Soybean Seed Classification with Fusion of Convolutional Neural Networks and ViT Technique
DOI:
https://doi.org/10.65150/EP-gjetr/V2E2/2026-03Keywords:
Soybean classification, Deep Learning, Convolutional Neural Networks, Vision Transformer, Feature FusionAbstract
Soybeans are a nutritious legume cultivated worldwide and are a staple in the human diet. They also play a vital role in animal feed production. Furthermore, soybean oil, extracted from soybeans, is widely used in the food industry. Several different convolutional neural network (CNN) models, along with image transformation (ViT) models, were used to classify soybean seeds. The seed classification comprised five categories: broken, immature, intact, shell-damaged, and defective. To enhance the generalizability of the dataset, data augmentation techniques were applied during the training process. Seventeen pre-trained CNN and ViT models with varying architectures were tested. Model performance was evaluated using performance metrics such as accuracy, fine-tuning, recall, and F1. The proposed model was constructed by combining feature extraction layers from the top-performing ViT-L/16, DenseNet201, and DenseNet169 models. The proposed model outperformed all other models, achieving an accuracy of 96.02% in the classification process. With this proposed model, we have obtained a hybrid approach to classifying soybean seeds, and it contributes to the use of artificial intelligence in the agricultural sector.
References
1) J. Pereira, M. Lopes, J. Parish, A. Silva, and M. PicanÇO, "Impact of RR soybeans and glyphosate on the community of soil surface arthropods," Planta Daninha, vol. 36, p. e018171324, 2018.
2) K.-C. Lee et al., "Rapid Identification Method for Gamma-Irradiated Soybeans Using Gas Chromatography–Mass Spectrometry Coupled with a Headspace Solid-Phase Microextraction Technique," Journal of agricultural and food chemistry, vol. 68, no. 9, pp. 2803-2815, 2020.
3) B. Behailu and M. Abebe, "Effect of soybean and finger millet flours on the physicochemical and sensory quality of beef meat sausage," Asian Journal of Chemical Sciences, vol. 7, no. 1, pp. 6-14, 2020.
4) X. Zhu, W. L. Leiser, V. Hahn, and T. Würschum, "Identification of QTL for seed yield and agronomic traits in 944 soybean (Glycine max) RILs from a diallel cross of early‐maturing varieties," Plant Breeding, vol. 140, no. 2, pp. 254-266, 2021.
5) M. A. McNiven, P. Robinson, and J. MacLeod, "Evaluation of a new high protein variety of soybeans as a source of protein and energy for dairy cows," Journal of dairy science, vol. 77, no. 9, pp. 2605-2613, 1994.
6) M. Friedman and D. L. Brandon, "Nutritional and health benefits of soy proteins," Journal of agricultural and food chemistry, vol. 49, no. 3, pp. 1069-1086, 2001.
7) A. E. Atabani, A. S. Silitonga, I. A. Badruddin, T. Mahlia, H. Masjuki, and S. Mekhilef, "A comprehensive review on biodiesel as an alternative energy resource and its characteristics," Renewable and sustainable energy reviews, vol. 16, no. 4, pp. 2070-2093, 2012.
8) P. Lin et al., "Rapidly and exactly determining postharvest dry soybean seed quality based on machine vision technology," Scientific Reports, vol. 9, no. 1, p. 17143, 2019.
9) C. Xia, S. Yang, M. Huang, Q. Zhu, Y. Guo, and J. Qin, "Maize seed classification using hyperspectral image coupled with multi-linear discriminant analysis," Infrared Physics & Technology, vol. 103, p. 103077, 2019.
10) P. Singh et al., "Development of an intelligent laser biospeckle system for early detection and classification of soybean seeds infected with seed-borne fungal pathogen (Colletotrichum truncatum)," Biosystems Engineering, vol. 212, pp. 442-457, 2021.
11) Y. Hamid, S. Wani, A. B. Soomro, A. A. Alwan, and Y. Gulzar, "Smart seed classification system based on MobileNetV2 architecture," in 2022 2nd international conference on computing and information technology (iccit), 2022: IEEE, pp. 217-222.
12) N. Çetin, "Machine learning for varietal binary classification of soybean (Glycine max (L.) Merrill) seeds based on shape and size attributes," Food Analytical Methods, vol. 15, no. 8, pp. 2260-2273, 2022.
13) Z. Huang et al., "Deep learning based soybean seed classification," Computers and Electronics in Agriculture, vol. 202, p. 107393, 2022.
14) W. Lin, L. Shu, W. Zhong, W. Lu, D. Ma, and Y. Meng, "Online classification of soybean seeds based on deep learning," Engineering Applications of Artificial Intelligence, vol. 123, p. 106434, 2023.
15) "Kaggle Soybean Seeds Dataset." [Online]. Available: https://www.kaggle.com/datasets/warcoder/soyabean-seeds.
16) W. Lin et al., "Soybean image dataset for classification," Data in Brief, p. 109300, 2023.
17) C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9.
18) Ünlükal, N., Ülker, E., Solmaz, M., Uyar, K., & Taşdemir, Ş. (2024). Histological tissue classification with a novel statistical filter‐based convolutional neural network. Anatomia, Histologia, Embryologia, 53(4), e13073.
19) J. Wang, S. C. Satapathy, S. Wang, and Y. Zhang, "LCCNN: a lightweight customized CNN-based distance education app for COVID-19 recognition," Mobile Networks and Applications, pp. 1-16, 2023.
20) Cengel, T. A., Gencturk, B., Yasin, E. T., Yildiz, M. B., Cinar, I., & Koklu, M. (2024). Apple (Malus domestica) Quality Evaluation Based on Analysis of Features Using Machine Learning Techniques. Applied Fruit Science, 1-11.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ghazwan Hani Hussien, Ahmed Khalaf Zager Alsaedi, Abdul Hakim Moawia Dreheeb (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
