Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 20, 2026Global HeritageOpen Access

Deep learning for crack detection in cultural heritage sites: a systematic review

View Full Paper
Ask AI
Bookmark
Share

Authors

AOAndré Luiz Carvalho OttoniLOLara Toledo Cordeiro Ottoni

Discussion

Loading...

Member takes

Overview

Systematic review identifies AI methods, datasets, and challenges in crack detection for cultural heritage sites.

Key Points

  • This paper aims to present a systematic literature review on the use of deep learning for crack detection in cultural heritage sites.
  • Analyzed 26 papers published from 2020 to 2025 in the Scopus database.
  • Addressed five research questions regarding methods, datasets, and case studies.
  • Identified most commonly used deep learning methods and countries studied.
  • Identified six publicly available datasets for training AI models in crack detection.
  • YOLO was the most frequently adopted deep learning method.
  • Seven future challenges were presented, including improving dataset quality and generalization capabilities.

Cite This Study

Ottoni et al. (2026) studied this question.

synapsesocial.com/papers/6a362de1db0793dc1a535d72https://doi.org/10.1016/j.gloher.2026.100002
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Artificial Intelligence at the Interface between Cultural Heritage and Photography: A Systematic Literature Review2024 · 30 citations
  2. 2Crack morphology and its correlation with ground materials used in paintings by Danish portrait painter Jens Juel2024 · 4 citations
  3. 3Artificial intelligence-assisted visual inspection for cultural heritage: State-of-the-art review2024 · 154 citations
  4. 4Efficient on-device damage segmentation for cultural heritage using pruning and knowledge distillation2025 · 8 citations