一种用于浮游生物智能分析的光学成像方法、系统
By setting microscope system parameters and fluid flow control, combined with adaptive image processing and a lightweight model, the problem of low detection accuracy in phytoplankton imaging was solved, achieving efficient and automated algae identification and population analysis.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAMEN UNIV OF TECH
- Filing Date
- 2026-06-12
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies suffer from low detection accuracy in phytoplankton imaging due to limited depth of field and random cell flipping, making it difficult to accurately identify phytoplankton and analyze population dynamics.
By setting the depth of field, numerical aperture of the objective lens, and total magnification of the microscope system, and combining the liquid flow generated by the sheath fluid injection pump, the flow rate of the liquid flow is dynamically adjusted to control the orientation of algal cells in the microscope field of view. Adaptive threshold segmentation and morphological operations are used to segment algal cells, and a lightweight large model is used for identification.
It achieves efficient, automated, and high-precision identification of phytoplankton, reduces the need for frequent focusing, and improves detection efficiency and identification accuracy.
Smart Images
Figure CN122409436A_ABST