Core box corner point extraction and perspective distortion correction method based on multi-scale retinex fusion
By combining multi-scale Retinex fusion, topological constraint Shi-Tomasi and graph cut optimization, thin plate spline transformation and Markov random field, the problems of inaccurate corner point extraction, insufficient image preprocessing, unsuitable perspective correction and low batch processing efficiency in core box image correction in the field are solved. It realizes efficient and accurate core box image correction and batch processing, which meets the digital needs of field core exploration.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZIJIN MINING GRP SOUTHWEST GEOLOGICAL EXPLORATION CO LTD
- Filing Date
- 2026-04-15
- Publication Date
- 2026-06-23
AI Technical Summary
Existing core box image correction technology suffers from problems such as inaccurate corner point extraction, insufficient image preprocessing, unsuitable perspective correction, incomplete verification of correction results, low batch processing efficiency, and non-lightweight algorithms in field exploration, making it difficult to meet the high precision and high efficiency requirements of field core exploration.
Image preprocessing is performed using an iterative algorithm with multi-scale Retinex fusion. Corner points are extracted by combining topological constraints Shi-Tomasi and graph cut optimization. Perspective correction is performed by fusing thin plate spline transformation and Markov random field. Full-dimensional accuracy is verified by Hough transform line fitting and geometric moment invariants, enabling adaptive parameter transfer for batch images and lightweight deployment of the algorithm.
It achieves accurate extraction of core box corner points and efficient correction of image distortion, ensuring the full-dimensional accuracy and stability of the correction results, improving batch processing efficiency, and enabling the algorithm to be deployed and applied on field edge equipment, thus meeting the digital processing needs of field core exploration.
Smart Images

Figure CN122023206B_ABST
Abstract
Citation Information
Patent Citations
Rock core photograph automatic correction and cutting method based on YOLOv8-seg and perspective transformation
CN121707887A