A Curated Dataset for Crack Image Analysis: Experimental Verification and Future Perspectives

Identificador:  imarina:9380775

Handle: https://hdl.handle.net/20.500.11797/imarina9380775

Autores:  Okran, Ammar M; Abdel-Nasser, Mohamed; Rashwan, Hatem A; Puig, Domenec

Resumen:
Most crack image datasets are developed for crack segmentation or detection. They cannot be used to train a deep learning model to detect and segment cracks simultaneously. Most of existing datasets do not include a very accurate annotation. Besides, some crack images cannot be used to train deep learning models because of their inferior quality. In this paper, we propose a promising curated crack image dataset that allows the development of crack segmentation, detection, and classification on the same set of images simultaneously. There is no dataset for road crack that involves detection and segmentation tasks to the best of our knowledge. The current version of the curated database consists of 506 images derived from the RDD2020 dataset taken from multi-countries (Japan, Czech, and India). We use the curated dataset to build different deep learning-based crack detection and segmentation methods. Our experiments demonstrate that the proposed dataset yields promising results for crack detection and segmentation.