Auto-associative Neural Network Based Concrete Crack Detection
Crack is an important sign to indicate the health of the concrete structures. It is mandatory to detect the cracks in the concrete structures. This paper presents a method for automatic detection of concrete cracks. Auto-associative neural network is used to detect the cracks. Initially, the necessary features are extracted from the input images which is given to the training algorithm to train the system. The experimental output produces reliable results in terms of training and testing accuracies.
KeywordsConcrete crack Crack detection Classification Auto-associative neural network
The authors wish to acknowledge the Science and Engineering Research Board, Department of Science and Technology of the Indian Government for the financial support (YSS/2015/001196) provided for carrying out this research.
- 5.Cubero-Fernandez, A., Rodriguez-Lozano, F.J., Villatoro, R., Olivares, J., Palomares, J.M.: Efficient pavement crack detection and classification. EURASIP J. Image Video Process 39 (2017). https://doi.org/10.1186/s13640-017-0187-0
- 9.Marques, A.S., Correia, P.L.: Automatic Road Pavement Crack Detection Using a Support Vector Machine. Proceedings of Conference on Telecommunications—ConfTele, Castelo Baranco, Portugal (2013)Google Scholar