Defective Wheat Kernel Recognition Using EfficientNet with Attention Mechanism and Multi-Binary Classification
Open Access
- 26 January 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (3) , 1247
Abstract
As a globally significant food crop, the assessment of wheat quality is essential for ensuring food security and enhancing the processing quality of agricultural products. Conventional methods for assessing wheat kernel quality are often inefficient and markedly subjective, which hampers their ability to accurately distinguish the complex and diverse phenotypic characteristics of wheat kernels. To tackle the aforementioned issues, this study presents an enhanced recognition method for defective wheat kernels, based on the EfficientNet-B1 architecture. Building upon the original EfficientNet-B1 network structure, this approach incorporates the lightweight attention mechanism known as CBAM (Convolutional Block Attention Module) to augment the model’s capacity to discern features in critical regions. Simultaneously, it modifies the classification head structure to facilitate better alignment with the data, thereby enhancing accuracy. The experiment employs a self-constructed dataset comprising five categories of wheat kernels—perfect wheat kernels, insect-damaged wheat kernels, scab-damaged wheat kernels, moldy wheat kernels, and black germ wheat kernels—which are utilized for training and validation purposes. The results indicate that the enhanced model attains a classification accuracy of 99.80% on the test set, reflecting an increase of 2.6% compared to its performance prior to the enhancement. Furthermore, the Precision, Recall, and F1-score all demonstrated significant improvements. The proposed model achieves near-perfect performance on several categories under controlled experimental conditions, with particularly high precision and recall for scab-damaged and insect-damaged kernels. This study demonstrates the efficacy of the enhanced EfficientNet-B1 model in the recognition of defective wheat kernels and offers novel technical insights and methodological references for intelligent wheat quality assessment.Keywords
Funding Information
- Natural Science Foundation of Shandong Province (ZR2023MA076)
This publication has 31 references indexed in Scilit:
- Interactive effects of irrigation and planting density on photosynthetic performance and yield of winter wheatField Crops Research, 2025
- Optimizing the water-energy-food nexus in dryland winter wheat systems on the loess plateauAgricultural Water Management, 2025
- Advancing deep learning for automated stroke detection: a reviewBrain Hemorrhages, 2025
- The influence of organic matter in paddy soil on the profiles of minerals and toxic heavy metals in rice grainsCereal Research Communications, 2025
- Forecasting the mid-and-long-term crop evapotranspiration for winter wheat in China using combination models based on public weather forecast dataComputers and Electronics in Agriculture, 2025
- Crop Seeds Classification Using Traditional Machine Learning and Deep Learning Techniques: A Comprehensive SurveySN Computer Science, 2024
- Chemical control of wheat sunn pest, Eurygaster integriceps, by UAV sprayer and very low volume knapsack sprayerPhytoparasitica, 2024
- Deep Learning‐Based Classification of Image Data Sets Containing 111 Different SeedsAdvanced Theory and Simulations, 2023
- Fast and accurate wheat grain quality detection based on improved YOLOv5Computers and Electronics in Agriculture, 2022
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019