ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Technical Advances in Plant Science
Volume 16 - 2025 | doi: 10.3389/fpls.2025.1587845
This article is part of the Research TopicMachine Vision and Machine Learning for Plant Phenotyping and Precision Agriculture, Volume IIView all 41 articles
SE-enhanced 1-D CNN with Full-Band Hyperspectral 1 Imaging for Rapid and Accurate Maize Seed Variety 2 Classification
Provisionally accepted
- Gansu Agricultural University, Lanzhou, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Accurate identification of maize seed varieties is essential for enhancing 4 crop yield and ensuring genetic purity in breeding programs. This study establishes a 5 non-destructive classification approach based on hyperspectral imaging for 6 discriminating 30 widely cultivated maize varieties from Northwest China. 7 Hyperspectral images were acquired within the 380–1018 nm range, and the embryo 8 region of each seed was selected as the region of interest for spectral extraction. The 9 collected spectra were preprocessed using Savitzky–Golay (SG) smoothing. Several 10 machine learning models—KNN, ELM, and a two-layer convolutional neural network 11 integrated with squeeze-and-excitation (SE) attention modules (CNN2c-SE)—were 12 constructed and compared. Results demonstrated that the CNN2c-SE model utilizing 13 full-spectrum data achieved a superior classification accuracy of 93.89%, significantly 14 outperforming both conventional machine learning models and 15 feature-waveband-based approaches. The proposed method offers an effective and 16 efficient tool for high-throughput, non-destructive maize seed variety identification, 17 with promising applications in seed quality control and precision breeding.
Keywords: Hyperspectral imaging technology, Maize seeds, Classification, Convolutional Neural Network, Full band
Received: 05 Mar 2025; Accepted: 24 Sep 2025.
Copyright: © 2025 Zhang, Liu, Han, Sun and Feng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Chengzhong Liu, liucz@gsau.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.