基于机器视觉的SEM下岩石断面孔隙变化自动识别计算方法
The automatic identification and calculation of rock cross-sectional pore changes using machine vision technology under SEM solves the problems of insufficient accuracy and low automation in pore segmentation and edge extraction. It achieves accurate and efficient automatic identification of rock pore changes and is applicable to rock samples with different lithologies and pore development levels.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HOHAI UNIV
- Filing Date
- 2025-11-14
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for identifying and calculating pore changes in rock cross-sections under SEM suffer from insufficient accuracy in pore segmentation and edge extraction, as well as low levels of automation and integration. This results in the accuracy and efficiency of pore structure analysis failing to meet engineering requirements.
A machine vision-based approach was adopted to acquire rock cross-sectional image data through scanning electron microscopy. The machine vision SEM porosity intelligent quantification cloud platform was then used to perform image sub-region division, two-phase porosity threshold inversion, pore edge gradient enhancement, and topological structure analysis, thereby achieving automated identification and calculation of pore parameters.
It enables accurate and efficient automatic identification and calculation of changes in rock cross-section pores, improves the accuracy and stability of pore parameter analysis, adapts to rock samples with different lithologies and pore development levels, and meets the needs of engineering fields for dynamic monitoring of rock pores.
Smart Images
Figure CN121505339B_ABST