About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Cognitive Computing and Cyber Physical Systems. 5th EAI International Conference, IC4S 2024, Bhimavaram, India, April 5–7, 2024, Proceedings, Part-I

Research Article

Assessment of the Decay of Monuments Using Deep Learning and CNN

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-77075-3_28,
        author={P. Ramani and S. Meena and S. Sugumaran},
        title={Assessment of the Decay of Monuments Using Deep Learning and CNN},
        proceedings={Cognitive Computing and Cyber Physical Systems. 5th EAI International Conference, IC4S 2024, Bhimavaram, India, April 5--7, 2024, Proceedings, Part-I},
        proceedings_a={IC4S},
        year={2025},
        month={2},
        keywords={Crack Detection Deep Learning Technique Histogram Convolutional Neural Network},
        doi={10.1007/978-3-031-77075-3_28}
    }
    
  • P. Ramani
    S. Meena
    S. Sugumaran
    Year: 2025
    Assessment of the Decay of Monuments Using Deep Learning and CNN
    IC4S
    Springer
    DOI: 10.1007/978-3-031-77075-3_28
P. Ramani1, S. Meena2, S. Sugumaran3,*
  • 1: SRM Institute of Science and Technology
  • 2: St. Joseph’s College of Engineering
  • 3: Vishnu Institute of Technology
*Contact email: sugumaran.s@vishnu.edu.in

Abstract

In any culture, the monuments are significant part of the heritage, the witnesses of the history that have been existing upto the current era. Since these monuments are inherited from previous generations, it is essential to preserve them, which can be done by monitoring the monuments. In the proposed method, the deep learning technique of convolutional neural networks [CNN] is used to figure out the reasons that cause the decay of monuments and thereby figuring out the causes that damage them. Using the CNN technique, 20000 images which are resized to 256 × 256 data set are used to train and test the Convnet, that has 3 layers of 32 × 3 layers of filters. The proposed work detects the cracks that are present in the monuments, that are caused by various factors including weather and aging. Weather and aging also causes moss and loss of stone. In this work, cracks are identified using CNN with an accuracy of 97.5%, and histogram distribution is used to detect the cracks. In the proposed work, the Keras library is used to create the convolutional neural networks.

Keywords
Crack Detection Deep Learning Technique Histogram Convolutional Neural Network
Published
2025-02-09
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-031-77075-3_28
Copyright © 2024–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL