Soybean Seed Quality Classification using Magnitude-Enhanced Multiple Channel LBP and SVM

Adrian Chandra; Yohannes Yohannes

doi:10.29408/edumatic.v10i1.33519

Authors

Adrian Chandra Universitas Multi Data Palembang https://orcid.org/0009-0002-1568-839X
Yohannes Yohannes Universitas Multi Data Palembang https://orcid.org/0009-0009-3261-2611

DOI:

https://doi.org/10.29408/edumatic.v10i1.33519

Keywords:

magnitude information, multiple channel local binary pattern, quality classification, soybean seeds, support vector machine

Abstract

Soybean is a major source of plant-based protein The quality of soybean seed affects resulting food. Therefore, image processing for classifying soybean seed quality is needed. Previous studies mainly used handcrafted or deep learning features and not evaluated local texture representations that using magnitude information for multi-class problems with high visual similarity. Traditional texture descriptors such as LBP or GLCM mainly using sign-based or global statistics and have limitations in representing colour-texture variations. This study aims to classify soybean seed quality using SVM with Multiple Channel Local Binary Pattern (MCLBP) and its enhanced variant with magnitude information (MCLBP+M) for feature extraction by utilizing correlations between colour channels through multi-radius approach. The dataset used is Soybean Seeds includes five classes: intact, spotted, immature, broken, and skin-damaged. This research conduct dataset splitting using 10-fold cross validation, data balancing (SMOTE), feature extraction, SVM model training and testing, and performance evaluation. The results show that MCLBP+M with Lab colour space and RBF kernel achieves accuracy of 86.30%, precision of 86.32%, recall of 85.99%, and F1-score of 86.07%. The results show that magnitude information in MCLBP+M consistently stable and improves classification performance across colour spaces and kernels, making it suitable for soybean seed quality classification.

References

Alimoussa, M., Porebski, A., Vandenbroucke, N., El Fkihi, S., & Oulad Haj Thami, R. (2022). Compact Hybrid Multi-Color Space Descriptor Using Clustering-Based Feature Selection for Texture Classification. Journal of Imaging, 8(8). https://doi.org/10.3390/jimaging8080217

Baisch, J. S., Grohs, M., Ferreira, P. A. A., Ugalde, G. A., Tres, M. V., & Zabot, G. L. (2024). Protein and Oil Contents, Micro- and Macronutrients, and Other Quality Indicators of Soybean Cultivated in Lowland Fields. Foods, 13(23), 1–18. https://doi.org/10.3390/foods13233719

Balachandan, G. C., Jain, S. K., Joshi, M. A., & Singh, D. (2025). Effect of Seed Coat Characteristics on Seed Quality in Soybean [Glycine max (L) Merrill] Genotypes with Contrasting Seed Longevity Traits. Legume Research, 48(5), 787–792. https://doi.org/10.18805/LR-4987

Cañizares, L. da C. C., Gaioso, C. A., Timm, N. da S., Meza, S. L. R., Ramos, A. H., Oliveira, M. de, Lutz, É., & Elias, M. C. (2024). Influence of broken kernels content on soybean quality during storage. Grain and Oil Science and Technology, 7(2), 105–112. https://doi.org/10.1016/j.gaost.2024.03.002

Chauhan, D., Kumar, K., Ahmed, N., Thakur, P., Rizvi, Q. U. E. H., Jan, S., & Yadav, A. N. (2022). Impact of soaking, germination, fermentation, and roasting treatments on nutritional, anti-nutritional, and bioactive composition of black soybean (Glycine max L.). Journal of Applied Biology and Biotechnology, 10(5), 186-192. https://doi.org/10.7324/JABB.2022.100523

Çetin, N. (2022). Machine Learning for Varietal Binary Classification of Soybean (Glycine max (L.) Merrill) Seeds Based on Shape and Size Attributes. Springer Nature, 15, 2260–2273. https://doi.org/10.1007/s12161-022-02286-3

Chen, M., Chang, Z., Jin, C., Cheng, G., Wang, S., & Ni, Y. (2025). Classification and Recognition of Soybean Quality Based on Hyperspectral Imaging and Random Forest Methods. Sensors, 25(5). https://doi.org/10.3390/s25051539

Du, K. L., Jiang, B., Lu, J., Hua, J., & Swamy, M. N. S. (2024). Exploring Kernel Machines and Support Vector Machines: Principles, Techniques, and Future Directions. Mathematics, 12(24), 1–58. https://doi.org/10.3390/math12243935

