Complex background crack image candidate optimization, continuous repair and quantification method and system

By using a dual-threshold and skeleton length-area ratio screening method, the problems of false target interference and insufficient continuity in crack images under complex backgrounds are solved, and stable extraction and parameter quantification of crack candidate regions are achieved, thereby improving the accuracy and interpretability of crack image analysis.

CN122244057APending Publication Date: 2026-06-19QINGDAO UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
QINGDAO UNIV OF TECH
Filing Date
2026-05-25
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

In complex contexts, existing technologies struggle to accurately identify crack images, exhibiting false target regions, discontinuous slender crack structures, and a lack of stable conversion mechanisms from segmentation results to engineering parameters.

Method used

Initial candidate regions are generated by linking dual thresholds. The region is then screened by combining the length and area ratio of the skeleton to perform local repair of slender cracks. Skeletonization and distance transformation are then performed to quantify crack parameters.

Benefits of technology

It improves the stability and continuity of crack candidate regions, enhances the continuous representation of the main trunk of slender discontinuous cracks, and strengthens the stability and engineering interpretability of crack quantification results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122244057A_ABST
    Figure CN122244057A_ABST
Patent Text Reader

Abstract

This invention discloses a method and system for candidate optimization, continuous repair, and quantization of crack images in complex backgrounds, belonging to the field of computer vision and digital image processing technology. To address the problems of crack recognition in complex backgrounds being susceptible to false target interference, discontinuous cracks, and difficulty in stable quantification of engineering parameters, this invention obtains the crack response probability map and determines a linked dual threshold. It retains low-threshold regions connected to the high-threshold region to generate initial candidate regions. The ratio of skeleton length to area is calculated as a thinness index for screening. Skeleton endpoints are extracted, and bridging pixel paths are generated to achieve local repair when the endpoints of different connected domains meet preset multi-condition constraints. The repaired region is then skeletonized to construct a graph structure. The number of original skeleton segments, the total number of cracks, and the total length are statistically analyzed. Width statistics and direction parameters are calculated by sampling along the skeleton using distance transformation. This effectively suppresses false targets in complex backgrounds, accurately connects discontinuous cracks, and outputs stable, accurate, and interpretable engineering parameters.
Need to check novelty before this filing date? Find Prior Art