A Hybrid Model Approach Based on Swin Transformer and EfficientNetV2 for Maize Variety Classification

Authors

DOI:

https://doi.org/10.58190/ijamec.2025.132

Keywords:

classification, Hybrid Deep Learning Model, Maize Classification

Abstract

In this study, two different deep learning-based models were proposed for the classification of the maize varieties Chulpi Cancha, Indurata, and Rugosa. In the first stage, a single model was developed using the Swin Transformer architecture with an attention mechanism. This model was then integrated with EfficientNetV2 to create a hybrid structure. The developed models were tested on a dataset consisting of 1050 images with a fixed background and high resolution. The Swin Transformer model produced successful results with 99.37% accuracy, while the hybrid model achieved 100% test accuracy, accurately classifying all samples. The findings demonstrate that the Swin Transformer and EfficientNetV2-based hybrid architectures offer high discrimination power and generalization capacity in image-based classification of maize varieties. Future studies are recommended to conduct additional tests using images taken under different environmental conditions and larger datasets encompassing a wider range of varieties.

Downloads

Download data is not yet available.

References

[1] A. Kumar, R. Singh, and S. S. Chauhan, “Revolutionizing Agriculture: Applications of Artificial Intelligence in Crop Management and Disease Detection,” Frontiers in Plant Science, vol. 15, no. 1356260, 2024. https://doi: 10.3389/fpls.2024.1356260

[2] Ambrose, A., Kandpal, L. M., Kim, M. S., Lee, W.-H., & Cho, B.-K. (2016). High speed measurement of corn seed viability using hyperspectral imaging. Infrared Physics & Technology, 75, 173–179. https://doi.org/10.1016/j.infrared.2015.12.008

[3] Avuçlu, E., Taşdemir, Ş., & Koklu, M. (2023). A new hybrid model for classification of corn using morphological properties. European Food Research and Technology, 249(3), 835–847. https://doi.org/10.1007/s00217-022-04181-x

[4] Chivasa, W., O. Mutanga, and C. Biradar. 2019. “Phenology-Based Discrimination of Maize (Zea mays L.) Varieties Using Multitemporal Hyperspectral Data.” Journal of Applied Remote Sensing 13, no. 1: 017504– 017504. https://doi.org/10.1117/1.JRS.13.017504.

[5] Kishore B, Yasar A, Taspinar YS, Kursun R, Cinar I, Shankar VG, Koklu M, Ofori I. Computer-Aided Multiclass Classification of Corn from Corn Images Integrating Deep Feature Extraction. Comput Intell Neurosci. 2022 Aug 10;2022:2062944. https://doi.org/10.1155/2022/2062944 .

[6] Isik, H., S. Tasdemir, Y. Selim Taspinar, et al. 2024. “Maize Seeds Forecasting With Hybrid Directional and Bi-Directional Long Short-Term Memory Models.” Food Science & Nutrition 12, no. 2: 786–803. https://doi.org/10.1002/fsn3.3783.

[7] Wang, F., H. Zhao, C. Yu, J. Tang, W. Wu, and Q. Yang. 2020. “Determination of the Geographical Origin of Maize (Zea mays L.) Using Mineral Element Fingerprints.” Journal of the Science of Food and Agriculture 100, no. 3: 1294–1300. https://doi.org/10.1002/jsfa.10144.

[8] Yang, X., Hong, H., You, Z., & Cheng, F. (2015). Spectral and image integrated analysis of hyperspectral data for waxy corn seed variety classification. Sensors, 15(7), 15578–15594. https://doi.org/10.3390/s150715578

[9] Zhao, M., Wu, W., Zhang, Y. Q., & Li, X. (2011). Combining genetic algorithm and SVM for corn variety identification. International Conference on Mechatronic Science, Electric Engineering and Computer, 990–993. https://doi.org/10.1109/MEC.2011.6025631

[10] Zhang, J., Dai, L. & Cheng, F. Corn seed variety classification based on hyperspectral reflectance imaging and deep convolutional neural network. Food Measure 15, 484–494 (2021). https://doi.org/10.1007/s11694-020-00646-3.

[11] H. O. Velesaca, R. Mira, P. L. Suárez, C. X. Larrea and A. D. Sappa, "Deep Learning based Corn Kernel Classification," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, 2020, pp. 294-302, https://doi.org/10.1109/CVPRW50498.2020.00041

[12] Ni, C., Wang, D., Vinson, R., Holmes, M., & Tao, Y. (2019). Automatic inspection machine for maize kernels based on deep convolutional neural networks. Biosystems Engineering, 178, 131–144. https://doi.org/10.1016/j.biosystemseng.2018.11.010

[13] Javanmardi, S., Ashtiani, S.-H. M., Verbeek, F. J., & Martynenko, A. (2021). Computer-vision classification of corn seed varieties using deep convolutional neural network. Journal of Stored Products Research, 92, 101800. https://doi.org/10.1016/j.jspr.2021.101800

[14] Isik H, Tasdemir S, Taspinar YS, Kursun R, Cinar I, Yasar A, Yasin ET, Koklu M. Maize seeds forecasting with hybrid directional and bi-directional long short-term memory models. Food Sci Nutr. 2023 Nov 9;12(2):786-803. doi: 10.1002/fsn3.3783. PMID: 38370035; PMCID: PMC10867492. https://doi.org/10.1002/fsn3.3783

[15] K. Kiratiratanapruk and W. Sinthupinyo, "Color and texture for corn seed classification by machine vision," 2011 International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS), Chiang Mai, Thailand, 2011, pp. 1-5, https://doi.org/:10.1109/ISPACS.2011.6146100.