Duan, Z., Li, Q., Wang, H., He, X., & Zhang, M. (2023). Genetic regulatory networks of soybean seed size, oil and protein contents. Frontiers in Plant Science, 14(March), 1–11. https://doi.org/10.3389/fpls.2023.1160418

Gulzar, Y. (2024). Enhancing soybean classification with modified inception model: A transfer learning approach. Emirates Journal of Food and Agriculture, 36, 1–9. https://doi.org/10.3897/ejfa.2024.122928

Guo, B., Sun, L., Jiang, S., Ren, H., Sun, R., Wei, Z., Hong, H., Luan, X., Wang, J., Wang, X., Xu, D., Li, W., Guo, C., & Qiu, L. J. (2022). Soybean genetic resources contributing to sustainable protein production. Theoretical and Applied Genetics, 135(11), 4095–4121. https://doi.org/10.1007/s00122-022-04222-9

Jin, C., Liu, S., & Chen, M. (2022). Semantic segmentation-based mechanized harvesting soybean quality detection. Science Progress, 105(2), 1–19. https://doi.org/10.1177/00368504221108518

Kudełka, W., Kowalska, M., & Popis, M. (2021). Quality of soybean products in terms of essential amino acids composition. Molecules, 26(16), 1–9. https://doi.org/10.3390/molecules26165071

Martignone, G. M. B., Ghosh, B., Papadas, D., & Behrendt, K. (2024). The rise of Soybean in international commodity markets: A quantile investigation. Heliyon, 10(15). https://doi.org/10.1016/j.heliyon.2024.e34669

Pereira, G. M. L., Foleis, J. H., De Souza Brito, A., & Bertolini, D. (2024). A Database for Soybean Seed Classification. Brazilian Symposium of Computer Graphic and Image Processing. https://doi.org/10.1109/SIBGRAPI62404.2024.10716268

Qin, P., Wang, T., & Luo, Y. (2022). A review on plant-based proteins from soybean: Health benefits and soy product development. Journal of Agriculture and Food Research, 7, 100265. https://doi.org/10.1016/j.jafr.2021.100265

Sable, A. V., Singh, P., & Kaur, A. (2024). Classification of Soybean Seed Using Support Vector Machine with Image Enhancement Techniques. Lecture Notes in Electrical Engineering, 1227. https://doi.org/10.1007/978-981-97-4657-6_21

Singer, W. M., Lee, Y. C., Shea, Z., Vieira, C. C., Lee, D., Li, X., ... & Zhang, B. (2023). Soybean genetics, genomics, and breeding for improving nutritional value and reducing antinutritional traits in food and feed. The Plant Genome, 16(4), e20415. https://doi.org/10.1002/tpg2.20415

Shu, X., Song, Z., Shi, J., Huang, S., & Wu, X. J. (2021). Multiple channels local binary pattern for color texture representation and classification. Signal Processing: Image Communication, 98(July), 116392. https://doi.org/10.1016/j.image.2021.116392

Toomer, O. T., Oviedo, E. O., Ali, M., Patino, D., Joseph, M., Frinsko, M., ... & Mian, R. (2023). Current agronomic practices, harvest & post-harvest processing of soybeans (Glycine max)—A review. Agronomy, 13(2), 427. https://doi.org/10.3390/agronomy13020427

van den Berg, L. A., Mes, J. J., Mensink, M., & Wanders, A. J. (2022). Protein quality of soy and the effect of processing: A quantitative review. Frontiers in Nutrition, 9, 1004754. https://doi.org/10.3389/fnut.2022.1004754

Wang, X., Sun, J., Yi, Z., & Dong, S. (2025). Effects of seed size on soybean performance: germination, growth, stress resistance, photosynthesis, and yield. BMC Plant Biology, 25(1). https://doi.org/10.1186/s12870-025-06224-3

Zhang, L., Jia, R., Liu, L., Shen, W., Fang, Z., Zhou, B., & Liu, B. (2023). Seed coat colour and structure are related to the seed dormancy and overwintering ability of crop-to-wild hybrid soybean. AoB PLANTS, 15(6), 1–10. https://doi.org/10.1093/aobpla/plad081

Zhao, Q., Zhang, Z., Huang, Y., & Fang, J. (2022). TPE-RBF-SVM Model for Soybean Categories Recognition in Selected Hyperspectral Bands Based on Extreme Gradient Boosting Feature Importance Values. Agriculture (Switzerland), 12(9). https://doi.org/10.3390/agriculture12091452