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