EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GCT-BCLN: a bidirectional closed-loop network for nondestructive detection of rice seed vigor using hyperspectral imaging

Linyu Yan, Ending Xu, Xiangan Meng, Shuxin Jiang, Juan Liao, Yi Ren, Xinchun Zhan, Yu Zou

Frontiers in Plant Science · 17.08.2026 · 17

DOI: 10.3389/fpls.2026.1923668 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 17.08.2026. Verfasst von Linyu Yan und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronics and Electrical Engineering, Anhui Agricultural University, Hefei, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rice seed vigor is a key determinant of germination performance and final crop yield, making its rapid and non-destructive assessment essential for seed quality evaluation. Conventional vigor detection methods are often destructive, labor-intensive, and time-consuming. Hyperspectral imaging provides a promising non-destructive alternative, but hyperspectral data are typically high-dimensional, redundant, and susceptible to noise and scattering interference. Moreover, existing models still have limited ability to discriminate subtle spectral differences among seed vigor levels. To address these challenges, this study proposes a gated recurrent unit (GRU)-guided closed-loop CNN-Transformer network (GCT-BCLN) for accurate, non-destructive identification of rice seed vigor. The model establishes bidirectional information flow between CNN and Transformer via the GRU, enabling dynamic and synergistic optimization of local spectral features and global spectral representations. In addition, a combined preprocessing strategy integrating adaptive iteratively reweighted penalized least squares (AirPLS), Savitzky–Golay (SG) smoothing, and multiplicative scatter correction (MSC) was adopted to improve spectral quality. Experimental results showed that GCT-BCLN achieved a test accuracy of 0.9795 for hybrid indica rice, outperforming the CNN-Transformer fusion model by 1.37%. The model also achieved accuracies of 0.9793 and 0.9758 on conventional japonica rice and glutinous japonica rice, respectively, showing consistent performance across the three evaluated variety-specific datasets under the controlled experimental protocol. These results support the feasibility of GCT-BCLN for laboratory-scale, non-destructive discrimination of aging-induced rice seed categories under controlled conditions, while practical application requires further external validation.

Schlagwörter

Stichwörter der Autor:innen

CNNgated recurrent unitshyperspectral imagingrice seed vigor detectiontransformer

Autor:innen und Institutionen

  • College of Electronics and Electrical Engineering, Anhui Agricultural University, Hefei, China.
  • Anhui Province Key Laboratory of Rice Germplasm Innovation and Molecular Improvement, Rice Research Institute, Anhui Academy of Agricultural Sciences, Hefei, China.
  • College of Agriculture, Anhui University of Science and Technology, Fengyang, China.

Zitieren

APA

Yan, L., Xu, E., Meng, X., Jiang, S., Liao, J., Ren, Y., Zhan, X., & Zou, Y. (2026). GCT-BCLN: a bidirectional closed-loop network for nondestructive detection of rice seed vigor using hyperspectral imaging. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1923668

Vancouver

Yan L, Xu E, Meng X, Jiang S, Liao J, Ren Y, et al. GCT-BCLN: a bidirectional closed-loop network for nondestructive detection of rice seed vigor using hyperspectral imaging. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1923668

BibTeX
@article{Yan2026,
  author = {Yan, Linyu and Xu, Ending and Meng, Xiangan and Jiang, Shuxin and Liao, Juan and Ren, Yi and Zhan, Xinchun and Zou, Yu},
  title = {GCT-BCLN: a bidirectional closed-loop network for nondestructive detection of rice seed vigor using hyperspectral imaging},
  journal = {Frontiers in Plant Science},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpls.2026.1923668}
}
Kostenlos starten →