(49-3) 12 * << * >> * Russian * English * Content * All Issues

Seed purity assessment by means of spectral imaging
G.V. Nesterov 1,2, A.V. Guryleva 1, A.A. Zolotukhina 1,2, D.S. Fomin 2,3, D.S. Fomin 2,3, Y.K. Shashko 4, A.S. Machikhin 1,2

1 Scientific and Technological Centre of Unique Instrumentation of the Russian Academy of Sciences,
Butlerova Str. 15, Moscow, 117342, Russia;
2 PREDURALIE Ltd, Russia,
Room 1, Kultury Str. 12, Lobanovo, 614532, Perm municipal district, Perm Region, Russia;
3 Perm Federal Research Center, Ural Branch of the Russian Academy of Sciences, Russia,
Kultury Str. 12, Lobanovo, 614532, Perm Region, Russia;
4 Republican Scientific Subsidiary Unitary Enterprise "The Institute for Soil Science and Agrochemistry",
Kazinets Str. 90, Minsk, 220108, Republic of Belarus

 PDF, 1701 kB

DOI: 10.18287/2412-6179-CO-1512

Pages: 461-469.

Full text of article: Russian language.

Abstract:
In this work, we propose a technique for identifying impurity grains from spectral images using neural networks that is able to analyze a heap of seeds, grouping grains with similar spectral and morphological characteristics and optimizing the main stages of forming a training sample of a neural network model, recording and processing data. An architecture of the neural network model is proposed based on sequentially running LSTM layers and fully connected layers of neurons. Approaches are proposed for choosing the training sample size, the number and position of central wavelengths of video spectrometer channels used in analysis, and a method for segmenting spectral images to form a training sample. The developed methodology is distinguished by the ability to analyze a heap of seeds and the ease of replenishing the database of distinguished crops and impurities. Testing of the method on wheat and barley seeds showed high classification accuracy (over 99 %) even for grains with very similar spectral and morphological characteristics. The proposed approach increases the accuracy, productivity and objectivity of assessing the purity of seed material, does not require the involvement of experienced personnel and, thus, may be expected to facilitate the introduction of video spectrometers when addressing research and production problems of the agro-industrial complex.

Keywords:
videospectrometry, hyperspectral imaging, digital image processing, spectral characteristics, machine learning, LSTM neural network, seed material, agriculture.

Citation:
Nesterov GV, Guryleva AV, Zolotukhina AA, Fomin DS, Fomin DS, Shashko YK, Machikhin AS. Seeds purity assessment by means of spectral imaging. Computer Optics 2025; 49(3): 461-469. DOI: 10.18287/2412-6179-CO-1512.

Acknowledgements:
This research was funded by the Ministry of Education and Science of the Perm Region as part of the scientific project "Development of methodological, hardware and software tools for remote multispectral monitoring of agricultural lands" of 26 January, 2024, project #FC-26/40.

