Related Experiment Video
Updated: Jun 8, 2026
04:36
Tea Aroma Analysis Based on Solvent-Assisted Flavor Evaporation Enrichment
Published on: May 26, 2023
Research on target recognition method for machine-plucked fresh tea leaves based on improved YOLOv11
Xinyong Shi1, Wenguang Zheng2, Rongyang Wang3
1School of Mechanical Engineering & Automation, University of Science and Technology Liaoning, Anshan, 114000, China.
Scientific Reports
|June 6, 2026
Summary
This study introduces YOLOv11-MSC, an improved object detection model for enhanced tea leaf sorting. It achieves high accuracy in detecting and classifying tea leaves, even with occlusion, making it suitable for real-time applications.
Area of Science:
- Computer Vision
- Agricultural Technology
- Machine Learning
Background:
- Multi-stage singulation of machine-plucked tea leaves faces challenges like partial occlusion and small object detection.
- Accurate recognition and classification are crucial for efficient tea leaf sorting and grading.
Purpose of the Study:
- To develop an improved object detection model for enhanced tea leaf sorting.
- To address challenges in detecting and classifying tea leaves in low-occlusion arrangements.
Main Methods:
- Proposed an improved YOLOv11-based detection model (YOLOv11-MSC).
- Incorporated multi-scale edge enhancement, convolution-attention fusion, and spatial attention optimization.
- Conducted ablation studies, comparative analyses with attention mechanisms and mainstream models.
Main Results:
- YOLOv11-MSC achieved a mean average precision (mAP@0.5) of 90.1%.
- The model maintains a lightweight architecture with 2.89 M parameters and 6.4 GFLOPs.
- Demonstrated excellent detection accuracy and computational efficiency.
Conclusions:
- YOLOv11-MSC shows strong performance in detecting and classifying tea leaves, even with occlusion.
- The model's efficiency makes it highly suitable for real-time tea leaf grading systems.
- The proposed enhancements effectively improve feature extraction and localization capabilities.
