使用YOLOv11-PFT模型在茶中的微杂质的非破坏性检测
Zejun Wang1,2,3, Chun Wang2,4, Wenxia Yuan2
1College of Agronomy and Biotechnology, Yunnan Agricultural University, Kunming, China.
NPJ science of food
|January 10, 2026
概括
一个新的深度学习模型,YOLOv11-PFT,有效地检测出微观的茶叶污染物. 这一进步提高了茶叶生产的食品安全和质量控制.
科学领域:
- 食品科学与技术 食品科学与技术
- 计算机科学 计算机科学
- 人工智能的人工智能
背景情况:
- 微观杂质对茶叶质量构成重大挑战,因为目前的检测方法不足.
- 现有的技术无法识别微观污染物,从而损害了产品的完整性和消费者安全.
研究的目的:
- 开发一种先进的深度学习模型,以准确有效地检测茶叶中的微观污染物.
- 创建一个轻量级和高性能解决方案,用于茶叶行业的自动化食品安全和质量控制.
主要方法:
- 开发YOLOv11-PFT,这是一个新的深度学习架构,集成了Powerful-IoU损失,FasterNet和三重注意力模块.
- 增强特征提取,检测精度和模型效率,用于微观污染物识别.
主要成果:
- YOLOv11-PFT实现了99.16%的微观茶叶污染物的检测准确度.
- 该模型展示了高性能指标 (精度,回忆,F1得分,mAP接近98.7-99.2%),低计算成本 (5.5 GFLOPs),高推断速度 (340.6 FPS) 和紧的模型大小 (5.0 MB).
- 在准确性方面表现优于七个基准模型.
结论:
- YOLOv11-PFT为茶叶中的微观污染物检测提供了强大而高效的解决方案.
- 该模型支持食品安全的自动化,智能质量控制和农业环境中的边缘设备的潜在部署.
更多相关视频
04:36Author Spotlight: Exploring Tea Aroma Using Solvent-Assisted Flavor Evaporation Technique
Published on: May 26, 2023
4.2K
08:43PTR-ToF-MS Coupled with an Automated Sampling System and Tailored Data Analysis for Food Studies: Bioprocess Monitoring, Screening and Nose-space Analysis
Published on: May 11, 2017
12.9K
相关概念视频
01:18Effects of EDTA on End-Point Detection Methods
611
Different methods, such as visual observance of metal-ion indicators, spectroscopic techniques, and potentiometric methods, can determine the endpoint of an EDTA titration.
In the visual method, metal-ion indicators (metallochromic dyes), which have distinct colors in their free and complex forms, are added to the mixture to signal the titration's end point. They form stable complexes with metal ions, but these complexes are weaker than the corresponding metal–EDTA complexes. As a...
In the visual method, metal-ion indicators (metallochromic dyes), which have distinct colors in their free and complex forms, are added to the mixture to signal the titration's end point. They form stable complexes with metal ions, but these complexes are weaker than the corresponding metal–EDTA complexes. As a...
611
01:19Precipitation Titration: Endpoint Detection Methods
4.7K
In argentometric precipitation titrations, endpoints can be detected visually by the Mohr, Volhard, and Fajans methods. In the Mohr method, adding a soluble chromate indicator gives an initial yellow color to the analyte solution. As the titrant is added, the first excess of silver ions forms a red silver chromate precipitate, marking the endpoint. The solution pH should be maintained at about 8 by adding solid CaCO3.
In the Volhard method, a standard excess of AgNO3 is first added to the...
In the Volhard method, a standard excess of AgNO3 is first added to the...
4.7K