References:
  1. Zolotukhina A, Machikhin A, Guryleva A, Gresis V, Tedeeva V. Extraction of chlorophyll concentration maps from AOTF hyperspectral imagery. Front Environ Sci 2023; 11. Source:   <https://www.readcube.com/articles/10.3389/fenvs.2023.1152450>. DOI: 10.3389/fenvs.2023.1152450.
  2. Aboughaleb IH, Aref MH, El-Sharkawy YH. Hyperspectral imaging for diagnosis and detection of ex-vivo breast cancer. Photodiagnosis Photodyn Ther 2020; 31: 101922. DOI: 10.1016/j.pdpdt.2020.101922.
  3. Singh T, Garg NM, Iyengar SRS. Nondestructive identification of barley seeds variety using near-infrared hyperspectral imaging coupled with convolutional neural network. J Food Process Eng 2021; 44(10): e13821. DOI: 10.1111/jfpe.13821.
  4. Stuart MB, McGonigle AJS, Willmott JR. Hyperspectral imaging in environmental monitoring: A review of recent developments and technological advances in compact field deployable systems. Sensors 2019; 19(14): 3071. DOI: 10.3390/s19143071.
  5. Berman M, Connor PM, Whitbourn LB, Coward DA, Osborne BG, Southan MD. Classification of sound and stained wheat grains using visible and near infrared hyperspectral image analysis. J Near Infrared Spectrosc 2007; 15(6): 351-358. DOI: 10.1255/jnirs.754.
  6. GOST 13586.3-2015. Grain. Acceptance rules and sampling methods [In Russian]. Moscow: "IPK Izdateljstvo Standartov" Publisher; 2015.
  7. Zhu S, et al. Identification of soybean seed varieties based on hyperspectral imaging technology. Sensors 2019; 19(23): 5225. DOI: 10.3390/s19235225.
  8. Pang L, Men S, Yan L, Xiao J. Rapid vitality estimation and prediction of corn seeds based on spectra and images using deep learning and hyperspectral imaging techniques. IEEE Access 2020; 8: 123026-123036. DOI: 10.1109/ACCESS.2020.3006495.
  9. Feng X, Peng C, Chen Y, Liu X, Feng X, He Y. Discrimination of CRISPR/Cas9-induced mutants of rice seeds using near-infrared hyperspectral imaging. Sci Rep 2017; 7(1): 15934. DOI: 10.1038/s41598-017-16254-z.
  10. Que H, Zhao X, Sun X, Zhu Q, Huang M. Identication of wheat kernel varieties based on hyperspectral imaging technology and grouped convolutional neural network with feature intervals. Preprint from Research Square. 2022. Source: <https://europepmc.org/article/ppr/ppr542233>. DOI: 10.21203/rs.3.rs-1951327/v1.
  11. Zhang L, Sun H, Rao Z, Ji H. Non-destructive identification of slightly sprouted wheat kernels using hyperspectral data on both sides of wheat kernels. Biosyst Eng 2020; 200: 188-199. DOI: 10.1016/j.biosystemseng.2020.10.004.
  12. Sagan V, et al. Monitoring inland water quality using remote sensing: Potential and limitations of spectral indices, bio-optical simulations, machine learning, and cloud computing. Earth-Sci Rev 2020; 205: 103187. DOI: 10.1016/j.earscirev.2020.103187.
  13. Liu N, Guo Y, Jiang H, Yi W. Gastric cancer diagnosis using hyperspectral imaging with principal component analysis and spectral angle mapper. J Biomed Opt 2020; 25(6): 066005. DOI: 10.1117/1.jbo.25.6.066005.
  14. Hong Z, Zhang C, Kong D, Qi Z, He Y. Identification of storage years of black tea using near-infrared hyperspectral imaging with deep learning methods. Infrared Phys Technol 2021; 114: 103666. DOI: 10.1016/j.infrared.2021.103666.
  15. Andriyanov N, Kamalova Y, Dementiev V. Comparison of MS custom vision auto machine learning with algorithms implementation methods. 2023 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF) 2023: 1-4. DOI: 10.1109/WECONF57201.2023.10148043.
  16. de Oliveira S, Topsakal O, Toker O. Benchmarking automated machine learning (AutoML) frameworks for object detection. Information 2024; 15(1): 63. DOI: 10.3390/info15010063.
  17. Li KY, et al. Toward automated machine learning-based hyperspectral image analysis in crop yield and biomass estimation. Remote Sens 2022; 14(5): 1114. DOI: 10.3390/rs14051114.
