danДоклады Национальной академии наук БеларусиDoklady of the National Academy of Sciences of Belarus1561-83232524-2431The Republican Unitary Enterprise Publishing House "Belaruskaya Navuka"10.29235/1561-8323-2025-69-2-168-176dan-1249Research ArticleАГРАРНЫЕ НАУКИAGRARIAN SCIENCESИдентификация дефектов в клубнях картофеля для автоматизации процесса их сортировкиIdentification methods of defects in potato tubers to automate the process of their sortinghttps://orcid.org/0000-0003-2122-3281АзаренкоВ. В.AzarenkoV. V.

Азаренко Владимир Витальевич – член-корреспондент, д-р техн. наук, доцент, академик-секретарь

пр. Независимости, 66, 220072, Минск

Azarenko Vladimir V. – Corresponding Member, D. Sc. (Engineering), Associate Professor, Academic Secretary

66, Nezavisimosti Ave., 220072, Minsk

azarenko@presidium.basnet.byКуриловичМ. И.KurylovichM. I.

Курилович Максим Игоревич – науч. сотрудник

ул. Кнорина, 1, 220049, Минск

Kurylovich Maksim I. – Researcher

1, Knorin Str., 220049, Minsk

labpotato@mail.ruГолдыбанВ. В.GoldybanV. V.

Голдыбан Виктор Владимирович – заведующий лабораторией

ул. Кнорина, 1, 220049, Минск

Goldyban Viktor V. – Head of the Laboratory

1, Knorin Str., 220049, Minsk

labpotato@mail.ruОтделение аграрных наук Национальной академии наук БеларусиDepartment of Agrarian Sciences of the National Academy of Sciences of BelarusНаучно-практический центр Национальной академии наук Беларуси по механизации сельского хозяйстваScientific and Practical Center of the National Academy of Sciences of Belarus for Agricultural Mechanization202506052025692168176Copyright © Азаренко В.В., Курилович М.И., Голдыбан В.В., 20252025Азаренко В.В., Курилович М.И., Голдыбан В.В.Azarenko V.V., Kurylovich M.I., Goldyban V.V.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://doklady.belnauka.by/jour/article/view/1249

Предложен и описан способ идентификации и отделения некондиционных клубней картофеля из общего вороха на основе систем технического зрения и автоматической инспекции. Для сегментации внешних дефектов клубней картофеля на фоне транспортирующего конвейера в режиме реального времени использован метод, основанный на вычислении цветового порога. Для трекинга движущихся клубней картофеля использовался алгоритм центроидного трекинга. Для обучения искусственной нейронной сети был создан собственный набор данных, состоящий из изображений товарных и дефектных клубней картофеля. Представлены результаты экспериментальных исследований определения внутренних дефектов клубней картофеля с помощью метода ядерного магнитного резонанса (ЯМР) и компьютерной томографии (КТ). Для создания скрытых дефектов в виде потемнений мякоти клубней был использован метод регулируемого удара о твердую поверхность. Описана методика проведения экспериментальных исследований и режимные параметры ЯМР и КТ. Проведен сравнительный анализ изображений, полученных при помощи ЯМР и КТ, с натурными снимками клубней в разрезе, что позволило с высокой точностью определить совпадение местоположения дефектов, выявленных неинвазивным методом с их реальным расположением в клубне. Работа продемонстрировала ценность ЯМР и КТ для детального неинвазивного способа определения скрытых дефектов клубней картофеля на автоматических сортировальных машинах. 

A method for identifying and separating substandard potato tubers from a common pile based on machine vision and automatic inspection systems is proposed and described. A method based on calculating the color threshold is used for segmenting external defects of potato tubers against the background of a transport conveyor in real time. A centroid tracking algorithm is used to track moving potato tubers. A proprietary dataset consisting of images of commercial and defective potato tubers is created to train the artificial neural network. The results of experimental studies of determining internal defects of potato tubers using nuclear magnetic resonance (NMR) and computed tomography (CT) are presented.

A method of controlled impact on a hard surface is used to create hidden defects in the form of darkening of the tuber pulp. The methodology for conducting experimental studies and the operating parameters of NMR and CT are described. A comparative analysis of images obtained using NMR and CT with natural images of tubers in section was carried out, which made it possible to determine with high accuracy the coincidence of the location of defects detected by a non-invasive method with their real location in the tuber. The work demonstrated the value of NMR and CT for a detailed non-invasive method for determining hidden defects of potato tubers on automatic sorting machines.

