基于视觉 Transformer 的马铃薯薯形与大小自动分级
Automatic grading of potato shape and size based on visual Transformer
樊宏鹏 1于鹏飞 1杨森2
作者信息
- 1. 兰州资源环境职业技术大学信息工程学院,甘肃兰州 730021
- 2. 甘肃农业大学机电工程学院,甘肃兰州 730070
- 折叠
摘要
[目的]解决基于人工特征设计分级方法精度低、鲁棒性差的 问题.[方法]提 出 了 一种强泛化的Transformer薯形与大小自动分级方法.基于Transformer模型构建2个PotatoViT模型,并完成马铃薯薯形分级和大小分级任务;利用迁移策略和数据增广方法训练出鲁棒性分级模型;通过测试集定量分析,验证了研究所提方法在马铃薯分级中的有效性.[结果]PotatoViT模型对薯形分级的准确率和模型F1得分分别为96.36％,94.75％,对大小分级的准确率和模型F1得分分别为89.66％,85.16％,分级精度优于VGG16、ResNet50和 MobileNetV3网络模型.[结论]研究所提方法对马铃薯薯形与大小的准确、实时检测是可行的.
Abstract
[Objective]Aiming at the problems of low accuracy and poor robustness in the previous classification methods based on artificial features.[Methods]A strong generalization automatic classification method of potato shape and size was proposed in this study.First,two potato ViT models were built based on Transformer model to complete potato shape grading and size grading tasks in parallel.Secondly,a robust model was trained by using migration strategy and data augmentation method.Finally,the effectiveness of this method in potato grading was verified by quantitative analysis of test sets.[Results]The experimental results show that the potato ViT model achieves 96.36％and 94.75％for potato shape classification,and 89.66％and 85.16％for size grading in terms of accuracy and μF1 index.The classification accuracy was better than VGG16,ResNet50 and MobileNetV3 network models.[Conclusion]The results shows that it is feasible to apply the proposed method for the real-time and accurate detection of potato shape and size.The results of this study can provide theoretical and technical support for potato intelligent grading.
关键词
马铃薯/薯形/大小/分级/TransformerKey words
potatoes/shape/size/grading/Transformer引用本文复制引用
基金项目
甘肃省教育厅高校教师创新基金项目(2023A-226)
兰州资源环境职业技术大学科研能力提升项目(X2023A-11)
出版年
2024
国家科技期刊平台
NSTL
万方数据