Protecting Historical Treasures: Deep Learning for Structural Health Assessment

Preserving ancient monuments not only stands as evidence of the collective history but is also a fundamental aspect of conserving cultural heritage. As these architectural wonders age, they become susceptible to the encroachment of moss and the development of structural cracks, jeopardizing their overall integrity. In the present era of advanced technology, the use of deep learning algorithms for the automatic detection and classification of cracks, moss, and seepages arises as a promising solution. This study explores the deployment of deep learning techniques, particularly Single Shot Multibox Detector (SSD), for the identification and localization of moss and cracks on ancient monuments. The proposed work investigates the effectiveness of these algorithms in analyzing high-resolution images, offering a non-invasive and precise means of monitoring structural defects and biological growth with the help of the dataset Indian Ancient Monuments (Kaggle). To delve into the architectural significance of these structures, which underlines the importance of their preservation. The deep learning models, trained on the dataset, exhibit remarkable proficiency in distinguishing between normal surfaces and those bearing cracks, moss, and seepages. We assess the model’s performance through metrics such as accuracy, precision, recall, and F1-score. The proposed work is compared with the state-of-the-art techniques like SVM, KNN, CNN, and Random Forest in the field. Furthermore, this study provides a glimpse into potential applications of the developed models, including real-time monitoring and alert systems for heritage conservationists and preservation authorities. By amalgamating advanced deep learning technology SSD with heritage preservation, this research underscores a proactive approach to safeguarding ancient monuments with the accuracy of detecting cracks, moss, and seepages as 96.9%, 97.5% and 97.5% respectively. The implications extend beyond the technical realm, transcending into cultural heritage and conservation practices, thereby ensuring the longevity of these historical treasures.

Authors

Institutions

Publication Details

Journal
International Journal of Basic and Applied Sciences
Published
2025-09-25
DOI
https://doi.org/10.14419/zc5xbc77
Primary Topic
Infrastructure Maintenance and Monitoring
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Protecting Historical Treasures: Deep Learning for Structural Health Assessment

A. Umamageswari, M. Snehapriya
International Journal of Basic and Applied Sciences
Infrastructure Maintenance and Monitoring
article

Protecting Historical Treasures: Deep Learning for Structural Health Assessment

A. Umamageswari, M. Snehapriya
article en

Abstract

Preserving ancient monuments not only stands as evidence of the collective history but is also a fundamental aspect of conserving cultural heritage. As these architectural wonders age, they become susceptible to the encroachment of moss and the development of structural cracks, jeopardizing their overall integrity. In the present era of advanced technology, the use of deep learning algorithms for the automatic detection and classification of cracks, moss, and seepages arises as a promising solution. This study explores the deployment of deep learning techniques, particularly Single Shot Multibox Detector (SSD), for the identification and localization of moss and cracks on ancient monuments. The proposed work investigates the effectiveness of these algorithms in analyzing high-resolution images, offering a non-invasive and precise means of monitoring structural defects and biological growth with the help of the dataset Indian Ancient Monuments (Kaggle). To delve into the architectural significance of these structures, which underlines the importance of their preservation. The deep learning models, trained on the dataset, exhibit remarkable proficiency in distinguishing between normal surfaces and those bearing cracks, moss, and seepages. We assess the model’s performance through metrics such as accuracy, precision, recall, and F1-score. The proposed work is compared with the state-of-the-art techniques like SVM, KNN, CNN, and Random Forest in the field. Furthermore, this study provides a glimpse into potential applications of the developed models, including real-time monitoring and alert systems for heritage conservationists and preservation authorities. By amalgamating advanced deep learning technology SSD with heritage preservation, this research underscores a proactive approach to safeguarding ancient monuments with the accuracy of detecting cracks, moss, and seepages as 96.9%, 97.5% and 97.5% respectively. The implications extend beyond the technical realm, transcending into cultural heritage and conservation practices, thereby ensuring the longevity of these historical treasures.

International Journal of Basic and Applied SciencesVol. 14(5)
SRM Institute of Science and Technology (IN), SRM Dental College (IN)
Openalex Percentile: Top 73%
Infrastructure Maintenance and Monitoring
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.