Digital technologies in vegetable seed quality assessment

Relevance. The shape determined by its linear parameters, the color of the surface are the most important characteristics of seed quality. The optical imaging method combined with the automatic analysis of digital scanned images allows statistically reliable differentiation of vegetable seeds by size and color parameters. The Federal Scientific Center of Vegetable Growing, together with employees of the Agrophysical Research Institute and “ArgusSoft” LLC, is developing a modern instrumental method of digital morphometry of seeds.

The purpose of the work is to determine the morphometric parameters of the seeds of three vegetable crops by digitally analyzing scanned images and establish their relationship with viability and quality indicators.

Methods. Digital images of the seeds were obtained using an HP Sasanjet 200 flatbed scanner, JPG file format, 600 DPI resolution. Morphometric analysis of digital scanned images of seeds was performed on the basis of the Agrophysical Research Institute using Argus-BIO software manufactured by “ArgusSoft” LLC, St. Petersburg.

Results. It is shown that by selecting onion and radish seeds in size and density, their quality indicators can be significantly improved: up to 75.5% germination in onions, up to 100% in radishes with maximum batch alignment estimated by digital morphometry. The ideal shape for cabbage seeds has been determined: for full-fledged cabbage seeds, the roundness index should be more than 0.9. Further development of the technique will allow determining the optimal parameters of the size and shape of seeds for various types of vegetable crops and linking them with qualitative indicators.

1. Zheng Y. et al. Genome-wide association studies of grain quality traits in maize. Scientific Reports. 2021; 11: 9797. https://doi.org/10.1038/s41598-021-89276-3

2. Wang X., Cai Z. Era of maize breeding 4.0. Journal of Maize Sciences. 2019; 27(1): 1‒9 (in Chinese). https://doi.org/10.13597/j.cnki.maize.science.20190101

3. Wallace J.G., Rodgers-Melnick E., Buckler E.S. On the Road to Breeding 4.0: Unraveling the Good, the Bad, and the Boring of Crop Quantitative Genomics. Annual Review of Genetics. 2018; 52: 421‒444. https://doi.org/10.1146/annurev-genet-120116-024846

4. Wang X. et al. Evaluation on phenotypic traits of crop germplasm: Status and development. Journal of Plant Genetic Resources. 2022; 23(1): 12‒20 (in Chinese). https://doi.org/10.13430/j.cnki.jpgr.20210802001

5. Budd J. et al. Digital technologies in the public-health response to COVID-19. Nature Medicine. 2020; 26(8): 1183‒1192. https://doi.org/10.1038/s41591-020-1011-4

6. Sun D., Robbins K., Morales N., Shu Q., Cen H. Advances in optical phenotyping of cereal crops. Trends Plant Science. 2022; 27(2): 191‒208. https://doi.org/10.1016/j.tplants.2021.07.015

7. Clohessy J.W. et al. A Low-Cost Automated System for High-Throughput Phenotyping of Single Oat Seeds. The Plant Phenome Journal. 2018; 1(1): 1‒13. https://doi.org/10.2135/tppj2018.07.0005

8. Gong Z. et al. Recent Developments of Seeds Quality Inspection and Grading Based on Machine Vision. 2015 ASABE Annual International Meeting. St. Joseph, Michigan: American Society of Agricultural and Biological Engineers. 2015; 152188378. https://doi.org/10.13031/aim.20152188378

9. Fu J., Yuan H., Zhao R., Chen Z., Ren L. Peeling Damage Recognition Method for Corn Ear Harvest Using RGB Image. Applied Sciences. 2020; 10(10): 3371. https://doi.org/10.3390/app10103371

10. Jitanan S., Chimlek P. Quality grading of soybean seeds using image analysis. International Journal of Electrical and Computer Engineering. 2019; 9(5): 3495‒3503. http://doi.org/10.11591/ijece.v9i5.pp3495-3503

11. Veeramani B., Raymond J.W., Chanda P. DeepSort: deep convolutional networks for sorting haploid maize seeds. BMC Bioinformatics. 2018; 19: 289. https://doi.org/10.1186/s12859-018-2267-2

12. Jia B., Wang W., Ni X.Z., Chu X., Yoon S.C., Lawrence K.C. Detection of mycotoxins and toxigenic fungi in cereal grains using vibrational spectroscopic techniques: a review. World Mycotoxin Journal. 2020; 13(2): 163‒177. https://doi.org/10.3920/WMJ2019.2510

13. Kapadia V.N., Sasidharan N., Patil К. Seed Image Analysis and Its Application in Seed Science Research. Advances in Biotechnology and Microbiology. 2017; 7(2): 555709. https://doi.org/10.19080/AIBM.2017.07.555709

14. Liu F. et al. Digital techniques and trends for seed phenotyping using optical sensors. Journal of Advanced Research. 2023; 63: 1‒16. https://doi.org/10.1016/j.jare.2023.11.010

15. Lin P. et al. Rapidly and exactly determining postharvest dry soybean seed quality based on machine vision technology. Scientific Reports. 2019; 9: 17143. https://doi.org/10.1038/s41598-019-53796-w

16. Peng S. et al. Research on Rapeseed Counting Based on Machine Vision. Journal of Physics: Conference Series. 2021; 1757: 012028. https://doi.org/10.1088/1742-6596/1757/1/012028

17. Kurtulmuş F., Alibaş İ., Kavdır I. Classification of pepper seeds using machine vision based on neural network. International Journal of Agricultural and Biological Engineering. 2016; 9(1): 51‒62. https://doi.org/10.3965/j.ijabe.20160901.1790

18. Arkhipov M.V., Potrakhov N.N., Tyukalov Yu.A., Gusakova L.P. Digital system for early detection of latent grain damage. Proceedings of the Kuban State Agrarian University. 2023; 106: 184‒188 (in Russian). https://elibrary.ru/wzuipa

19. Musaev F.B., Priyatkin N.S., Ivanova M.I., Shchukina P.A., Jafarov I.H., Nowar M. Geometrical parameters and colour index of chive (Allium schoenoprasum) seed. Research on Crops. 2020; 21(4): 775‒782. https://doi.org/10.31830/2348-7542.2020.119

20. Musaev F.B., Priyatkin N.S., Ivanova M.I., Bukharov A.F., Kashleva A.I. Computerized visualization of seeds of Sepa subgenus (Allium L., Alliaceae) — an effective tool to assess their quality. Bulletin of NSAU (Novosibirsk State Agrarian University). 2022; (2): 39‒50 (in Russian). https://doi.org/10.31677/2072-6724-2022-63-2-39-50