Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179647,
        author = {Ved Waje and Maanav Valecha and Nupur Pathare},
        title = {Indian Heritage Preservation using Crack detection Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {7411-7419},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179647},
        abstract = {Preserving historical monuments is essential 
to protect cultural heritage, especially in a country such 
as India, which has a rich history of architectural 
landmarks. This research introduces an AI-based 
system for detecting cracks in heritage structures using 
deep learning and computer vision. The proposed 
system incorporates the Roboflow 3.0 Instance 
Segmentation Model, based on the COCO architecture, 
within a Streamlit web application. By applying 
advanced image processing and segmentation methods, 
the system accurately identifies structural cracks and 
marks them with bounding boxes and heatmaps. The 
application allows users to analyze multiple images at 
once, providing results in under one second per image. 
Users can adjust detection settings, select from different 
pretrained models, and download the processed images 
for further examination. A feedback mechanism helps 
improve the accuracy of the model over time, making 
the system adaptable to different types of structural 
damage. This approach improves the efficiency and 
reliability of heritage conservation by enabling early 
detection of cracks, supporting timely maintenance and 
restoration efforts.},
        keywords = {Crack Detection, Heritage Preservation,  Deep learning, COCO Architecture, Computer Vision.},
        month = {May},
        }