EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Non-destructive identification of maize kernel varieties using a lightweight weakly supervised machine vision framework

Chunguang Bi, Hao Xie, Xinhua Bi, Zuo Zhang, Mohan Wang, Jing Chen

Frontiers in Plant Science · 10.11.2026 · 17

DOI: 10.3389/fpls.2026.1979068 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 10.11.2026. Verfasst von Chunguang Bi und 5 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Reliable identification of maize kernel varieties is important for seed-lot management, breeding, and quality control. However, subtle inter-varietal phenotypic differences make rapid, non-destructive identification challenging. This study aimed to develop an accurate and computationally efficient identification method using only image-level labels.

Methods

We developed Decoupled Refinement with Adaptive Hyperparameter Optimization (DRAHO), which integrates a MobileNetV4-Conv-Medium backbone, a decoupled Global -Locator -Reviewer (GLR) network, and Elite Adaptive Rime Optimization (EARIME). The GLR network performs global recognition, annotation-free localization, and attention-guided feature refinement without explicit image cropping. EARIME optimizes the learning rate and loss weights using a fixed proxy task based on validation performance. DRAHO was trained on 10,000 individual kernel images from ten maize varieties and evaluated on a held-out test set.

Results

DRAHO achieved 98.30% accuracy, exceeding Progressive Multi-Granularity (PMG) by 2.40 percentage points, with 7.16 million parameters and 1.65 GFLOPs. The proxy configuration reduced the nominal sample -epoch workload per candidate by 96.25% compared with full-data training for 100 epochs. After independent dataset-specific retraining, DRAHO achieved 97.50% accuracy on a public maize dataset and 98.26% accuracy on a public wolfberry dataset.

Discussion

These results demonstrate that DRAHO combines weakly supervised feature refinement with efficient hyperparameter selection. Under controlled imaging conditions, it provides a practical approach to non-destructive maize kernel variety identification with modest computational requirements.

Zitieren

APA

Bi, C., Xie, H., Bi, X., Zhang, Z., Wang, M., & Chen, J. (2026). Non-destructive identification of maize kernel varieties using a lightweight weakly supervised machine vision framework. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1979068

Vancouver

Bi C, Xie H, Bi X, Zhang Z, Wang M, Chen J. Non-destructive identification of maize kernel varieties using a lightweight weakly supervised machine vision framework. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1979068

BibTeX
@article{Bi2026,
  author = {Bi, Chunguang and Xie, Hao and Bi, Xinhua and Zhang, Zuo and Wang, Mohan and Chen, Jing},
  title = {Non-destructive identification of maize kernel varieties using a lightweight weakly supervised machine vision framework},
  journal = {Frontiers in Plant Science},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpls.2026.1979068}
}
Kostenlos starten →