10.14489/td.2025.09.pp.043-054

2025, 09 September

DOI: 10.14489/td.2025.09.pp.043-054

Platov Yu. T., Lysenkova A. A., Zelentsov S. V., Rassulov V. A., Beletsky S. L., Platova R. A.
NON-DESTRUCTIVE TESTING FOR DETECTION OF HIDDEN DEFECTS IN SOYBEAN SEEDS USING DIGITAL RADIOGRAPHY AND MACHINE LEARNING TECHNIQUES
(pp. 43-54)

Abstract. Non-destructive testing technology is a priority area of research in the field of quality monitoring of food products, including oilseeds. Detection and evaluation of hidden (internal) defects of seeds, including seedling bacteriosis, plays an important role at all stages of the life cycle. The object of the study was soybean seeds of Irbis variety of 2024 harvest. The quality assessment was carried out visually by defects of appearance, their X-ray image and seed germination test. A methodical approach of analysing digital X-ray images in terms of brightness by machine learning methods was proposed. A classification model of soybean seeds based on the brightness of X-ray images is constructed by principal component analysis (PCA) and principal component discriminant analysis (PCA-LDA) methods. The accuracy of the classification model of soybean seeds belonging to one of the quality categories was 87.5 %. It is shown that method of microfocus radiography is effective digital tools both for operative detection of hidden defects in the internal structure of seeds and for designing the technology of soybean seeds separation.

Keywords: non-destructive quality control methods, soya seeds, seed defects, microfocal X-ray radiography, classification model, method of principal components, discriminant analysis.

+ - About the Authors Click to collapse

Yu. T. Platov, A. A. Lysenkova (Russian University of Economics, Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
S. V. Zelentsov (V. S. Pustovoit All-Russian Research Institute of Oil Crops, Krasnodar, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
V. A. Rassulov (All-Russian Scientific-Research Institute of Mineral Resources named after N. M. Fedorovsky, Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. S. L. Beletsky (V. M. Gorbatov Federal Research Center for Food Systems of Russian Academy of Sciences, Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
R. A. Platova (Russian University of Economics, Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

