Intelligent characterization of complex cracks in strain-hardening cementitious composites based on generative computer vision

This paper presents a generative artificial intelligence (AI) approach to generate images of strain-hardening cementitious composite (SHCC) with complex crack patterns such as dense microcracks. This approach is developed to address the challenge of lacking data for training deep learning models used to automatically measure cracks in SHCC. The development of the approach is based on a framework which results in a hybrid generative adversarial network (HGAN) that seamlessly integrates a deep convolutional generative adversarial network (DCGAN) for generating images and a conditional generative adversarial network (CGAN) for labelling images. From the results, it was found that this approach provided high-quality labelled images automatically, and using these images significantly improved the accuracy of the deep learning models for measuring cracks in SHCC. The F1 score and Intersection Over Union (IOU) for crack segmentation reached 0.982 and 0.980, respectively. This approach will significantly promote crack measurement for SHCC materials and structures.