Classifying Sunn Pest Damaged and Healthy Wheat Grains Across Different Species with YOLOV8 and Vision Transformers

Abstract

Sunn pest damage is one of the most crucial types of agricultural damage. Authorities and farmers are working together to find a cost-effective solution for separating the damaged crops from the healthy ones. This challenge can be tackled cost-effectively with emerging technology. Over time, the number of researchers focusing on this problem by using various machine learning algorithms and image processing techniques has increased. This paper presents an approach using a recurrent neural networks-based transformer to identify different varieties of wheat grain that have been sunn pest-damaged and healthy. First, wheat grains were separated from each other using YOLOv8. Then, the dataset was enriched with different data augmentation techniques, and data-efficient vision transformers were used to classify sunn pest-damaged and healthy grains. Conversely, a high accuracy score of 98.61% was achieved on the augmented dataset while surpassing the accuracy score of 93.36% in the raw dataset. This paper's contributions to literature can be divided into three categories. In contrast to the previous research, perfectly shaped, broken, and half-wheat grains are used to better fit findings in real-life environments such as factory production lines. Moreover, this study employs a combination of augmentation techniques, implying that two separate augmentation techniques, texture-based and one morphological, were applied to the same image. Finally, no study in the available literature uses a vision transformer to classify healthy and sunned pest-damaged wheat grains. That leads to using a data-efficient vision transformer algorithm and achieving a high accuracy score of 98.61%.

Keywords

• Sunn pest
• sunn pest detection
• wheat cultivars
• wheat grain segmentation
• crop quality

References

1. B. Shiferaw, M. Smale, H.-J. Braun, E. Duveiller, M. Reynolds, G. Muricho, Crops that feed the world 10. Past successes and future challenges to the role played by wheat in global food security, Food Security 5 (2013) 291–317.
2. Britannica, Wheat (Plant) (2024), https://www.britannica.com/plant/wheat, Accessed 30 June 2024.
3. Statista, Wheat consumption worldwide in 2023/2024, by country (in 1,000 metric tons)* (2024), https://www.statista.com/statistics/1094065/total-global-wheat-consumption-by-country/, Accessed 30 June 2024.
4. Plant Health Australia, Sunn pest (2024), https://www.planthealthaustralia.com.au/wp-content/uploads/2024/01/Sunn-pest-FS.pdf, Accessed 30 June 2024.
5. M. Alamouti, M. Majdi, R. Talebi, M. Dastranj, A. Bandani, G. H. Salekdeh, M. R. Ghaffari, Transcriptome wide identification of neuropeptides and G protein-coupled receptors (GPCRs) in Sunn pest, Eurygaster integriceps Puton, Gene 893 (2024) 147911 14 pages.
6. K. Sabanci, Detection of sunn pest-damaged wheat grains using artificial bee colony optimization-based artificial intelligence techniques, Journal of the Science of Food and Agriculture 100 (2) (2020) 817–824.
7. Z. Basati, B. Jamshidi, M. Rasekh, Y. Abbaspour-Gilandeh, Detection of sunn pest-damaged wheat samples using visible/near-infrared spectroscopy based on pattern recognition, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 203 (2018) 308–314.
8. K. Sabanci, M. F. Aslan, E. Ropelewska, M. F. Unlersen, A. Durdu, A novel convolutional-recurrent hybrid network for sunn pest–damaged wheat grain detection, Food Analytical Methods 15 (6) (2022) 1748–1760.