+ - References Click to collapse

1. Coradi, P. C., Muller, A., Souza, G. A., Steinhaus, J. I., & Wagner, R. (2020). Quality of soybean cultivars in the drying and storage processes in real scale and experimental. Journal of Food Process Engineering, 43, 1–10.
2. Ramos, A. H., Timm, N. D. S., Ferreira, C. D., & de Oliveira, M. (2021). Effects of the intensification of soybean defects: Consequences on the physicochemical, technological, protein and oil properties. European Food Research and Technology, (247), 1277–1289.
3. Zelentsov, S. V., Saenko, G. M., Moshnenko, E. V., & Budnikov, E. N. (2021). The primary cause for the development of bacterial blight of seeds in soybean and other leguminous crops. Oil Crops, (1), 73–89. [in Russian language]
4. Chen, X., He, W., Ye, Z., Gai, J., Lu, W., & Xing, G. (2024). Soybean seed pest damage detection method based on spatial frequency domain imaging combined with RL-SVM. Plant Methods, 20(1), 130.
5. Rahman, A., & Cho, B.-K. (2016). Assessment of seed quality using non-destructive measurement techniques: A review. Seed Science Research, 26(4), 285–305.
6. Tu, K., Wen, S., Xu, Y., He, H., Li, H., Xu, R., & Sun, Q. (2024). Non-destructive detection strategy of maize seed vigor based on seed phenotyping and the potential for accelerating breeding. Journal of Advanced Research.
7. Çiftci, B., Çetin, N., Günaydın, S., & Kaplan, M. (2025). Machine learning approaches for binary classification of sorghum (Sorghum bicolor L.) seeds from image color features. Journal of Food Composition and Analysis, 140, 107208.
8. Saputri, D. A. S., Pahlawan, M. F. R., Murti, B. M., & Masithoh, R. E. (2022). Vis/NIR spectroscopy for non-destructive method in detecting soybean seeds viability. IOP Conference Series: Earth and Environmental Science, 1038(1), 012043.
9. Jitanan, S., & Chimlek, P. (2019). Quality grading of soybean seeds using image analysis. International Journal of Electrical and Computer Engineering, 9(5), 3495–3503.
10. Liu, W., Liu, Y., Hong, F., Li, J., Jiang, Q., Kong, L., & Zheng, L. (2025). Identification of varieties of wheat seeds based on multispectral imaging combined with improved YOLOv5. Food Physics, 2, 100042.
11. Zhao, G., Xu, Z., Tang, L., Li, X., Zhang, P., & Wang, Q. (2024). A rapid classification method for sorghum seed varieties based on HSI and PCA-SICNN algorithm. Microchemical Journal, 205, 111095.
12. Fu, J., Yuan, H., Zhao, R., Chen, Z., & Ren, L. (2020). Peeling damage recognition method for corn ear harvest using RGB image. Applied Sciences, 10(10), 3371.
13. Lee, H., Cho, B. K., Kim, M. S., Lee, W. H., Tewari, J., Bae, H., & Chi, H. Y. (2013). Prediction of crude protein and oil content of soybeans using Raman spectroscopy. Sensors and Actuators B: Chemical, 185, 694–700.
14. Li, W., Tan, F., Cui, J., & Ma, B. (2022). Fast identification of soybean varieties using Raman spectroscopy. Vibrational Spectroscopy, 123, 103447.
15. Gong, Y., Yu, L., Liu, Y., Zhao, W., Peng, W., Nie, X., & Ge, H. (2023). Non-destructive detection method for wheat freshness degree based on delayed luminescence. Journal of Cereal Science, 113(103748).
16. Arkhipov, M. V. (2024). Operational control of grain quality according to indicators of hidden grain integrity. Research Papers on Agronomy, (2), 5–17. [in Russian language]
17. Platov, Y. T., Beletskii, S. L., Metlenkin, D. A., Platova, R. A., Vereshchagin, A. L., & Marin, V. A. (2024). Identification and classification of buckwheat grain by microfocus radiography and hyperspectral imaging methods. Russian Journal of Nondestructive Testing, 60(4), 446–454.
18. Musaev, F. B., & Beletskiy, S. L. (2021). History and prospects for the application of X-ray diffraction analysis in seed breeding and seed study. Journal of the Russian Universities. Radioelectronics, 24(6), 6–15.
19. Antonov, R. Yu. (2023). Study of wheat grain structure by digital radiography. Radioelectronics and Communications Systems, 26(6), 103–112. [in Russian language]
20. Arkhipov, M. V., Priyatkin, N. S., Gusakova, L. P., Karamysheva, A. V., Trofimuk, L. P., Potrakhov, N. N., & Shchukina, P. A. (2020). Microfocus x-ray method for detecting hidden defects in seeds of woody forest species and other types of vascular plants. Technical Physics, (65), 324–332.
21. Nikolskiy, М. А., Tkachenko, K. G., Gryaznov, А. Yu., Staroverov, N. E., Kholopova, Е. D., & Klonov, V. A. (2017). Using x-ray separator with direct image increase for seed latent defects` identification. Advances in Current Natural Sciences, (10), 41–47. [in Russian language]
22. Schoeman, L., Williams, P., du Plessis, A., & Manley, M. (2016). X-ray micro-computed tomography (μCT) for non-destructive characterisation of food microstructure. Trends in Food Science & Technology, 47, 10–24.
23. Indore, N. S., Karunakaran, C., Jayas, D. S., Stobbs, J., Vu, M., Tu, K., & Marinos, O. (2024). Characterization of spring and durum wheat using non-destructive synchrotron phase contrast X-ray microtomography during storage. npj Science of Food, 8(1), 29.
24. Paziuk, B., Jayasinghe, M., & Erkinbaev, C. (2024). Non-destructive three-dimensional characterization of micronized pulse seeds using X-ray microcomputed tomography. Applied Food Research, 4(1), 100394.
25. França-Silva, F., Gomes-Junior, F. G., Rego, C. H. Q., Marassi, A. G., & Tannús, A. (2023). Advances in imaging technologies for soybean seed analysis. Journal of Seed Science, (45), e202345022.
26. Gargiulo, L., Leonarduzzi, C., & Mele, G. (2020). Micro-CT imaging of tomato seeds: Predictive potential of 3D morphometry on germination. Biosystems Engineering, 200, 112–122.
27. Pessoa, H. P., Copati, M. G. F., Azevedo, A. M., Dariva, F. D., Almeida, G. Q. D., & Gomes, C. N. (2023). Combining deep learning and X-ray imaging technology to assess tomato seed quality. Scientia Agricola, 80, e20220121.
28. Van De Looverbosch, T., Vandenbussche, B., Verboven, P., & Nicolaï, B. (2020). Nondestructive high-throughput sugar beet fruit analysis using X-ray CT and deep learning. Computers and Electronics in Agriculture, 200, 107228.
29. Gargiulo, L., Sorrentino, G., & Mele, G. (2020). 3D imaging of bean seeds: Correlations between hilum region structures and hydration kinetics. Food Research International, 134, 109211.
30. Guelpa, A., du Plessis, A., & Manley, M. (2016). A high-throughput X-ray micro-computed tomography (μCT) approach for measuring single kernel maize (Zea mays L.) volumes and densities. Journal of Cereal Science, 69, 321–328.
31. Singh, S. K., Jha, R., Pandey, S., Mohan, C., Ghosh, S., Singh, S. K., & Singh, A. (2025). Artificial Intelligence-based Tools for Next-Generation Seed Quality Analysis. Crop Design, 100094.
32. Liu, F., Yang, R., Chen, R., Guindo, M. L., He, Y., Zhou, J., & Kong, W. (2024). Digital techniques and trends for seed phenotyping using optical sensors. Journal of Advanced Research, 63, 1–16.
33. Arkhipov, M. V., Priyatkin, N. S., Gusakova, L. P., Karamysheva, A. V., Trofimuk, L. P., Potrakhov, N. N., Bessonov, V. B., & Shchukina, P. A. (2023). Microfocus x-ray method for detecting hidden defects in seeds of woody forest species and other types of vascular plants. Technical Physics, 90(2), 338–346. [in Russian language]
34. Shchukina, P. A., Arkhipov, M. V., Gusakova, L. P., & Priyatkin, N. S. (2020). Technique of digital x-ray seed images preparation for visual image interpretation. Agrophysics, (3), 36–44. [in Russian language]
35. Musaev, F. B., Potrakhov, N. N., & Arkhipov, M. V. (2016). X-ray analysis of vegetable seeds. St. Petersburg State Electrotechnical University named after V.I. Ulyanov (Lenin). [in Russian language]
36. Dagher, I. (2010). Incremental PCA-LDA algorithm. 2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, 97–101.
37. Zelentsov, S., Saenko, G., & Moshnenko, E. (2022). Primary cause of cotyledonous bacterial blight on soybean. BIO Web of Conferences, 43, 02014.

+ - Purchase digital version of a single article Click to collapse

This article is available in electronic format (PDF).

The cost of a single article is 700 rubles. (including VAT 20%). After you place an order within a few days, you will receive following documents to your specified e-mail: account on payment and receipt to pay in the bank.

After depositing your payment on our bank account we send you file of the article by e-mail.

To order articles please copy the article doi:

10.14489/td.2025.09.pp.043-054

and fill out the form