Identification of Hybrid Indica Paddy Rice Grain Varieties Based on Hyperspectral Imaging and Deep Learning
Biosensors · 2025
DOI: 10.3390/bios15100647 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors, 2025. Verfasst von Meng Zhang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Agricultural Economy and Information Research Institute, Anhui Academy of Agricultural Sciences, Hefei 230031, China. Hauptthemen laut MEDLINE: Oryza, Deep Learning, Hyperspectral Imaging. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Project of Anhui Academy of Agricultural Sciences, Agricultural Science and Technology Achievement Transformation Project of Anhui Academy of Agricultural Sciences, Central Leading Local Science and Technology Development Special Plan.
Abstract (Originalsprache)
Paddy rice grain variety classification is essential for quality control, as different rice varieties exhibit significant variations in quality attributes, affecting both food security and market value. The integration of hyperspectral imaging with machine learning presents a promising approach for precise classification, though challenges remain in managing the high dimensionality and variability of spectral data, along with the need for model interpretability. To address these challenges, this study employs a CNN-Transformer model that incorporates Standard Normal Variate (SNV) preprocessing, Competitive Adaptive Reweighted Sampling (CARS) for feature wavelength selection, and interpretability analysis to optimize the classification of hybrid indica paddy rice grain varieties. The results show that the CNN-Transformer model outperforms baseline models, achieving an accuracy of 95.33% and an F1-score of 95.40%. Interpretability analysis reveals that the model’s ability to learn from key wavelength features is significantly stronger than that of the comparison models. The key spectral bands identified for hybrid indica paddy rice grain variety classification lie within the 400–440 nm, 580–700 nm, and 880–960 nm ranges. This study demonstrates the potential of hyperspectral imaging combined with machine learning to advance rice variety classification, providing a powerful and interpretable tool for automated rice quality control in agricultural practices.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Agricultural Economy and Information Research Institute, Anhui Academy of Agricultural Sciences, Hefei 230031, China.
- College of Engineering, South China Agricultural University, Guangzhou 510642, China.
- School of Computer and Information Engineering, Fuyang Normal University, Fuyang 236037, China.
- Anhui Disater Earnly Warning and Agricultural Meteorological Information Center, Hefei 230031, China.
ORCID-Profile: Meng Zhang
Förderung
- Research Project of Anhui Academy of Agricultural Sciences
- Agricultural Science and Technology Achievement Transformation Project of Anhui Academy of Agricultural Sciences
- Central Leading Local Science and Technology Development Special Plan
- Scientific Research Project of Fuyang Normal University
Zitieren
APA
Zhang, M., Li, P., Dong, W., Tang, S., Wang, Y., Li, R., Ju, S., Guan, B., Zhu, J., Kong, J., & Zhang, L. (2025). Identification of Hybrid Indica Paddy Rice Grain Varieties Based on Hyperspectral Imaging and Deep Learning. Biosensors. https://doi.org/10.3390/bios15100647
Vancouver
Zhang M, Li P, Dong W, Tang S, Wang Y, Li R, et al. Identification of Hybrid Indica Paddy Rice Grain Varieties Based on Hyperspectral Imaging and Deep Learning. Biosensors. 2025. doi:10.3390/bios15100647
BibTeX
@article{Zhang2025,
author = {Zhang, Meng and Li, Peng and Dong, Wei and Tang, Shuqi and Wang, Yan and Li, Runmei and Ju, Shucun and Guan, Bolun and Zhu, Jingbo and Kong, Juanjuan and Zhang, Liping},
title = {Identification of Hybrid Indica Paddy Rice Grain Varieties Based on Hyperspectral Imaging and Deep Learning},
journal = {Biosensors},
year = {2025},
doi = {10.3390/bios15100647}
}
EUVIMED