клубни картофелясортировкавнутренние дефектывнешние дефектыискусственная нейронная сетьядерный магнитный резонансТ2 релаксацияnuclear magnetic resonanceinternal defectsexternal defectsartificial neural networkwirewormdeep processing of potatoesReferencesHigh speed potato grading and quality inspection based on a color vision system / J. C. Noordam, G. W. Otten, A. J. M. Timmermans, B. H. van Zwol // Control Systems. – 2017. – P. 15–24.Noordam J. C., Otten G. W., Timmermans A. J. M., van Zwol B. H. High speed potato grading and quality inspection based on a color vision system. Control Systems, 2017, pp. 15–24.Golmohammadi, A. Design, development and evaluation of an online potato sorting system using machine vision / A. Golmohammadi, F. Bejaei, H. Behfar // International Journal of Agriculture and Crop Sciences. – 2013. – Vol. 6, N 7. – P. 396–402.Golmohammadi A., Bejaei F., Behfar H. Design, development and evaluation of an online potato sorting system using machine vision. International Journal of Agriculture and Crop Sciences, 2013, vol. 6, no. 7, pp. 396–402.Caprara, C. Image analysis implementation for evaluation of external potato damage / C. Caprara, R. Martelli // Applied Mathematical Sciences. – 2015. – Vol. 9, N 81. – P. 4029–4041. https://doi.org/10.12988/ams.2015.52170Caprara C., Martelli R. Image analysis implementation for evaluation of external potato damage. Applied Mathematical Sciences, 2015, vol. 9, no. 81, pp. 4029–4041. https://doi.org/10.12988/ams.2015.52170Tavakoli, M. Application of the image processing technique for sepa-rating sprouted potatoes in the sorting line / M. Tavakoli, N. Mohsen // Journal of Applied Environmental and Biological Sciences. – 2015. – Vol. 4, N 11S. – P. 223–227.Tavakoli M., Mohsen N. Application of the image processing technique for sepa-rating sprouted pota-toes in the sorting line. Journal of Applied Environmental and Biological Sciences, 2015, vol. 4, no. 11S, pp. 223–227.Comparison of X-ray CT and MRI of watercore disorder of different apple cultivars / E. Herremans, A. Melado-Herreros, T. Defraeye [et al.] // Postharvest Biology and Technology. – 2014. – Vol. 87. – P. 42–50. https://doi.org/10.1016/j.postharvbio.2013.08.008Herremans E., Melado-Herreros A., Defraeye T., Verlinden B., Hertog M., Verboven P., Val J., Fernández-Valle M. E., Bongaers E., Estrade P., Wevers M., Barreiro P., Nicolai B. M. Comparison of X-ray CT and MRI of watercore disorder of different apple cultivars. Postharvest Biology and Technology, 2014, vol. 87, pp. 42–50. https://doi.org/10.1016/j.postharvbio.2013.08.008Томография в почвоведении: от первых опытов к современным методам (обзор) / К. Н. Абросимов, К. М. Герке, Д. С. Фомин [и др.] // Почвоведение. – 2021. – Т. 55, № 9. – С. 1097–1112.Abrosimov K. N., Fomin D. S., Romanenko K. A., Korost D. V., Gerke K. M. Tomography in soil science: from the first experiments to modern methods (a review). Eurasian Soil Science, 2021, vol. 54, no. 9, pp. 1385–1399. https://doi.org/10.1134/s1064229321090027Petrovic, A. M. Soil bulk density analysis in three dimensions by computed tomographic scanning / A. M. Petrovic, J. E. Siebert, P. E. Rieke // Soil Science Society of America Journal. – 1982. – Vol. 46, N 3. – P. 445–450. https://doi.org/10.2136/sssaj1982.03615995004600030001xPetrovic A. M., Siebert J. E., Rieke P. E. Soil bulk density analysis in three dimensions by computed tomographic scanning. Soil Science Society of America Journal, 1982, vol. 46, no. 3, pp. 445–450. https://doi.org/10.2136/sssaj1982.03615995004600030001xA non-destructive method for the morphological assessment of earthworm burrow systems in three