中草药

一种基于FR-YOLO注意力增强的轻量化中药饮片识别检测方法

PDF下载

中草药 | 数据挖掘与循证医学 2026,57(10): 3902-3911

收起

中草药 |数据挖掘与循证医学 2026 , 57 (10) : 3902 -3911

一种基于FR-YOLO注意力增强的轻量化中药饮片识别检测方法

全屏

于喆源¹, 王晓霞¹, 李晓芳¹, 樊东琴²

作者信息

通讯作者:

王晓霞

作者简介:

于喆源: 于喆源,工程师,从事食品药品检验检测及品质评价。E-mail:305117349@qq.com

A lightweight recognition and detection method for Chinese herbal slices based on FR-YOLO attention enhancement

YU Zheyuan, WANG Xiaoxia, LI Xiaofang, FAN Dongqin

Affiliations

doi: 10.7501/j.issn.0253-2670.2026.10.019

文章导航

摘要

收起

目的改进YOLOv8模型，为中药生产、调剂与教学等实际应用场景提供一种高精度、高效率的中药饮片自动化检测方案。方法以YOLOv8为基线模型，提出轻量化残差深度注意瓶颈模块（residual depthwise-attention Bottleneck，RDA-Bottleneck），替换C2f中的Bottleneck模块，以降低冗余计算并增强通道特征表达；提出频域感知空间注意力模块（frequency-aware spatial attention，FASA），替换YOLOv8的Backbone网络与Neck网络中的Conv模块，以增强检测网络在多尺度特征学习过程中的判别能力；构建包含板蓝根、甘草等10种中药饮片数据集，共8 281张图像，用于评价改进模型的检测性能。结果相较于YOLOv8模型，改进后的模型参数量降低了39.5%，浮点运算量（floating point operations，FLOPs）降低了34.1%，单阈值平均精度mAP50提升了0.2%，多阈值平均精度mAP50-95提升了0.2%。结论改进后的模型在复杂背景与形态多变的中药饮片检测任务中展现出更高的检测精度与推理效率，为中药饮片自动化检测提供了一种高效的新方法。

关键词

中药饮片检测 / YOLOv8 / 轻量化目标检测 / 注意力机制 / 残差深度注意瓶颈模块 / 频域感知空间注意力模块

Abstract

收起

Objective To improve the YOLOv8 model and provide a high-accuracy and high-efficiency automated detection solution for Chinese herbal slices in practical scenarios such as production, dispensing, and teaching. Methods Taking YOLOv8 as the baseline model, a lightweight residual depthwise-attention Bottleneck (RDA-Bottleneck) is proposed to replace the Bottleneck blocks in C2f, reduce redundant computations and enhance the expression of channel features. To strengthen the discriminative capability of the detector during multi-scale feature learning, a frequency-aware spatial attention (FASA) module is introduced to replace the Conv blocks in the Backbone and Neck of YOLOv8. To evaluate the performance of the improved model, a dedicated dataset containing 10 categories of Chinese herbal slices [e.g., Banlangen (Isatidis Radix) and Gancao (Glycyrrhizae Radix et Rhizoma)] is constructed, comprising 8 281 images. Results Compared with YOLOv8, the proposed model reduces parameters by 39.5% and floating point operations (FLOPs) by 34.1%, while improving single-threshold average accuracy mAP50 by 0.2% and multi-threshold average accuracy mAP50-95 by 0.2%. Conclusion The improved model achieves higher detection accuracy and inference efficiency for Chinese herbal slice detection under complex backgrounds and diverse appearances, providing an effective method for automatic detection of Chinese herbal slices.

Key words

Chinese herbal slices detection / YOLOv8 / lightweight object detection / attention mechanism / residual depthwise-attention Bottleneck / frequency-aware spatial attention

引用本文

于喆源, 王晓霞, 李晓芳, 樊东琴. 一种基于FR-YOLO注意力增强的轻量化中药饮片识别检测方法. 中草药, 2026 , 57 (10) : 3902 -3911 . DOI: 10.7501/j.issn.0253-2670.2026.10.019

YU Zheyuan, WANG Xiaoxia, LI Xiaofang, FAN Dongqin. A lightweight recognition and detection method for Chinese herbal slices based on FR-YOLO attention enhancement[J]. Chinese Traditional and Herbal Drugs, 2026 , 57 (10) : 3902 -3911 . DOI: 10.7501/j.issn.0253-2670.2026.10.019

