Robust Image-based Crack Detection in Concrete Structures Images using Multi-Scale Enhancement and Visual Features

Abstract

In order to improve the robustness of the crack detection in the complex background, a new crack detection framework based on multi-scale enhancement and visual features is developed. Firstly, to deal with the effect of low contrast, a multi-scale enhancement method using guided filter and gradient information is proposed to get the enhanced image. Then, the adaptive threshold algorithm is used to obtain the binary image. Finally, the combination of morphological processing and visual features are adopted to purify the cracks. The experimental results with different images of real concrete surfaces demonstrate the high robustness and validity of the developed technique.