Method for automated assessment of the effectiveness of means to improve fruit safety using an acousto-optical imaging spectrometer

Batashova S.S., Zolotukhina A.А., Guryleva, A.V., Platonova N.B., Kunina V.A.

For Russian citation (Opticheskii Zhurnal):

Баташова С.С., Золотухина А.А., Гурылева А.В., Платонова Н.В., Кунина В.А. Метод автоматизированной оценки эффективности средств повышения сохранности плодов с помощью акустооптического видеоспектрометра // Оптический журнал. 2024. Т. 91. № 7. С. 25–36. http://doi.org/10.17586/1023-5086-2024-91-07-25-36

Batashova S.S., Zolotukhina A.A., Guryleva A.V., Platonova N.B., Kunina V.A. Method for automated assessment of the effectiveness of means to improve fruit safety using an acousto-optical imaging spectrometer [in Russian] // Opticheskii Zhurnal. 2024. V. 91. № 7. P. 25–36. http://doi.org/10.17586/1023-5086-2024-91-07-25-36

For citation (Journal of Optical Technology):

Abstract:

Subject of study. Registration, processing and interpretation methods and algorithms for spectral images aimed at evaluating surface defects in fruits. Aim of study. Development of a method for assessing fruit preservation techniques based on automatic detection and quantitative evaluation of their surface defects using imaging spectroscopy. Method. Spectral images were acquired using an acousto-optical imaging spectrometer with a spectral range of 450–850 nm (bandwidth of 2.5 nm at wavelength 650 nm) with a 5 nm step. For processing spectral images, well-established operations and algorithms for data enhancement and analysis were employed. This included correction for uneven illumination, correction for spatial and spectral inhomogeneity of the optical system’s transmittance coefficient, various image filtering techniques, threshold binarization, object classification based on spectral features. The proposed approach was tested in an experimental study evaluating the effectiveness of peaches and nectarines preservation techniques using a treatment inhibiting ethylene production. Main results. A methodology for registering and processing spectral images have been developed. This enables the automated detection and quantitative characterization of surface defects on fruits. An evaluative parameter has been introduced, defined as the ratio of the defect area to the total surface area of the fruit, allowing for the comparison of different experimental conditions. The testing of the approach demonstrated the possibility of automated determination of the fetal defect size with a relative error of 11%. Practical significance. The developed data processing algorithms enable regular diagnostics of samples and the identification of defects at early stages. The methodology for registering and processing data can be extended to devices based on other physical principles for obtaining the spatial distribution of spectral characteristics of objects. The developed solution is suitable for complementing existing methods for assessing fruit preservation techniques and contributes to the integration of imaging spectrometers into the routine practice of the agro-industrial complex.

Keywords:

imaging spectroscopy, spectral images, digital processing, reflection spectrum, classification, non-invasive analysis, acousto-optics, fruit crops, fruit preservation technologies, peaches, nectarines

Acknowledgements:

in the development of the storage experiment scheme and sample preparation, this publication was prepared as part of the implementation of the state task of the Federal Scientific Center for Research and Development of the Russian Academy of Sciences (FGRW-2022-0014, registration № 123013100006-9). Regarding the development of methods for registering and processing spectral images, interpreting and statistically processing data, this study received support from the Federal State Task Program by Scientific and Technological Center of Unique Instrumentation of the Russian Academy of Sciences (FFNS 2022 0010).

OCIS codes: 110.2970, 330.6180

References:

