Statistical analysis of seeds morphology and texture for interspecific similarity assessment across taxonomic levels
Seweryn Lipiński
seweryn.lipinski@uwm.edu.plFaculty of Technical Sciences, University of Warmia and Mazury in Olsztyn (Poland)
https://orcid.org/0000-0001-9771-6897
Abstract
The identification of plant species based on seed images plays a vital role in botanical research and agricultural applications. This study investigates the potential of distinguishing plant species using fundamental geometric and textural features extracted from seed images. A dataset comprising images of seeds from 88 different species was analyzed to obtain key morphological descriptors. These features were then subjected to statistical analyses, including dendrogram construction and heatmap visualization, to uncover patterns and correlations relevant to species differentiation. The results indicate that the integration of geometric and textural characteristics enables effective classification of plant species. This combined approach provides a robust and efficient framework for botanical identification, allowing for the recognition of similarities and distinctions at the species, genus, and family levels. The findings underscore the significance of advanced image processing and statistical techniques in enhancing the accuracy of plant species identification, with promising implications for automated agricultural systems and biodiversity research.
Keywords:
plant species identification, seed image analysis, botanical classification, geometric and textural features, hierarchical clusteringReferences
Barbierato, E., & Gatti, A. (2024). The challenges of machine learning: A critical review. Electronics, 13(2), 416.
DOI: https://doi.org/10.3390/electronics13020416
Google Scholar
Buhrmester, V., Münch, D., & Arens, M. (2021). Analysis of explainers of black box deep neural networks for computer vision: A survey. Machine Learning and Knowledge Extraction, 3(4), 966–989.
DOI: https://doi.org/10.3390/make3040048
Google Scholar
Chen, L., Li, S., Bai, Q., Yang, J., Jiang, S., & Miao, Y. (2021). Review of image classification algorithms based on convolutional neural networks. Remote Sensing, 13(22), 4712.
DOI: https://doi.org/10.3390/rs13224712
Google Scholar
Chen, Z., Fan, W., Luo, Z., & Guo, B. (2022). Soybean seed counting and broken seed recognition based on image sequence of falling seeds. Computers and Electronics in Agriculture, 196, 106870.
DOI: https://doi.org/10.1016/j.compag.2022.106870
Google Scholar
Cho, M., & Martinez, W. L. (2014). Statistics in MATLAB: A Primer. CRC Press: Boca Raton, USA.
DOI: https://doi.org/10.1201/b17998
Google Scholar
Djoulde, K., Ousman, B., Hamadjam, A., Bitjoka, L., & Tchiegang, C. (2024). Classification of pepper seeds by machine learning using color filter array images. Journal of Imaging, 10(2), 41.
DOI: https://doi.org/10.3390/jimaging10020041
Google Scholar
Engle, S., Whalen, S., Joshi, A., & Pollard, K. S. (2017). Unboxing cluster heatmaps. BMC Bioinformatics, 18, 1–15.
DOI: https://doi.org/10.1186/s12859-016-1442-6
Google Scholar
Ermiş, S., Ercan, U., Kabaş, A., Kabaş, Ö., & Moiceanu, G. (2025). Machine learning-based morphological classification and diversity analysis of ornamental pumpkin seeds. Foods, 14(9), 1498.
DOI: https://doi.org/10.3390/foods14091498
Google Scholar
Eryigit, R., & Tugrul, B. (2021). Performance of various deep-learning networks in the seed classification problem. Symmetry, 13(10), 1892.
DOI: https://doi.org/10.3390/sym13101892
Google Scholar
Espinosa-Roldán, F. E., Rodríguez-Lorenzo, J. L., Martín-Gómez, J. J., Tocino, Á., Ruiz Martínez, V., Remón Elola, A., ... Muñoz-Organero, G. (2024). Morphometric analysis of grape seeds: Looking for the origin of Spanish cultivars. Seeds, 3(3), 286–310.
DOI: https://doi.org/10.3390/seeds3030022
Google Scholar
Gonzalez, R. C., Woods, R. E., & Eddins, S. L. (2003). Digital Image Processing Using MATLAB. Prentice Hall: New Jersey, USA.
Google Scholar
Islam, T., Sarker, T. T., Ahmed, K. R., & Lakhssassi, N. (2024). Detection and classification of cannabis seeds using RetinaNet and Faster R-CNN. Seeds, 3(3), 456–478.
DOI: https://doi.org/10.3390/seeds3030031
Google Scholar
Kalicka, R., & Lipiński, S. (2010). A fast method of separation of the noisy background from the head-cross section in the sequence of MRI scans. Biocybernetics and Biomedical Engineering, 30(2), 15–27.
Google Scholar
Krohn, J., Beyleveld, G., & Bassens, A. (2019). Deep Learning Illustrated: A Visual, Interactive Guide to Artificial Intelligence. Addison-Wesley Professional: Boston, USA.
Google Scholar
Kumar, V., Aydav, P. S. S., & Minz, S. (2024). Crop Seeds Classification Using Traditional Machine Learning and Deep Learning Techniques: A Comprehensive Survey. SN Computer Science, 5(8), 1031.
DOI: https://doi.org/10.1007/s42979-024-03379-y
Google Scholar
Lipiński, A. J., & Lipiński, S. (2020). Binarizing water sensitive papers–how to assess the coverage area properly?. Crop Protection, 127, 104949.