基金

收起

甘肃省药品监督管理局青年科技创新项目 (2024GSMPA034)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

史亚博, 李铭轩, 傅饶, 等. 在线检测技术在中药饮片智能化生产与质量控制中的研究现状与展望[J]. 中国现代中药, 2024, 26(5): 881-888.
王超超, 张先超, 谷正昌, 等. 中药材及饮片检测中人工智能应用探讨[J]. 中国工程科学, 2024, 26(2): 245-254.
周明, 周金海, 张燕群, 等. 中药饮片性状质量智能检测关键技术研究[J]. 世界科学技术—中医药现代化, 2023, 25(5): 1580-1589.
张琴, 郭为安. 深度学习小目标检测算法综述[J]. 计算机应用研究, 2025, 42(10): 2893-2904.
刘晶, 张璐, 刘加峰. 基于EfficientDet算法的易混淆中药饮片识别[J]. 北京生物医学工程, 2025, 44(4): 373-378.
李云阳, 李根, 闫磊. 基于改进YOLOv5的中药饮片缺陷检测算法[J]. 林业机械与木工设备, 2024, 52(5): 71-75.
谷瑞, 宋翠玲, 李元昊. 基于BIM-Res2Net-ICA的中药饮片图像识别模型[J]. 时珍国医国药, 2025, 36(6): 1192-1200.
孙兴, 李杨, 毛天驰, 等. 改进YOLOv8在中药饮片自动识别标注中的研究与应用[J]. 中草药, 2025, 56(1): 216-226.
Varghese R, M S. YOLOv8: A novel object detection algorithm with enhanced performance and robustness [A] // 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS) [C]. Chennai: IEEE, 2024: 1-6.
Paszke A, Gross S, Massa F, et al. PyTorch: An imperative style, high-performance deep learning library [J/OL]. arXiv, (2019-12-13) [2025-12-02]. https://arxiv.org/abs/ 1912.01703
Wang C Y, Yeh I H, Mark Liao H Y. YOLOv9: Learning what you want to Learn using programmable gradient information [A] // Computer Vision-ECCV 2024[C]. Cham: Springer, 2025: 1-21.
Chen H, Chen K, Ding G G, et al. YOLOv10: Real-time end-to-end object detection [A] // Advances in Neural Information Processing Systems 37[C]. Vancouver BC: Neural Information Processing Systems Foundation Inc. (NeurIPS), 2024: 107984-108011.
Khanam R, Hussain M. YOLOv11: An overview of the key architectural enhancements [J/OL]. arXiv, (2024-10-24) [2025-12-02]. https://arxiv.org/abs/2410.17725.
Tian Y J, Ye Q X, Doermann D. YOLOv12: Attention-centric real-time object detectors [J/OL]. arXiv, (2025-02-18) [2025-12-02]. https://arxiv.org/abs/2502.12524
Lei M Q, Li S Q, Wu Y H, et al. YOLOv13: Real-time object detection with hypergraph-enhanced adaptive visual perception [J/OL]. arXiv, (2025-0905) [2025-12-02]. https://arxiv.org/abs/2506.17733
Tian Z, Shen C, Chen H, et al. Fcos: Fully convolutional one-stage object detection [A] // Proceedings of the IEEE/CVF international conference on computer vision [C]. Seoul: IEEE, 2019: 9627-9636.
Feng C J, Zhong Y J, Gao Y, et al. TOOD: Task-aligned one-stage object detection [A] // 2021 IEEE/CVF International Conference on Computer Vision (ICCV) [C]. Montreal QC: IEEE, 2022: 3490-3499.
Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection [A] // 2017 IEEE International Conference on Computer Vision (ICCV) [C]. Venice: IEEE, 2017: 2999-3007.
Hu J, Shen L, Sun G. Squeeze-and-excitation networks [A] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition [C]. Salt Lake City: IEEE, 2018: 7132-7141.
Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module [A] // Computer Vision-ECCV [C]. Cham: Springer, 2018: 3-19.
Wang Q L, Wu B G, Zhu P F, et al. ECA-net: Efficient channel attention for deep convolutional neural networks [A] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [C]. Seattle WA: IEEE, 2020: 11531-11539.

2026年第57卷第10期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.7501/j.issn.0253-2670.2026.10.019

接收时间：2026-01-02
首发时间：2026-09-09

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2026-01-02

基金

作者信息

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/zcy/CN/10.7501/j.issn.0253-2670.2026.10.019

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT