A Novel Crack Segmentation Method based on Morphological-Processing Network

With the wide application of computer vision technology and deep learning theory in engineering, image-based detection of cracks appearing in pipelines, pavements and dams has received more and more attention. Aiming at the problems of high cost, low efficiency and poor detection accuracy in traditional crack detection methods, this paper proposes a crack segmentation method based on a morphological network. In order to improve the identification of cracks with different resolutions, the U-Net network is first used to extract multi-scale features of crack images. In order to eliminate the effect of polarized light on the cracks under different illumination, the extracted crack features are further morphologically processed by a white-top hat transform and a black-bottom hat transform. Finally, a multi-level loss function fusion mechanism is designed to solve the problem of inaccurate segmentation of cracks on a single scale. Extensive experiments are carried out on five open crack datasets: Crack500, CrackTree200, CFD, AEL and GAPs384. The experimental results show that average ODS, OIS, AIU, sODS and sOIS are 75.7%, 73.9%, 36.4%, 52.4% and 52.2%, respectively. Compared with state-of-the-art methods, the proposed method achieves better crack segmentation performance.