dimensions by X-ray computed tomography / M. Joschko, O. Graff, P. C. Muller [et al.] // Biology and Fertility of Soils. – 1991. – Vol. 11. – P. 88–92. https://doi.org/10.1007/bf00336369Joschko M., Graff O., Muller P.C., Kotzke K., Lindner P., Pretschner D. P., Larink O. A non-destructive method for the morphological assessment of earthworm burrow systems in three dimensions by X-ray computed tomography. Biology and Fertility of Soils, 1991, vol. 11, рр. 88–92. https://doi.org/10.1007/bf00336369Crestana, S. Water physics study on soil using computerized tomography (in Portuguese): Ph. D. Thesis / S. Crestana. – Säo Paulo, 1985. – 151 p.Crestana S. Water physics study on soil using computerized tomography (in Portuguese) [Ph. D. Thesis]. Säo Paulo, 1985. 151 p.Hainsworth, J. M. The use of computed assisted tomography to determine spatial distribution of soil water content / J. M. Hainsworth, L. A. G. Aylmore // Australian Journal of Soil Research. – 1983. – Vol. 21, N 4. – P. 435–443. https://doi.org/10.1071/sr9830435Hainsworth J. M., Aylmore L. A. G. The use of computed assisted tomography to determine spatial distribution of soil water content. Australian Journal of Soil Research, 1983, vol. 21, no. 4, pp. 435–443. https://doi.org/10.1071/sr9830435Microstructure analysis and detection of mealiness in ‘Forelle’ pear (Pyrus communis L.) by means of X-ray computed tomography / T. Muziri, K. I. Theron, D. Cantre [et al.] // Postharvest Biology and Technology. – 2016. – Vol. 120. – P. 145–156. https://doi.org/10.1016/j.postharvbio.2016.06.006Muziri T., Theron K. I., Cantre D., Wang Z., Verboven P., Nicolai B. M., Crouch E. M. Microstructure analysis and detection of mealiness in ‘Forelle’ pear (Pyrus communis L.) by means of X-ray computed tomography. Postharvest Biology and Technology, 2016, vol. 120, pp. 145–156. https://doi.org/10.1016/j.postharvbio.2016.06.006MRI and X-ray CT study of spatial distribution of core breakdown in ‘Conference’ pears / J. Lammertyn, T. Dresselaers, P. Van Hecke [et al.] // Magnetic Resonance Imaging. – 2003. – Vol. 21, N 7. – P. 805–815. https://doi.org/10.1016/s0730725x(03)00105-xLammertyn J., Dresselaers T., Van Hecke P., Jancsók P., Wevers M., Nicolaï B. M. MRI and X-ray CT study of spatial distribution of core breakdown in ‘Conference’ pears. Magnetic Resonance Imaging, 2003, vol. 21, no. 7, pp. 805–815. https://doi.org/10.1016/s0730-725x(03)00105-xCharacterization of the 3-D microstructure of mango (Mangifera indica L. cv. Carabao) during ripening using X-ray computed microtomography / D. Cantre, E. Herremans, P. Verboven [et al.] // Innovative Food Science and Emerging Technologies. – 2014. – Vol. 24. – P. 28–39. https://doi.org/10.1016/j.ifset.2013.12.008Cantre D., Herremans E., Verboven P., Ampofo-Asiama J., Nicolaï B. Characterization of the 3-D microstructure of mango (Mangifera indica L. cv. Carabao) during ripening using X-ray computed microtomography. Innovative Food Science and Emerging Technologies, 2014, vol. 24, pp. 28–39. https://doi.org/10.1016/j.ifset.2013.12.008Multifractal properties of pore-size distribution in apple tissue using X-ray imaging / F. Mendoza, P. Verboven, Q. Tri Ho [et al.] // Journal of Food Engineering, – 2010. – Vol. 99, N 2. – P. 206–215. https://doi.org/10.1016/j.jfoodeng.2010.02.021Mendoza F., Verboven P., Tri Ho Q., Kerckhofs G., Wevers M., Nicolaï B. Multifractal properties of pore-size distribution in apple tissue using X-ray imaging. Journal of Food Engineering, 2010, vol. 99, no. 2, pp. 206–215. https://doi.org/10.1016/j.jfoodeng.2010.02.021

The authors declare that there are no conflicts of interest present.