Abstract
Accurate identification of wheat varieties at the seedling stage is crucial for maintaining seed purity and optimizing field management. However, the subtle phenotypic variations among seedlings present a significant challenge for visual recognition. To address this, we propose SeedlingNet, a novel deep learning model specifically designed for fine-grained wheat seedling variety classification. The core innovations of SeedlingNet include: The Kolmogorov-Arnold-based Convolutional Attention (KCA) mechanism, which dynamically enhances feature representation by replacing static activation functions with learnable, adaptive ones; A multi-scale feature fusion architecture that integrates hierarchical features to capture both global and local characteristics. We established a comprehensive image dataset of 13,600 images representing 17 wheat varieties at the early growth stage. Experimental results demonstrate that SeedlingNet achieves a remarkable classification accuracy of 99.26%, outperforming traditional machine learning methods and mainstream deep learning models. Ablation studies confirm the significant impact of the KCA module and the multi-scale fusion structure on the model's performance. This research provides an effective, non-destructive tool for early-stage variety identification, with strong potential for precision agriculture applications.The dataset is licensed in Zhang, Wenbo (2025), "Seedings", Mendeley Data, V1, doi: 10.17632/f8ykx4sz6w. 1.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-nd. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 3
Claim · model-written summary
The SeedlingNet deep learning model classified wheat seedling varieties with 99.26% accuracy, outperforming traditional machine learning methods and mainstream deep learning models.
- Taxon
- wheat
Triticum aestivumt0 - Outcome
- classification accuracye0
- Direction
- outperforminge0
- Value
- 99.26%e0
- Comparator
- traditional machine learning methods and mainstream deep learning modelse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“wheat seedling variety recognition”
e0“SeedlingNet achieves a remarkable classification accuracy of 99.26%, outperforming traditional machine learning methods and mainstream deep learning models”
Claim · model-written summary
The authors established an image dataset of 13,600 images representing 17 wheat varieties at the early growth stage.
- Taxon
- wheatTriticum aestivume0
- Organ / stage
- early growth stagee0
- Outcome
- image datasete0
- Value
- 13,600 imagese0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“We established a comprehensive image dataset of 13,600 images representing 17 wheat varieties at the early growth stage”
Claim · model-written summary
Ablation studies confirmed a significant impact of the KCA module and the multi-scale fusion structure on the model's performance.
- Taxon
- wheatTriticum aestivumt0
- Treatment
- KCA module and the multi-scale fusion structuree0
- Outcome
- model's performancee0
Not reportedComparatorDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“wheat seedling variety recognition”
e0“Ablation studies confirm the significant impact of the KCA module and the multi-scale fusion structure on the model's performance”