Aliiev, E., & Vedmedeva, K.
(2025).
Automated devices for quantitative phenotyping of sunflower seeds.
Machinery & Energetics,
16(1),
54-64.
https://doi.org/10.31548/machinery/1.2025.54
To develop new sunflower varieties, it is important to accurately assess phenotypic traits that influence yield, disease resistance, and stress tolerance. Automation allows for systematic data collection and more informed decision-making in the breeding process. The goal of the work was to enhance the efficiency of selecting and predicting the development of sunflower genotypes through the development of new methods, hardware, and software tools for quantitative phenotypic characterisation of seeds. The methods for determining phenotypic characteristics of sunflower seeds, including geometric dimensions, mass, colour, rheological properties, and seed surface properties, have been presented and improved. A module for determining the morphological properties of seeds (geometric dimensions, mass, surface colour, etc.) was developed. This module was configured for high precision in the individual measurement of the geometric dimensions of sunflower seeds, with the determination of their shape and colour. It ensured low labour intensity and high technological efficiency in the implementation of the phenotyping procedure (determination, identification, and separation) of seeds. The methodology for analysing the rheological properties of seeds was refined, and a method for their automatic determination, along with a corresponding module, was substantiated. The proposed module maintains the accuracy of individual measurement of the rheological properties of seeds, consistent with modern measurement tools, while ensuring low labour intensity and high technological efficiency. Additionally, the module significantly reduced the influence of the human factor on the accuracy of measuring the rheological properties of seeds. The proposed module for determining seed surface properties ensured the accuracy of individual measurements of the coefficients of static and sliding friction of seeds, aligning with modern measurement tools, while also ensuring low labour intensity and high technological efficiency. This also significantly minimised the influence of the human factor on the accuracy of these measurements. The use of automated devices in practical conditions can help optimise the selection of seeds with the best characteristics
module, software, geometric dimensions, surface colour, rheological properties, frictional properties
[1] Aliiev, E.B. (2020). Automatic phenotyping test of sunflower seeds. Helia, 43(72), 51-66. doi: 10.1515/helia-2019-0019.
[2] Aliiev, Е.B. (2023). The prospects of quantitative phenotyping of oilseed crops. Agrology, 6(3), 49-59. doi: 10.32819/021109.
[3] Bai, S., Yuan, Y., Niu, K., Zhou, L., Zhao, B., Wei, L., Liu, L., Xiong, S., Shi, Z., Ma, Y., Zheng, Y., & Xing. G. (2022). Simulation parameter calibration and experimental study of a discrete element model of cotton precision seed metering. Agriculture, 12, article number 870. doi: 10.3390/agriculture12060870.
[4] Colmer, J., O’Neill, C.M., Wells, R., Bostrom, A., Reynolds, D., Websdale, D., Shiralagi, G., Lu, W., Lou, Q., Cornu, T.L., Ball, J., Renema, J., Andaluz, G.F., Benjamins, R., Penfield, S., & Zhou, J. (2020). SeedGerm: A cost-effective phenotyping platform for automated seed imaging and machine-learning based phenotypic analysis of crop seed germination. New Phytologist, 228, 778-793. doi: 10.1111/nph.16736.
[5] Costa, C., Schurr, U., Loreto, F., Menesatti, P., & Carpentier, S. (2019). Plant phenotyping research trends, a science mapping approach. Frontiers in Plant Science, 9, article number 1933. doi: 10.3389/fpls.2018.01933.
[6] Daviet, B., Fernandez, R., Cabrera-Bosquet, L., Pradal, C., & Fournier, C. (2022). PhenoTrack3D: An automatic high-throughput phenotyping pipeline to track maize organs over time. Plant Methods, 18, article number 130. doi: 10.1186/s13007-022-00961-4.
[7] Deb, M., Dhal, K.G., Das, A., Hussien, A.G., Abualigah, L., & Garai, A. (2024). A CNN-based model to count the leaves of rosette plants (LC-Net). Scientific Reports, 14, article number 1496. doi: 10.1038/s41598-024-51983-y.
[8] Hu, M., Xia, J., Zhou, Y., Luo, C., Zhou, M., & Liu, Z. (2022). Measurement and calibration of the discrete element parameters of coated delinted cotton seeds. Agriculture, 12, article number 286. doi: 10.3390/agriculture12020286.
[9] Jahnke, S., Roussel, J., Hombach, T., Kochs, J., Fischbach, A., Huber, G., & Scharr, H. (2016). phenoSeeder – a robot system for automated handling and phenotyping of individual seeds. Plant Physiology, 172, 1358-1370. doi: 10.1104/pp.16.01122.
[10] Jiang, Y., & Li, C. (2020). Convolutional neural networks for image-based high-throughput plant phenotyping: A review. Plant Phenomics, 4152816, article number 22. doi: 10.34133/2020/4152816.
[11] Jin, X., Zhao, Y., Wu, H., & Sun, T. (2022). Sunflower seeds classification based on sparse convolutional neural networks in multi-objective scene. Scientific Reports, 12, article number 19890. doi: 10.1038/s41598-022-23869-4.
[12] Jotautiene, E., Bivainis, V., Karayel, D., & Mieldažys, R. (2024). Theoretical and experimental verification of the physical-mechanical properties of organic bone meal granular fertilizers. Agronomy, 14, article number 1171. doi: 10.3390/agronomy14061171.
[13] Kumar, S.B., Raju, V.S., & Maheswari, U.V. (2023). OpenCV libraries for computer vision. In Computer vision: Applications of visual AI and image processing (pp. 1-22). Boston: De Gruyter. doi: 10.1515/9783110756722-001.
[14] Liu, F., Yang, R., Chen, R., Guindo, M.L., He, Y., Zhou, J., Lu, X., Chen, M., Yang, Y., & Kong, W. (2024). Digital techniques and trends for seed phenotyping using optical sensors. Journal of Advanced Research, 63, 1–16. doi: 10.1016/j.jare.2023.11.010.
[15] Nehoshtan, Y., Carmon, E., Yaniv, O., Ayal, S., & Rotem, O. (2021). Robust seed germination prediction using deep learning and RGB image data. Scientific Reports, 11, article number 22030. doi: 10.1038/s41598-021-01712-6.
[16] Pieruschka, R., & Schurr U. (2019). Plant phenotyping: Past, present, and future. Plant Phenomics, 2019, article number 7507131. doi: 10.34133/2019/7507131.
[17] Tanabata, T., Shibaya, T., Hori, K., Ebana, K., & Yano, M. (2012). SmartGrain: High-throughput phenotyping software for measuring seed shape through image analysis. Plant Physiology, 160(4): 1871-1880. doi: 10.1104/pp.112.205120.
[18] Tu, K., Wu, W., Cheng, Y., Zhang, H., Xu, Y., Dong, X., Wang, M., & Sun, Q. (2023). AIseed: An automated image analysis software for high-throughput phenotyping and quality non-destructive testing of individual plant seeds. Computers and Electronics in Agriculture, 207, article number 107740. doi: 10.1016/j.compag.2023.107740.
[19] Wang, S., Yu, Z., Zhang, W., Zhao D., & Aorigele. (2022). Friction coefficient calibration of sunflower seeds for discrete element modeling simulation. Phyton-International Journal of Experimental Botany, 91(11), 2559-2582. doi: 10.32604/phyton.2022.021354.
[20] Yang, S., Zheng, L., He, P., Wu, T., Sun, S., & Wang, M. (2021). High‑throughput soybean seeds phenotyping with convolutional neural networks and transfer learning. Plant Methods, 17, 50, article number 50. doi: 10.1186/s13007-021-00749-y.