Application of Deep Convolution Neural Network in Crack Identification

Abstract

The surface crack of structure is an important sign to evaluate the safety of structure. In order to ensure the safety and reliability of the building structure, it is necessary to detect and monitor the surface cracks of the structure. Traditional artificial surface inspections are time-consuming because inspectors have different experience and knowledge, which can lead to misjudgments. Based on the basic framework of four deep convolution neural networks, their classifiers are reconstructed. To fully train these networks and simulate crack images taken in various situations in life, image enhancement techniques are used to extend the dataset. After training, compared with the established shallow network structure, they can learn the feature information in the image more fully, and finally improve the accuracy. After further verification, it is found that one of the models can achieve an accuracy of 96.5%. To verify the universality and validity of the model, two cross-datasets experiments were performed. The experimental results show the validity of the model, and the diagnostic precision is 98.23% and 99.04%, respectively.