The Algorithm of Concrete Surface Crack Detection Based on the Genetic Programming and Percolation Model

Abstract

Because of the impact of the variation in different concrete surface images, such as the heterogeneity of the detection environment, uneven illumination, stains, the block, and water leakage, the existing crack detection algorithms cannot detect the real crack quickly and effectively. In this paper, a genetic algorithm based on genetic programming (GP) and percolation model is proposed. This method involves three steps. First, the cracks are pre-extracted by the image processing model of GP. Second, the crack tip is calculated after the crack skeleton is extracted. With the endpoint as the anchor point, high speed, and high precision percolation are used to detect the cracks with small width accurately. Concurrently, the fracture unit areas are scanned for connection. Finally, the pre-extracted cracks are connected with the cracks detected by the percolation, and the mass interference area is removed to obtain the real cracks on the concrete surface. The simulation results show that the concrete surface crack detection algorithm based on the GP and percolation model can effectively combine both of their advantages. The algorithm proposed in this paper can detect real concrete surface cracks accurately and effectively with strong robustness.