Classification of maize seed hyperspectral images based on variable-depth convolutional kernels
These 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.
Authors
- Qianfu Su
- Wei Wang (ORCID: https://orcid.org/0000-0002-9616-1145)
- Hongchen Zhang (ORCID: https://orcid.org/0009-0002-0924-8945)
- Changming Li (ORCID: https://orcid.org/0000-0003-2535-4115)
- Yating Hu (ORCID: https://orcid.org/0000-0003-2946-1006)
Institutions
- Jilin Academy of Agricultural Sciences (CN)
- Jilin Agricultural University (CN)
- Changchun University (CN)
Publication Details
- Journal
- Frontiers in Plant Science
- Published
- 2025-06-06
- DOI
- https://doi.org/10.3389/fpls.2025.1599231
- Citations
- 1
- Primary Topic
- Spectroscopy and Chemometric Analyses
- Type
- article
- Field-Weighted Citation Impact
- 0.75
Funders
- Jilin Agricultural University