ARTIFICIAL INTELLIGENCE TECHNOLOGIES FOR CRACK DETECTION IN CULTURAL HERITAGE OBJECTS

T. V. Karpeta, E. V. Kazantseva

Abstract


Driven by the need for systematic structural health monitoring of cultural heritage sites to ensure timely defect identification, this study employs neural network-based computer vision techniques. We details the development and annotation of a dataset comprising images of cracks in historical buildings. Particular emphasis is placed on data acquisition and preprocessing, as these stages significantly influence subsequent model performance metrics. The training results for both models are presented, followed by a comparative analysis. Finally, a cascaded pipeline integrating detection and segmentation is proposed to enhance the accuracy and reliability of defect identification.

Keywords


neural networks; object detection; image segmentation; cultural heritage objects; cracks; YOLOv11; U-Net

Full Text:

PDF

References


Sirota A.A., Dryuchenko M.A., Ivankov A.Y. Steganalysis of Digital Images Using Shallow and Deep Machine Learning Methods: Known Approaches and New Solutions. Proceedings of VSU, Series: Systems Analysis and Information Technologies, 2021, no. 1, pp. 33-52. DOI: 10.17308/sait.2021.1/3369.

Krylov S.A., Kashevarova G.G. Automation of the Process of Assessing the Technical Condition of Exterior Walls of Brick Buildings Using Machine Learning. Herald of Daghestan State Technical University. Technical Sciences, 2025, vol. 52, no. 3, pp. 61-70. DOI: 10.21822/2073-6185-2025-52-3-61-70.

Koul A., Ganju S., Kasam M. Practical Deep Learning for Cloud, Mobile, and Edge. Sebastopol, O'Reilly Media, 2019.

Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Lecture Notes in Computer Science, 2015, vol. 9351, pp. 234-241. DOI: 10.1007/978-3-319-24574-4_28

Protopapadakis E., Voulodimos A., Doulamis A., Doulamis N., Stathaki T. Automatic Crack Detection for Tunnel Inspection Using Deep Learning and Heuristic Image Post-Processing. Applied Intelligence, 2019, vol. 49, no. 7, pp. 2793-2806. DOI: 10.1007/s10489-018-01396-y.


Refbacks

  • There are currently no refbacks.


 Save