9. K. Laabassi, M. A. Belarbi, S. Mahmoudi, S. A. Mahmoudi, K. Ferhat, Wheat varieties identification based on a deep learning approach, Journal of the Saudi Society of Agricultural Sciences 20 (5) (2021) 281–289.
10. M. Olgun, A. O. Onarcan, K. Özkan, Ş. Işık, O. Sezer, K. Özgişi, N. G. Ayter, Z. B. Başçiftçi, M. Ardiç, O. Koyuncu, Wheat grain classification by using dense SIFT features with SVM classifier, Computers and Electronics in Agriculture 122 (2016) 185–190.
11. K. Sabanci, M. F. Aslan, A. Durdu, Bread and durum wheat classification using wavelet based image fusion, Journal of the Science of Food and Agriculture 100 (15) (2020) 5577–5585.
12. K. Sabanci, A. Kayabasi, A. Toktas, Computer vision-based method for classification of wheat grains using artificial neural network, Journal of the Science of Food and Agriculture 97 (8) (2017) 2588–2593.
13. A. Taner, Y. B. Öztekin, A. Tekgüler, H. Sauk, H. Duran, Classification of varieties of grain species by artificial neural networks, Agronomy 8 (7) (2018) 123 14 pages.
14. D. Agarwal, Sweta, P. Bachan, Machine learning approach for the classification of wheat grains, Smart Agricultural Technology 3 (2023) 100136 10 pages.
15. A. Sharma, T. Singh, N. Garg, Combining near-infrared hyperspectral imaging and ANN for varietal classification of wheat seeds, in: Manu Malek (Ed.), 2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT), Kannur, 2022, pp. 1103–1108.
16. A. Khatri, S. Agrawal, J. M. Chatterjee, Wheat seed classification: Utilizing ensemble machine learning approach, Scientific Programming 2022 (1) (2022) Article ID 2626868 9 pages.
17. S. Shedole, S. B. J, N. A. V. P, A convolution neural network-based wheat grain classification system, Journal of Scientific Research of The Banaras Hindu University 66 (2) (2022) 204 22–29.
18. S. Lingwal, K. Bhatia, M. Tomer, Image-based wheat grain classification using convolutional neural network, Multimedia Tools and Applications 80 (28) (2021) 35441–35465.
19. A. Kayabasi, An application of ANN trained by ABC algorithm for classification of wheat grains, International Journal of Intelligent Systems and Applications in Engineering 6 (1) (2018) 85–91.
20. W. Zhao, S. Liu, X. Li, X. Han, H. Yang, Fast and accurate wheat grain quality detection based on improved YOLOv5, Computers and Electronics in Agriculture 202 (2022) 107426 10 pages.
21. N. Pervan Akman, M. Çolak, Ö. Özkan, T. Tümer Sivri, A. Berkol, M. Olgun, Z. Budak Başçiftçi, G. Ayter, O. Sezer, M. Ardıç, Wheat dataset for species classification and sunn pest damage detection (2023), https://data.mendeley.com/datasets/gmw48bvxdz/1, Accessed 30 June 2024.
22. R. Shen, T. Zhen, Z. Li, Segmentation of unsound wheat kernels based on improved mask RCNN, Sensors 23 (7) (2023) 3379 17 pages.
23. R. C. Bernardes, A. De Medeiros, L. da Silva, L. Cantoni, G. F. Martins, T. Mastrangelo, A. Novikov, C. B. Mastrangelo, Deep-learning approach for fusarium head blight detection in wheat seeds using low-cost imaging technology, Agriculture 12 (11) (2022) 1801 14 pages.
24. M. F. Unlersen, M. E. Sonmez, M. F. Aslan, B. Demir, N. Aydin, K. Sabanci, E. Ropelewska, CNN–SVM hybrid model for varietal classification of wheat based on bulk samples, European Food Research and Technology 248 (8) (2022) 2043–2052.
25. H. Gao, T. Zhen, Z. Li, Detection of wheat unsound kernels based on improved ResNet, IEEE Access 10 (2022) 20092–20101.
26. J. B. Motie, M. H. Saeidirad, M. Jafarian, Identification of sunn-pest affected (eurygaster integriceps put.) wheat plants and their distribution in wheat fields using aerial imaging, Ecological Informatics 76 (2023) 102146 15 pages.
27. Y. Abbaspour-Gilandeh, H. Ghadakchi-Bazaz, M. Davari, Discriminating healthy wheat grains from grains infected with fusarium graminearum using texture characteristics of image-processing technique, discriminant analysis, and support vector machine methods, Journal of Intelligent Systems 29 (1) (2019) 1576–1586.
28. Z. Fazel-Niari, A. H. Afkari-Sayyah, Y. Abbaspour-Gilandeh, I. Herrera-Miranda, J. L. Hernandez Hernandez, M. Hernandez-Hernandez, Quality assessment of components of wheat seed using different classifications models, Applied Sciences 12 (9) (2022) 4133 12 pages.
29. E. Kaya, İ. Saritas, Towards a real-time sorting system: Identification of vitreous durum wheat kernels using ann based on their morphological, colour, wavelet and gaborlet features, Computers and Electronics in Agriculture 166 (2019) 105016 9 pages.
30. C. Erkinbaev, M. Nadimi, J. Paliwal, A unified heuristic approach to simultaneously detect fusarium and ergot damage in wheat, Measurement: Food 7 (2022) 100043 6 pages.
31. L. Zhang, H. Ji, Identification of wheat grain in different states based on hyperspectral imaging technology, Spectroscopy Letters 52 (6) (2019) 356–366.
32. W. Zhang, H. Ma, X. Li, X. Liu, J. Jiao, P. Zhang, L. Gu, Q. Wang, W. Bao, S. Cao, Imperfect wheat grain recognition combined with an attention mechanism and residual network, Applied sciences 11 (11) (2021) 5139 12 pages.
33. H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, H. Jegou, Training data-efficient image transformers distillation through attention, in: Marina Meila, Tong Zhang (Eds.), 38th International Conference on Machine Learning, Austria, 2021, pp. 10347–10357.