Answers are grounded in this paper and cite their sources.
Machine learning enhances crack detection in structural images, indicating various risk levels and cost efficiencies.
This paper introduces a machine learning based approach for cracks detection and classification on IC image processing. The process involve image preprocessing, segmentation of crack and the analysis of its characteristics (length, thickness). All these results show that Image 2 has the highest structural risk for a dominant crack with significant thickness and length. Image 3 was flagged for high variability in crack thickness, suggesting isolated risk, while Image 1 was considered low risk with small and regular crack shapes. The research identifies advantages of AI in structural inspection including efficiencies and cost savings that supplement passive non-destructive methodologies. The limitations include the fact that two dimensional images cannot measure crack depth. Future work could involve combining 3D imaging with IoT installations for further analysis. This study provides valuable insights into the use of new technologies to enhance the structural inspection process.
No takes yet. Share an insight, caveat, or question.
Mititelu et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: