EUVIMEDEUVIMED entdecken
Vergleichsstudie

Hyperspectral imaging combined with texture features for maize hybrid purity detection: a multi-model comparison based on machine learning and SHAP interpretability study

Xiaoshan Han, Xuenan Li, Suowei Wu, Xinjie Liu, Ziwen Li, Yang Song, Yong He, Xi Tian, Xiangyuan Wan

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-12 · 363 · 128407

DOI: 10.1016/j.saa.2026.128407 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-12. Verfasst von Xiaoshan Han und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Advanced Agriculture Sciences, University of Science and Technology Beijing, Beijing 100083, China. Hauptthemen laut MEDLINE: Zea mays, Hyperspectral Imaging, Seeds, Hybridization, Genetic. Die Arbeit nennt 33 Literaturangaben. Gefördert von: National Science and Technology Major Project, Beijing Nova Program, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hybrid maize performance depends strongly on the genetic purity of hybrid seeds, but female self-pollinated seeds and target hybrid seeds are difficult to distinguish by conventional visual inspection because of their highly similar phenotypes. This study developed a nondestructive and interpretable maize hybrid purity detection framework by integrating hyperspectral imaging and RGB-derived texture features. Hyperspectral images were acquired from the embryo and endosperm sides of five female parents, one common male parent, and their corresponding hybrids. Texture-based, full-band spectral, characteristic-band spectral, and texture-spectral fusion models were systematically constructed and compared. Competitive Adaptive Reweighted Sampling (CARS), Successive Projections Algorithm (SPA), and Synchronous Two-Dimensional Correlation Spectroscopy (Sync2D) were used for characteristic wavelength selection. The results showed that the embryo side provided more stable and discriminative spectral information than the endosperm side. Texture-only models showed limited ability to distinguish hybrids from female self-pollinated seeds, whereas embryo-side texture-spectral fusion models combined with CARS or SPA and Support Vector Machine (SVM) or Partial Least Squares Discriminant Analysis (PLS-DA) achieved average test accuracies of 0.99-1.00, meeting the national maize hybrid seed purity requirement of 97%. In the optimal low-dimensional models, the retained high-dimensional spectral variables were compressed to 28-69 key features, corresponding to a dimensionality reduction ratio of approximately 88%-95%. SHAP analysis identified mean saturation and seed size as important texture features; among spectral intervals, the 450-462 nm region appeared among the top-ranked embryo-side SHAP features in all five maize lines and showed the highest embryo-side mean absolute SHAP magnitude (0.0107 ± 0.0028). Overall, the proposed framework provides a high-throughput, low-dimensional, and interpretable solution for maize hybrid seed purity detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Zea maysHyperspectral ImagingSeedsHybridization, GeneticMachine LearningDiscriminant AnalysisAlgorithmsSupport Vector MachineLeast-Squares Analysis

Stichwörter der Autor:innen

Feature interpretabilityHybrid seedsHyperspectralMultisource dataNondestructive detectionPurityWavelength selection

Autor:innen und Institutionen

  • School of Advanced Agriculture Sciences, University of Science and Technology Beijing, Beijing 100083, China.
  • School of Advanced Agriculture Sciences, University of Science and Technology Beijing, Beijing 100083, China. Electronic address: tianx2019@sina.com.
  • School of Advanced Agriculture Sciences, University of Science and Technology Beijing, Beijing 100083, China. Electronic address: wanxiangyuan@ustb.edu.cn.

Förderung

  • National Science and Technology Major Project
  • Beijing Nova Program
  • National Natural Science Foundation of China

Zitieren

APA

Han, X., Li, X., Wu, S., Liu, X., Li, Z., Song, Y., He, Y., Tian, X., & Wan, X. (2026). Hyperspectral imaging combined with texture features for maize hybrid purity detection: a multi-model comparison based on machine learning and SHAP interpretability study. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 363, 128407. https://doi.org/10.1016/j.saa.2026.128407

Vancouver

Han X, Li X, Wu S, Liu X, Li Z, Song Y, et al. Hyperspectral imaging combined with texture features for maize hybrid purity detection: a multi-model comparison based on machine learning and SHAP interpretability study. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;363:128407. doi:10.1016/j.saa.2026.128407

BibTeX
@article{Han2026,
  author = {Han, Xiaoshan and Li, Xuenan and Wu, Suowei and Liu, Xinjie and Li, Ziwen and Song, Yang and He, Yong and Tian, Xi and Wan, Xiangyuan},
  title = {Hyperspectral imaging combined with texture features for maize hybrid purity detection: a multi-model comparison based on machine learning and SHAP interpretability study},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  volume = {363},
  pages = {128407},
  doi = {10.1016/j.saa.2026.128407}
}
Kostenlos starten →