Assessing Genetic Diversity of Soybean Based on Smartphone Image-Derived Canopy Parameter

Document Type : Original Research

Authors
Myong-Kwang Ri
Kwang-O Jong
Ye-Kwang Sin
Department of Garden Plant Breeding, Faculty of Life Science, Kim Il Sung University, Pyongyang, Democratic People’s Republic of Korea.
Abstract
Convenient and accurate characterization of field-grown crops is essential for effective use of germplasm resources and breeding programs. In this study, we evaluated genetic relationships among 18 soybean accessions at the early growth stage using a smartphone image-derived canopy parameter, the Canopy Cover Rate (CCR). Field experiments were conducted over two consecutive years (2021 and 2022). CCR was estimated from top-view images using image analysis software, providing a non-destructive and efficient indicator of plant morphology. CCR showed significant variation among accessions and was strongly correlated with traditional morphological/biomass traits (Correlation coefficients> 0.8). Multivariate analyses, including Principal Component Analysis (PCA), Hierarchical Cluster Analysis (HCA), and Discriminant Analysis (DA), revealed that CCR could effectively classify accessions, with DA achieving an average correct classification rate of 88.9%. The results suggest that CCR is a reliable index for assessing genetic diversity in field-grown soybean genotypes. This study introduces an innovative, simple, and accurate method for evaluating soybean genetic resources using image-derived parameter.


Keywords

Subjects

1.       Adhikari, R., Li, C., Kalbaugh, K. and Nemali, K. 2020. A Low-Cost Smartphone Controlled Sensor Based on Image Analysis for Estimating Whole-Plant Tissue Nitrogen (N) Content in Floriculture Crops. Comput. Electron. Agric., 169: 105173.
2.       An, N., Palmer, C. M., Baker, R. L., Markelz, R. J. C., Ta, J., Covington, M. F., Maloof, J. N., Welch, S. M. and Weinig, C. 2016. Plant High-throughput Phenotyping Using Photogrammetry and Imaging Techniques to Measure Leaf Length and Rosette Area. Comput. Electron. Agric.,127: 376-394.
3.       Barman,U., Choudhury, R. D., Sahu, D. and Barman, G. G. 2020. Comparison of Convolution Neural Networks for Smartphone Image Based on Real Time Classification of Citrus Leaf Disease.Comput. Electron. Agric., 177: 105661.
4.       Chen, Y. M., Zhang, W. M., Hu, R. H., Qi, J. B., Shao, J., Li, D., Wan, P., Qiao, C., Shen, A. J. and Yan, G. J. 2018. Estimation of Forest Leaf Area Index Using Terrestrial Laser Scanning Data and Path Length Distribution Model in Open-Canopy Forests. Agric. For. Meteorol., 263: 323-333.
5.       Gadissa, F., Tesfaye, K., Dagne, K. and Geleta, M. 2020. Morphological Traits Based on Genetic Diversity Assessment of Ethiopian Potato [Plectranthus edulis (Vatke) Agnew] Populations from Ethiopia. Genet. Resour. Crop Evol., 67: 809-829.
6.       Jiang, Y., Li, C. Y. and Paterson, A. H. 2016. High throughput Phenotyping of Cotton Plant Height Using Depth Images under Field Conditions. Comput. Electron. Agric., 130: 57-68.
7.       Jong, K. O., Han, K. M., Kawk, S. L., Jang, Y. J., Kim, K. P. and Ho, C. 2021. Simple Estimation of Green Area Rate Using Image Analysis and Quantitative Traits Related to Plant Architecture and Biomass in Rice Seedling. Theor. Exp. Plant Physiol., 33: 225-234.
8.       Khadivi, A. 2018. Phenotypic Characterization of Elaeagnus angustifolia Using Multivariate Analysis. Ind. Crops Prod., 120: 155-161.
9.       Liang, W. Z., Kirk, K. R. and Greene, J. K. 2018. Estimation of Soybean Leaf Area, Edge, and Defoliation Using Color Image Analysis. Comput. Electron. Agric., 150:41-51.
10.    McDonald, S. C., Bilyeu, K., Koebernick, J., Buckley, B., Fallen, B., Rouf Mian, M. A. and Li, Z. L. 2023. Selecting Recombinant to Stack High Protein with High Oleic Acid and Low Linoleic Acid in Soybean (Glycine max). Plant Breed., 142:477-488.
11.    Rees, W. G., Golubeva, E. I., Tutubalina, O. V., Zimin, M. V. and Derkacheva, A. A. 2020. Relation between Leaf Srea Index and NDVI for Subarctic Deciduous Vegetation. Int. J. Remote Sens., 41: 8573-8589.
12.    Shahid, A., Ayyub, C. M., Abbas, M. and Ahmad, R. 2021. Assessment of genetic Diversity in Round Gourd (Praecitrullus fistulosus) Germplasm of Pakistan Considering Morphological Characters. Genet. Resour. Crop Evol., 66: 215-224.
13.    Tan, K. S. and Isa, N. A. M. 2010. Color Image Segmentation Using Histogram Thresholding– Fuzzy C-Means Hybrid Approach. Pattern Recognit., 44: 1-15.
14.    Wang, B., Gao, Y. S., Yuan, X. H., Xiong, S. W. and Feng, X. Z.2020. From Species to Cultivar: Soybean Cultivar Recognition Using Joint Leaf Image Patterns by Multiscale Sliding Chord Matching. Biosyst. Eng., 194: 99-111.
15.    Wen, Z. F., Ma, M. H., Zhang, C.,Yi, X. M., Chen, J. L. and Wu, S. J. 2017. Estimating Seasonal Aboveground Biomass of a Riparian Pioneer Plant Community: An Exploratory Analysis by Canopy Structural Data. Ecol. Indic., 83:441-450.
16.    Zanklan, S., Becker, H. C., Sørensen, M., Pawelzik, E. and Grüneberg, W. J. 2018. Genetic Diversity in Cultivated Yam Bean (Pachyrhizus spp.) Evaluated through Multivariate Analysis of Morphological and Agronomic Traits. Genet. Resour. Crop Evol., 65:811-843.
17.    Zhang, C. Y., Si, Y. S., Lamkey, J. and Boydston, R. A., Garland-Campbell, K. A. And Sankaran, S. 2018. High-Throughput Phenotyping of Seed/Seedling Evaluation Using Digital Image Analysis. Agronomy, 8: 63-77.
18.    Zhao, F., Jiao, L. C. and Liu, H. Q. 2013. Kernel Generalized Fuzzy C-Means Clustering with Spatial Information for Image Segmentation. Digit. Signal Process., 23: 184-199.
19.    Zhou, J. F., Chen, H. T., Zhou, J., Fu, X. Q., Ye, H. and Nguyen, H. T. 2018. Development of an Automated Phenotyping Platform for Quantifying Soybean Dynamic Responses to Salinity Stress in Greenhouse Environment. Comput. Electron. Agric., 151: 319-330.
Journal of Agricultural Science and Technology
Volume 28, Issue 1
January and February 2026
Pages 147-161