What does this research mean for the field?

In crack detection for historical structures, image processing techniques offer advantages for interpretable geometric analysis, while deep learning methods provide superior automation and feature learning, though both are currently limited by a lack of heritage-specific datasets and domain shift. Novelty: ClaimNovelty.SYNTHESIS. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This review aims to assess recent advancements in image processing and deep learning techniques for detecting cracks in historic structures.

June 28, 2026npj Heritage ScienceOpen Access

Application of image processing and deep learning in crack detection of historical structures: a systematic review

View Full Paper

Ask AI

Bookmark

Authors

WFWeiwu Feng SCSiwen Cao JYJianfeng Yao

Discussion

Member takes

Overview

Systematic review evaluates image-based crack detection technologies in historical structures, suggesting future research directions.

Key Points

This review aims to assess recent advancements in image processing and deep learning techniques for detecting cracks in historic structures.
Conducted a systematic review based on the PRISMA framework.
Summarized developments in crack identification, segmentation, and geometric quantification.
Evaluated the performance of IPT- and DL-based methods in historic structures.
IPT-based methods excel in geometric analysis and multi-source sensing integration.
DL-based methods show superior automation and adaptability to complex backgrounds.
Challenges include limited heritage-specific datasets affecting the applicability of techniques.

Cite This Study

Feng et al. (2026) studied this question.

synapsesocial.com/papers/6a40ba8861bb0a67205c66e2 https://doi.org/10.1038/s40494-026-02744-9

View Full Paper

Ask AI

Bookmark

June 28, 2026npj Heritage ScienceOpen Access

Application of image processing and deep learning in crack detection of historical structures: a systematic review

View Full Paper

Ask AI

Bookmark

Authors

WFWeiwu Feng SCSiwen Cao JYJianfeng Yao

Discussion

Member takes

Overview

Systematic review evaluates image-based crack detection technologies in historical structures, suggesting future research directions.

Key Points

This review aims to assess recent advancements in image processing and deep learning techniques for detecting cracks in historic structures.
Conducted a systematic review based on the PRISMA framework.
Summarized developments in crack identification, segmentation, and geometric quantification.
Evaluated the performance of IPT- and DL-based methods in historic structures.
IPT-based methods excel in geometric analysis and multi-source sensing integration.
DL-based methods show superior automation and adaptability to complex backgrounds.
Challenges include limited heritage-specific datasets affecting the applicability of techniques.

Cite This Study

Feng et al. (2026) studied this question.

synapsesocial.com/papers/6a40ba8861bb0a67205c66e2 https://doi.org/10.1038/s40494-026-02744-9

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark