Comparison of Crack Extraction Performance According to Different Edge Detectors

Abstract

Edges of images contain important information such as form, size, and location of objects. Thus, edge detection is an extremely important factor in image processing. In order to detect such edges, much research has been carried out, and edge detectors such as Sobel, Prewitt, Robert, Canny, and Laplacian of Gaussian (“LoG”) are universally used. This Research compares and analyzes the crack extraction function of each edge detector to automatically detect cracks occurring in concrete structures. In order to do this, simulated crack samples of various widths and contrasts were produced and attached to concrete walls, and crack images were taken from different distances. Cracks were extracted from the images taken using edge detectors like Sobel, Prewitt, Robert, Canny, and LoG, and the crack extraction performance of the edge detectors used were compared and analyzed based on the photographed distance.