This dataset contains crack images and corresponding annotated ground truth masks. This data was used to train, validate, and test a deep convolutional neural network to detect crack pixels on images taken as input for the digital image correlation (DIC) method. For more information about the trained network, please refer to our publication at this link. The source codes to reproduce the results are shared at this link. Please cite the following articles: [1] Rezaie, A., Achanta, R., Godio, M., & Beyer, K. (2020). Comparison of crack segmentation using digital image correlation measurements and deep learning. Construction and Building Materials, 261, 120474. doi:https://doi.org/10.1016/j.conbuildmat.2020.120474 [2] Rezaie, A., Godio, M., & Beyer, K. (2021). Investigating the cracking of plastered stone masonry walls under shear–compression loading. Construction and Building Materials, 306, 124831. doi:https://doi.org/10.1016/j.conbuildmat.2021.124831