DOI: https://doi.org/10.1016/j.cropro.2019.104949
Google Scholar
Loddo, A., Loddo, M., & Di Ruberto, C. (2021). A novel deep learning based approach for seed image classification and retrieval. Computers and Electronics in Agriculture, 187, 106269.
DOI: https://doi.org/10.1016/j.compag.2021.106269
Google Scholar
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62–66.
DOI: https://doi.org/10.1109/TSMC.1979.4310076
Google Scholar
Pavlopoulos, G. A., Soldatos, T. G., Barbosa-Silva, A., & Schneider, R. (2010). A reference guide for tree analysis and visualization. BioData Mining, 3, 1–24.
DOI: https://doi.org/10.1186/1756-0381-3-1
Google Scholar
Rajalakshmi, R., Faizal, S., Sivasankaran, S., & Geetha, R. (2024). RiceSeedNet: Rice seed variety identification using deep neural network. Journal of Agriculture and Food Research, 16, 101062.
DOI: https://doi.org/10.1016/j.jafr.2024.101062
Google Scholar
Reyes-Aldasoro, C. C. (2015). Biomedical Image Analysis Recipes in MATLAB: For Life Scientists and Engineers. John Wiley & Sons: Oxford, UK.
DOI: https://doi.org/10.1002/9781118657546
Google Scholar
Sezgin, M., & Sankur, B. (2004). Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging, 13(1), 146–165.
DOI: https://doi.org/10.1117/1.1631315
Google Scholar
Szandała, T. (2023). Unlocking the black box of CNNs: Visualising the decision-making process with PRISM. Information Sciences, 642, 119162.
DOI: https://doi.org/10.1016/j.ins.2023.119162
Google Scholar
Taheri-Garavand, A., Nasiri, A., Fanourakis, D., Fatahi, S., Omid, M., & Nikoloudakis, N. (2021). Automated in situ seed variety identification via deep learning: A case study in chickpea. Plants, 10(7), 1406.
DOI: https://doi.org/10.3390/plants10071406
Google Scholar
Taye, M. M. (2021). Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation, 11(3), 52.
DOI: https://doi.org/10.3390/computation11030052
Google Scholar
Wang, L., & Wang, L. (2021). Variety identification model for maize seeds using hyperspectral pixel-level information combined with convolutional neural network. National Remote Sensing Bulletin, 25(11), 2234–2244.
DOI: https://doi.org/10.11834/jrs.20219349
Google Scholar
Wiesnerova, D & Wiesner, Ivo (2008). Computer image analysis of seed shape and seed color for flax cultivar description. Computers and Electronics in Agriculture, 61(2), 126–135.
DOI: https://doi.org/10.1016/j.compag.2007.10.001
Google Scholar
Wilkinson, L., & Friendly, M. (2009). The history of the cluster heat map. The American Statistician, 63(2), 179–184.
DOI: https://doi.org/10.1198/tas.2009.0033
Google Scholar
Yasar, A. (2024). Analysis of selected deep features with CNN-SVM-based for bread wheat seed classification. European Food Research and Technology, 250(6), 1551–1561.
DOI: https://doi.org/10.1007/s00217-024-04488-x
Google Scholar
Yuan, M., Lv, N., Dong, Y., Hu, X., Lu, F., Zhan, K., ... Xie, Y. (2024). A dataset for fine-grained seed recognition. Scientific Data, 11(1), 344.
DOI: https://doi.org/10.1038/s41597-024-03176-5
Google Scholar
Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M., & Parmar, M. (2024). A review of convolutional neural networks in computer vision. Artificial Intelligence Review, 57(4), 99.
DOI: https://doi.org/10.1007/s10462-024-10721-6
Google Scholar
Authors
Seweryn Lipińskiseweryn.lipinski@uwm.edu.pl
Faculty of Technical Sciences, University of Warmia and Mazury in Olsztyn Poland
https://orcid.org/0000-0001-9771-6897
Statistics
Abstract views: 36PDF downloads: 8
License
Copyright (c) 2025 Seweryn Lipiński
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Upon submitting the article, the Authors grant the Publisher a non-exclusive and free license to use the article for an indefinite period of time throughout the world in the following fields of use:
- Production and reproduction of copies of the article using a specific technique, including printing and digital technology.
- Placing on the market, lending or renting the original or copies of the article.
- Public performance, exhibition, display, reproduction, broadcasting and re-broadcasting, as well as making the article publicly available in such a way that everyone can access it at a place and time of their choice.
- Including the article in a collective work.
- Uploading an article in electronic form to electronic platforms or otherwise introducing an article in electronic form to the Internet or other network.
- Dissemination of the article in electronic form on the Internet or other network, in collective work as well as independently.
- Making the article available in an electronic version in such a way that everyone can access it at a place and time of their choice, in particular via the Internet.
Authors by sending a request for publication:
- They consent to the publication of the article in the journal,
- They agree to give the publication a DOI (Digital Object Identifier),
- They undertake to comply with the publishing house's code of ethics in accordance with the guidelines of the Committee on Publication Ethics (COPE), (http://ihar.edu.pl/biblioteka_i_wydawnictwa.php),
- They consent to the articles being made available in electronic form under the CC BY-SA 4.0 license, in open access,
- They agree to send article metadata to commercial and non-commercial journal indexing databases.
