Classification of maize seed hyperspectral images based on variable-depth convolutional kernels

IntroductionAccurate classification of corn seeds is vital for the effective utilization of germplasm resources and the improvement of seed selection and breeding efficiency. Traditional manual classification methods are labor-intensive and prone to errors. In contrast, machine learning techniques—p...

Full description

Saved in:
Bibliographic Details
Main Authors: Yating Hu, Hongchen Zhang, Changming Li, Qianfu Su, Wei Wang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1599231/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850232237377716224
author Yating Hu
Hongchen Zhang
Hongchen Zhang
Changming Li
Qianfu Su
Wei Wang
author_facet Yating Hu
Hongchen Zhang
Hongchen Zhang
Changming Li
Qianfu Su
Wei Wang
author_sort Yating Hu
collection DOAJ
description IntroductionAccurate classification of corn seeds is vital for the effective utilization of germplasm resources and the improvement of seed selection and breeding efficiency. Traditional manual classification methods are labor-intensive and prone to errors. In contrast, machine learning techniques—particularly convolutional neural networks (CNNs)—have demonstrated superior performance in terms of classification accuracy, robustness, and generalization. However, conventional hyperspectral data processing approaches often fail to simultaneously capture both spectral and textural features effectively.MethodsTo overcome this limitation, we propose a novel convolutional neural network architecture with a variable-depth convolutional kernel structure (VD-CNN). This design enables the network to adaptively extract continuous spectral features by modulating kernel depth, while simultaneously capturing fine-grained textural patterns through hierarchical convolutional operations. In our experiments, we selected eight widely cultivated corn seed varieties and collected hyperspectral images for 100 seeds per variety. A four-layer CNN framework was constructed, and a total of 12 models were developed by varying the convolutional kernel depth to evaluate the impact on classification performance.ResultsExperimental results show that the proposed VD-CNN achieves optimal performance when the convolutional kernel depth is set to 15, attaining a training accuracy of 98.65% and a test accuracy of 96.97%. To assess the generalization ability of the model, additional experiments were conducted on a publicly available rice seed hyperspectral dataset. The VD-CNN consistently outperformed existing benchmark models, improving the classification accuracy by 3.14% over the best baseline. These results validate the robustness and adaptability of the proposed architecture across different crop species and imaging conditions.DiscussionThese findings demonstrate that the proposed VD-CNN effectively captures both spectral and textural features in hyperspectral data, significantly enhancing classification performance. The method offers a promising framework for hyperspectral image analysis in seed classification and other agricultural applications.
format Article
id doaj-art-eb39321d15f44f2b89e490fdc265bb49
institution OA Journals
issn 1664-462X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-eb39321d15f44f2b89e490fdc265bb492025-08-20T02:03:15ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-06-011610.3389/fpls.2025.15992311599231Classification of maize seed hyperspectral images based on variable-depth convolutional kernelsYating Hu0Hongchen Zhang1Hongchen Zhang2Changming Li3Qianfu Su4Wei Wang5College of Information Technology, Jilin Agricultural University, Changchun, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun, ChinaEngineering Technology R & D Center, Changchun Guanghua University, Changchun, ChinaEngineering Technology R & D Center, Changchun Guanghua University, Changchun, ChinaInstitute of Plant Protection, Jilin Academy of Agricultural Sciences (Northeast Agricultural Research Center of China), Changchun, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun, ChinaIntroductionAccurate classification of corn seeds is vital for the effective utilization of germplasm resources and the improvement of seed selection and breeding efficiency. Traditional manual classification methods are labor-intensive and prone to errors. In contrast, machine learning techniques—particularly convolutional neural networks (CNNs)—have demonstrated superior performance in terms of classification accuracy, robustness, and generalization. However, conventional hyperspectral data processing approaches often fail to simultaneously capture both spectral and textural features effectively.MethodsTo overcome this limitation, we propose a novel convolutional neural network architecture with a variable-depth convolutional kernel structure (VD-CNN). This design enables the network to adaptively extract continuous spectral features by modulating kernel depth, while simultaneously capturing fine-grained textural patterns through hierarchical convolutional operations. In our experiments, we selected eight widely cultivated corn seed varieties and collected hyperspectral images for 100 seeds per variety. A four-layer CNN framework was constructed, and a total of 12 models were developed by varying the convolutional kernel depth to evaluate the impact on classification performance.ResultsExperimental results show that the proposed VD-CNN achieves optimal performance when the convolutional kernel depth is set to 15, attaining a training accuracy of 98.65% and a test accuracy of 96.97%. To assess the generalization ability of the model, additional experiments were conducted on a publicly available rice seed hyperspectral dataset. The VD-CNN consistently outperformed existing benchmark models, improving the classification accuracy by 3.14% over the best baseline. These results validate the robustness and adaptability of the proposed architecture across different crop species and imaging conditions.DiscussionThese findings demonstrate that the proposed VD-CNN effectively captures both spectral and textural features in hyperspectral data, significantly enhancing classification performance. The method offers a promising framework for hyperspectral image analysis in seed classification and other agricultural applications.https://www.frontiersin.org/articles/10.3389/fpls.2025.1599231/fullvariable-depth convolutional kernels3D convolutional kernelCNNcornhyperspectral imagevariety identification
spellingShingle Yating Hu
Hongchen Zhang
Hongchen Zhang
Changming Li
Qianfu Su
Wei Wang
Classification of maize seed hyperspectral images based on variable-depth convolutional kernels
Frontiers in Plant Science
variable-depth convolutional kernels
3D convolutional kernel
CNN
corn
hyperspectral image
variety identification
title Classification of maize seed hyperspectral images based on variable-depth convolutional kernels
title_full Classification of maize seed hyperspectral images based on variable-depth convolutional kernels
title_fullStr Classification of maize seed hyperspectral images based on variable-depth convolutional kernels
title_full_unstemmed Classification of maize seed hyperspectral images based on variable-depth convolutional kernels
title_short Classification of maize seed hyperspectral images based on variable-depth convolutional kernels
title_sort classification of maize seed hyperspectral images based on variable depth convolutional kernels
topic variable-depth convolutional kernels
3D convolutional kernel
CNN
corn
hyperspectral image
variety identification
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1599231/full
work_keys_str_mv AT yatinghu classificationofmaizeseedhyperspectralimagesbasedonvariabledepthconvolutionalkernels
AT hongchenzhang classificationofmaizeseedhyperspectralimagesbasedonvariabledepthconvolutionalkernels
AT hongchenzhang classificationofmaizeseedhyperspectralimagesbasedonvariabledepthconvolutionalkernels
AT changmingli classificationofmaizeseedhyperspectralimagesbasedonvariabledepthconvolutionalkernels
AT qianfusu classificationofmaizeseedhyperspectralimagesbasedonvariabledepthconvolutionalkernels
AT weiwang classificationofmaizeseedhyperspectralimagesbasedonvariabledepthconvolutionalkernels