  18. Zolotukhina A, et al. Evaluation of Leaf Chlorophyll Content from Acousto-Optic Hyperspectral Data: A Multi-Crop Study. Remote Sens 2024; 16(6): 1073. DOI: 10.3390/rs16061073.
  19. Zhao X, Pang L, Wang L, Men S, Yan L. Deep convolutional neural network for detection and prediction of waxy corn seed viability using hyperspectral reflectance imaging. Math Comput Appl 2022; 27(6): 109. DOI: 10.3390/mca27060109.
  20. Zhao Y, Zhang C, Zhu S, Gao P, Feng L, He Y. Non-destructive and rapid variety discrimination and visualization of single grape seed using near-infrared hyperspectral imaging technique and multivariate analysis. Molecules 2018; 23(6): 1352. DOI: 10.3390/molecules23061352.
  21. Xu P, et al. Identification of defective maize seeds using hyperspectral imaging combined with deep learning. Foods 2023; 12(1): 144. DOI: 10.3390/foods12010144.
  22. Zhao X, Pang L, Wang L, Men S, Yan L. Deep Convolutional Neural Network for Detection and Prediction of Waxy Corn Seed Viability Using Hyperspectral Reflectance Imaging. Math Comput Appl 2022; 27(6): 109. DOI: 10.3390/mca27060109.
  23. Zhang J, Feng X, Liu X, He Y. Identification of hybrid okra seeds based on near-infrared hyperspectral imaging technology. Appl Sci 2018; 8(10): 1793. DOI: 10.3390/app8101793.
  24. GOST 9353-2016. Wheat. Specifications [In Russian]. Moscow: "IPK Izdateljstvo Standartov" Publisher; 2016.
  25. Li H, Zhu J, Rao Z, Ji H. Identification of wheat seed varieties based on hyperspectral imaging technology and deep learning. 2024. Source: <https://ssrn.com/abstract=4425384>.
  26. Zhang L, Ji H. Identification of wheat grain in different states based on hyperspectral imaging technology. Spectrosc Lett 2019; 52(6): 356-366. DOI: 10.1080/00387010.2019.1639762.
  27. Zhang L, Sun H, Li H, Rao Z, Ji H. Identification of rice-weevil (Sitophilus oryzae L.) damaged wheat kernels using multi-angle NIR hyperspectral data. J Cereal Sci 2021; 101: 103313. DOI: 10.1016/j.jcs.2021.103313.
  28. Bao Y, Mi C, Wu N, Liu F, He Y. Rapid classification of wheat grain varieties using hyperspectral imaging and chemometrics. Appl Sci 2019; 9(19): 4119. DOI: 10.3390/app9194119.
  29. Zhang H, Hou Q, Luo B, Tu K, Zhao C, Sun Q. Detection of seed purity of hybrid wheat using reflectance and transmittance hyperspectral imaging technology. Front Plant Sci 2022; 13: 1015891. DOI: 10.3389/fpls.2022.1015891.
  30. Pozhar VE, Machikhin AS, Gaponov MI, Shirokov SV, Mazur MM, Sheryshev AE. AOTF based hyperspectrometer for UAV [In Russian]. Light & Engineering 2018; 4: 47-50.
  31. Katrašnik J, Pernuš F, Likar B. Radiometric calibration and noise estimation of acousto-optic tunable filter hyperspectral imaging systems. Appl Opt 2013; 52(15): 3526-3537. DOI: 10.1364/AO.52.003526.
  32. Stringer C, Wang T, Michaelos M, Pachitariu M. Cellpose: a generalist algorithm for cellular segmentation. Nat Methods 2021; 18(1): 100-106. DOI: 10.1038/s41592-020-01018-x.
  33. Bruce LM, Koger CH, Li J. Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction. IEEE Trans Geosci Remote Sens 2022; 40(10): 2331-2338. DOI: 10.1109/TGRS.2002.804721.
  34. Greenacre M, Groenen PJF, Hastie T, D’Enza AI, Markos A, Tuzhilina E. Principal component analysis. Nat Rev Methods Primers 2022; 2(1): 100. DOI: 10.1038/s43586-022-00184-w.
  35. Li H, Liang Y, Xu Q, Cao D. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Anal Chim Acta 2009; 648(1): 77-84. DOI: 10.1016/j.aca.2009.06.046.
  36. Maas AL, Hannun AY, Ng AY. Rectifier nonlinearities improve neural network acoustic models. Proc 30th Int Conf on Machine Learning 2013; 28: 3. Source: <https://ai.stanford.edu/~amaas/papers/relu_hybrid_icml2013_final.pdf>.
  37. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv Preprint. 2017. Source: <https://arxiv.org/abs/1412.6980>. DOI: 10.48550/arXiv.1412.6980.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20