AUTHOR=Hu Yating , Zhang Hongchen , Li Changming , Su Qianfu , Wang Wei 

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

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 16 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2025.1599231

DOI=10.3389/fpls.2025.1599231

ISSN=1664-462X

ABSTRACT=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.