1.   Dristi D., Manoranjan P., Manzur M., et al. Comparative analysis of machine and deep learning models for soil properties prediction from hyperspectral visual band // Environments. 2023. V. 10. № 5. P. 77. https://doi.org/10.3390/environments10050077.
2.   Soucy N., Sekeh S.Y. CEU-Net: Esemble semantic segmentation of hyperspectral images using clustering // J. Big Data. 2023. V. 10. № 1. P. 42. https://doi.org/10.1186/s40537-023-00718-3
3.   van Vliet-Perez S.M., van de Berg N.J., Manni F., et al. Hyperspectral imaging for tissue classification after advanced stage ovarian cancer surgery — a pilot study // Cancers. 2022. V. 14. № 6. P. 1422. https://doi.org/10.3390/cancers14061422
4.   Jong L.S., de Kruif N., Geldof F., et al. Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging // Biomed. Opt. Exp. 2022. V. 13. № 5. P. 2581–2604. https://doi.org/10.1364/BOE.455208
5.   Singh T., Garg N.M., Iyengar S.R.S. Nondestructive identification of barley seeds variety using near-infrared hyperspectral imaging coupled with convolutional neural network // J. Food Process Eng. 2021. V. 44. № 10. P. e13821. https://doi.org/10.1111/jfpe.13821
6.   Garini Y., Young I.T., McNamara G. Spectral imaging: Principles and applications // Cytometry Part A. 2006. V. 69A. № 8. P. 735–747. https://doi.org/10.1002/cyto.a.20311
7.   Fan S., Huang W., Guo Z., et al. Prediction of soluble solids content and firmness of pears using hyperspectral reflectance imaging // Food Analytical Methods. 2015. V. 8. № 8. P. 1936–1946. https://doi.org/10.1007/s12161-014-0079-1
8.   Juhnevica-Radenkova K., Radenkovs V., Kundzins K., Seglina D. Effect of ozone treatment on the microstructure, chemical composition and sensory quality of apple fruits // Food Sci. and Technol. Internat. 2019. V. 25. № 3. P. 252–267. https://doi.org/10.1177/1082013218815285
9.   Li J., Chen L., Huang W., et al. Multispectral detection of skin defects of bi-colored peaches based on vis — NIR hyperspectral imaging // Postharvest Biol. Technol. 2016. V. 112. P. 121–133. https://doi.org/10.1016/j.postharvbio.2015.10.007
10.   Manley M. Near-infrared spectroscopy and hyperspectral imaging: Non-destructive analysis of biological materials // Chem. Soc. Rev. 2014. V. 43. № 24. P. 8200–8214. https://doi.org/10.1039/c4cs00062e
11.   ElMasry G., Wang N., Vigneault C. Detecting chilling injury in Red Delicious apple using hyperspectral imaging and neural networks // Postharvest Biol. Technol. 2009. V. 52. № 1. P. 1–8. https://doi.org/10.1016/j.postharvbio.2008.11.008
12.   Molto E., Blasco J., Gomez-Sanchis J. Analysis of hyperspectral images of citrus fruits // Hyperspectral Imaging for Food Quality Analysis and Control. 2010. P. 321–348. https://doi.org/10.1016/b978-0-12-374753-2.10010-3
13.   Polder G., van der Heijden G. Measuring ripening of tomatoes using imaging spectrometry // Hyperspectral Imaging for Food Quality Analysis and Control. 2010. P. 369–402. https://doi.org/10.1016/B978-0-12-374753-2.10012-7
14.   Qin J., Lu R. Measurement of the optical properties of fruits and vegetables using spatially resolved hyperspectral diffuse reflectance imaging technique // Postharvest Biol. Technol. 2008. V. 49. № 3. P. 355–365. https://doi.org/10.1016/j.postharvbio.2008.03.010
15.   Shang M., Xue L., Zhan Y., et al. Full-surface defect detection of navel orange based on hyperspectral online sorting technology // J. Food Sci. 2023. V. 88. № 6. P. 2488–2495. https://doi.org/10.1111/1750-3841.16569
16.   Балабанов П.В., Жиркова А.А., Дивин А.Г. и др. Информационно-измерительная система для управления процессом сортировки овощей и фруктов // Вестник тамбовского государственного технического университета. 2022. Т. 28. № 4. С. 526–533. https://doi.org/10.17277/vestnik.2022.04.pp.526-533
   Balabanov P.V., Zhirkova A.A., Divin A.G., et al. An information-measuring system to monitor vegetable and fruit sorting process [in Russian] // Bulletin of the Tambov State Technical University. 2022. V. 28. № 4. P. 526–533. https://doi.org/10.17277/vestnik.2022.04.pp.526-533
17.   Егорович С.Н. Температурный режим и продуктивность сортов персика во влажных субтропиках России // Новые технологии. 2018. Т. 13. № 4. С. 230–235.
