一种基于深度学习的叶菜根部与叶片特性识别方法和系统
By using an improved YOLOv8 network to identify the characteristics of leafy vegetable roots and leaves, the problem of accuracy in identifying root location and leaf characteristics in leafy vegetable processing was solved, improving processing efficiency and identification accuracy while reducing labor costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIANGNAN UNIV
- Filing Date
- 2026-04-24
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, it is difficult to accurately and in real time identify the location of the roots and characteristics of the leaves of leafy vegetables, resulting in low processing efficiency, high labor costs, and problems such as incomplete root removal, incomplete cleaning, and low precision in removing yellow leaves.
A deep learning-based method for identifying the characteristics of leafy vegetable roots and leaves is adopted. By using an improved YOLOv8 network, including Backbone, Neck, VRF-Head and Head networks, features of different resolutions in vegetable images are extracted. Feature fusion, orthogonal task decoupling and dynamic attention processing are then performed to identify the characteristics of leafy vegetable roots and leaves.
It enables effective and accurate identification of the characteristics of leafy vegetable roots and leaves, improving processing efficiency, reducing loss rate, and enhancing identification accuracy and stability.
Smart Images
Figure CN122090439B_ABST