2023. Source: <https://arxiv.org/abs/2302.03751>. DOI: 10.48550/arXiv.2302.03751.
  24. Loshchilov I, Hutter F. Decoupled weight decay regularization. 7th Int Conf on Learning Representations (ICLR) 2019: 1-8. Source: <https://openreview.net/pdf?id=Bkg6RiCqY7>.
  25. Kim Y, Lee Y, Jeon M. Imbalanced image classification with complement cross entropy. Pattern Recogn Lett 2022; 151: 33-40. DOI: 10.1016/j.patrec.2021.07.017.      
  26. Ho Y, Wookey S. The real-world-weight cross-entropy loss function: Modeling the costs of mislabeling. IEEE Access 2020; 8: 4806-4813. DOI: 10.1109/ACCESS.2019.2962617.
  27. Huynh T, Nibali A, He Z. Semi-supervised learning for medical image classification using imbalanced training data. Comput Methods Programs Biomed 2022; 216: 106628. DOI: 10.1016/j.cmpb.2022.106628.
  28. Vo NH, Won Y. Classification of unbalanced medical data with weighted regularized least squares. 2007 Frontiers in the Convergence of Bioscience and Information Technologies 2007: 347-352. DOI: 10.1109/FBIT.2007.20.
  29. Aurelio YS, de Almeida GM, de Castro CL. Learning from imbalanced data sets with weighted cross-entropy function. Neural Process Lett 2019; 50(2): 1937-1949. DOI: 10.1007/s11063-018-09977-1.
  30. Dong Y, Shen X, Jiang Z, Wang H. Recognition of imbalanced underwater acoustic datasets with exponentially weighted cross-entropy loss. Appl Acoust 2021; 174: 107740. DOI: 10.1016/j.apacoust.2020.107740.
  31. Ghosh P, Mondal AK, Chatterjee S, Masud M, Meshref H, Bairagi AK. Recognition of sunflower diseases using hybrid deep learning and its explainability with AI. Mathematics 2023; 11(10): 2241. DOI: 10.3390/math11102241.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20