A skeleton extraction method based on a particle swarm algorithm applied to a microfluidic chip
By optimizing threshold segmentation and Canny edge detection using particle swarm optimization, combined with morphological processing, the problem of accurate extraction of rock matrix regions in cast thin sections was solved, providing a foundation for microfluidic chip fabrication.
CN119963557BActive Publication Date: 2025-11-25SANYA MARINE OIL & GAS RESEARCH INSTITUTE NORTHEAST PETROLEUM UNIVERSITY
Patent Information
- Application Number
- CN202510449904.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-11
- Publication Date
- 2025-11-25
- Estimated Expiration
- 2045-04-11
Smart Images
Figure CN119963557B_ABST
Abstract
The application discloses a kind of based on particle swarm algorithm applied to microfluidic chip's skeleton extraction method, comprising the following steps: S1: input two-dimensional rock cast thin section image, and it is preprocessed;S2: preliminary extraction is carried out to rock skeleton area by threshold segmentation of particle swarm algorithm;S3: by the Canny edge detection of particle swarm algorithm, skeleton edge is revised;S4: morphological processing smooth and continuous edge is carried out, and the skeleton extraction of rock cast thin section is completed.The beneficial effects of the present application are: by the pre-processing of two-dimensional rock cast thin section image, then the parameters in threshold segmentation-Canny edge detection are optimized using particle swarm algorithm, and the result is weighted output, so as to realize the accurate extraction of skeleton part in cast thin section, and provide the basis for subsequent microfluidic chip production.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Image border detecting method and system based on particle swarm algorithm
CN108198197A
Road crack detection method based on particle swarm heuristic algorithm
CN118365943A