   Egorovich S.N. Temperature regime and productivity of peach varieties in humid subtropics of Russia [in Russian] // New Technologies. 2018. V. 13. № 4. P. 230–235.
18.   Причко Т.Г. Регулирование качества плодов при выращивании, уборке, хранении и переработке // Садоводство и виноградарство. 2004. № 6. С. 2–4.
   Prichko T.G. Regulation of fruit quality during cultivation, harvesting, storage and processing [in Russian] // Horticulture and Viticulture. 2004. № 6. P. 2–4.
19.   Zanella A. Control of apple superficial scald and ripening — a comparison between 1-methylcyclopropene and diphenylamine postharvest treatments, initial low oxygen stress and ultra-low oxygen storage // Postharvest Biol. Technol. 2003. V. 27. № 1. P. 69–78. https://doi.org/10.1016/S0925-5214(02)00187-4
20.   Першакова Т.В., Лисовой В.В., Купин Г.А. и др. Способы обеспечения стабильного качества растительного сырья в процессе хранения // Политематический сетевой электронный научный журнал Кубанского государственного аграрного университета. 2016. Т. 116. № 2. С. 205–217.
   Pershakova T.V., Lisovoy V.V., Kupin G.A. et al. Methods of ensuring stable quality of plant raw materials during storage [in Russian] // Polythematic Online Scientific Journal of Kuban State Agrarian University. 2016. V. 116. № 2. P. 205–217.
21.   Уайлд Г., Парадовский А. Коммерческое использование технологии применения ингибитора этилена (1-МСР) за последние 8 лет в США // Тез. докл. междунар. научно-практической конф. — Высокоточные технологии производства, хранения и переработки плодов и ягод. Краснодар, Россия. 07–10 сентября 2010. С. 330–336.
   Wild G., Paradovsky A. Commercial use of ethylene inhibitor (1-MCP) technology in the USA: High-precision technologies for the production, storage and processing of fruits and berries [in Russian] // Internat. Scientific and Practical Conf. — High-precision Technologies for the Production, Storage and Processing of Fruits and Berries (Abstracts of reports). Krasnodar, Russia. September 07–10, 2010. P. 330–336.
22.   Омарова З.М., Причко Т.Г., Омаров М.Д. и др. Особенности уборки, переработки и изменения, происходящие в плодах фейхоа (Acca sellowiana O. Berg) при хранении // Субтропическое и декоративное садоводство. 2023. № 86. С. 85–96. https://doi.org/10.31360/2225-3068-2023-86-85-96
   Omarova Z.M., Prichko T.G., Omarov M.D., et al. Features of harvesting, processing and changes occurring in feijoa fruits (Acca sellowiana O. Berg) during storage [in Russian] // Subtropical and Decorative Gardening. 2023. № 86. P. 85–96. https://doi.org/10.31360/2225-3068-2023-86-85-96
23.   Pozhar V., Gaponov M., Machikhin A., Shirokov S. Hyperspectral monitoring AOTF-based apparatus // J. Phys. Conf. Ser. 2019. V. 1368. № 2. P. 022046. https://doi.org/10.1088/1742-6596/1368/2/022046
24.   Мачихин А.С., Пожар В.Э., Батшев В.И. Акустооптический видеоспектрометрический модуль для медицинских эндоскопических исследований // Оптический журнал. 2013. Т. 80. № 7. С. 44–49.
   Machikhin A., Pozhar V., Batshev V. Acousto-optic video spectrometer module for medical endoscopic studies // J. Opt. Technol. 2013. V. 80. № 7. P. 439–443. https://doi.org/10.1364/JOT.80.000439
25.   Шарикова М.О., Баландин И.А., Батшев В.И., Козлов А.Б. Пространственно-спектральная коррекция акустооптического видеоспектрометра // Оптический журнал. 2023. Т. 90. № 11. С. 79–89. http://doi.org/10.17586/1023-5086-2023-90-11-79-89
   Sharikova М.O., Balandin I.A., Batshev V.I., Kozlov A.B. Spatial and spectral correction of acousto-optical videospectrometer // J. Opt. Technol. 2023. V. 90. № 11. P. 00–00. http://doi.org/10.1364/JOT.90.000000
26.   Shang M., Xue L., Zhang Y., et al. Full surface defect detection of spherical fruit based on hyperspectral online sorting technology // J. Food Sci. 2022. V. 88. № 6. P. 2488–2495. https://doi.org/10.1111/1750-3841.16569
27.   Anuar M.S.K., Asral J., Nasri S. A study of image processing using morphological opening and closing processes // Internat. J. Control Theory and Applications. 2016. V. 9. № 31. P. 15–21.
28.   Nidamanuri R.R., Zbell B. Normalized spectral similarity score (NS3) as an efficient spectral library searching method for hyperspectral image classification // IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 2011. V. 4. № 1. P. 226–240. https://doi.org/10.1109/JSTARS.2010.2086435