[16] Zhao, Y., S. Zhu, C. Zhang, X. Feng, L. Feng, and Y. He. 2018. Application of Hyperspectral Imaging and Chemometrics for Variety Classification of Maize Seeds. RSC Advances 8, no. 3: 1337–1345. https://doi.org/10.1039/C7RA05954J

[17] S. Kai, L. Zhikun, S. Hang and G. Chunhong, "A Research of Maize Disease Image Recognition of Corn Based on BP Networks," 2011 Third International Conference on Measuring Technology and Mechatronics Automation, Shanghai, China, 2011, pp. 246-249, https://doi.org/10.1109/ICMTMA.2011.66.

[18] Yang, X., Hong, H., You, Z., & Cheng, F. (2015). Spectral and Image Integrated Analysis of Hyperspectral Data for Waxy Corn Seed Variety Classification. Sensors, 15(7), 15578-15594. https://doi.org/10.3390/s150715578

[19] Huang M, Tang J, Yang B, Zhu Q (2016) Classifcation of corn seeds of diferent years based on hyperspectral imaging and model updating. Comput Electron Agric 122:139–145. https://doi.org/10.1016/j.compag.2016.01.029

[20] Williams PJ, Kucheryavskiy S (2016). Classifcation of corn kernels using NIR hyperspectral imaging. Food Chem 209:131–138. https://doi.org/10.1016/j.foodchem.2016.04.044

[21] Wu A, Zhu J, Yang Y, Liu X, Wang X, Wang L, Chen J (2018). Classifcation of corn kernels grades using image analysis and support vector machine. Adv Mech Eng 10(12):1687814018817642. https://doi.org/10.1177/1687814018817642

[22] Daskalov P, Kirilova E, Georgieva T (2018). Performance of an automatic inspection system for classifcation of Fusarium Moniliforme damaged corn seeds by image analysis. In: MATEC Web of Conferences, Vol. 210, EDP Sciences, p. 02014. https://doi.org/10.1051/matecconf/201821002014

[23] Li, X., Dai, B., Sun, H., & Li, W. (2019). Corn Classification System based on Computer Vision. Symmetry, 11(4), 591. https://doi.org/10.3390/sym11040591

[24] Lopes, J.F., da Costa, V.G.T., Barbin, D.F. et al. Deep computer vision system for cocoa classification. Multimed Tools Appl 81, 41059–41077 (2022). https://doi.org/10.1007/s11042-022-13097-3

[25] Marciano M. Oliveira, Breno V. Cerqueira, Sylvio Barbon, Douglas F. Barbin, Classification of fermented cocoa beans (cut test) using computer vision, Journal of Food Composition and Analysis, Volume 97, 2021, 103771, ISSN 0889-1575, https://doi.org/10.1016/j.jfca.2020.103771.

[26] Lopes, J. F., Ludwig, L., Barbin, D. F., Grossmann, M. V. E., & Barbon, S., Jr. (2019). Computer Vision Classification of Barley Flour Based on Spatial Pyramid Partition Ensemble. Sensors, 19(13), 2953. https://doi.org/10.3390/s19132953

[27] Avuçlu E, Köklü M. Fast and Accurate Classification of Corn Varieties Using Deep Learning With Edge Detection Techniques. J Food Sci. 2025 Jul;90(7):e70439. https://doi.org/10.1111/1750-3841.70439 . PMID: 40702919.

[28] M. E. Sönmez, K. Sabancı, and N. Aydın, “Classification of Wheat Rootstock and Their Hybrids According to Color Features by Machine Learning Algorithms”, International Journal of Applied Mathematics Electronics and Computers, vol. 10, no. 2, pp. 39–48, 2022, https://doi.org/10.18100/ijamec.1098276.

[29] P. K. Das and S. S. Rupa. ResNet for Leaf-based Disease Classification in Strawberry Plant. J. Appl. Methods Electron. Comput., vol. 11, no. 3, pp. 151–157, Sep. 2023, https://doi.org/10.58190/ijamec.2023.42.

[30] G. Altan, “Performance Evaluation of Capsule Networks for Classification of Plant Leaf Diseases”, International Journal of Applied Mathematics Electronics and Computers, vol. 8, no. 3, pp. 57–63, 2020, https://doi.org/10.18100/ijamec.797392

[31] Sun, Y., Ning, L., Zhao, B., & Yan, J. (2024). Tomato Leaf Disease Classification by Combining EfficientNetv2 and a Swin Transformer. Applied Sciences. https://doi.org/10.3390/app14177472.

[32] Li, L., & Tanone, R. (2023). Disease Identification in Potato Leaves using Swin Transformer. 2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM), 1-5. https://doi.org/10.1109/IMCOM56909.2023.10035609.

[33] Zhao, K., Huo, Y., Xue, L., Yao, M., Tian, Q., & Wang, H. (2023). Mushroom Image Classification and Recognition Based on Improved Swin Transformer. 2023 IEEE 6th International Conference on Information Systems and Computer Aided Education (ICISCAE), 225-231. https://doi.org/10.1109/ICISCAE59047.2023.10392483.

Downloads

Published

30-09-2025

Issue

Section

Research Articles

How to Cite

[1]
H. Bulduk and K. . Sabancı, “A Hybrid Model Approach Based on Swin Transformer and EfficientNetV2 for Maize Variety Classification”, J. Appl. Methods Electron. Comput., vol. 13, no. 3, pp. 84–92, Sep. 2025, doi: 10.58190/ijamec.2025.132.

Similar Articles

1-10 of 147

You may also start an advanced similarity search for this article.