2020/05/21 by Yu Song, Zilong Huang, Song, Yu +7
Engineering · #Computer Vision and Pattern Recognition (cs.CV) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Geophysical Methods and Applications #Infrastructure Maintenance and Monitoring #Machine Learning (cs.LG) #Non-Destructive Testing Techniques
paper · pdf · doi:10.48550/arxiv.2005.10434
openalex publication_date 2020/05/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The standard petrography test method for measuring air voids in concrete (ASTM C457) requires a meticulous and long examination of sample phase composition under a stereomicroscope. The high expertise and specialized equipment discourage this test for routine concrete quality control. Though the task can be alleviated with the aid of color-based image segmentation, additional surface color treatment is required. Recently, deep learning algorithms using convolutional neural networks (CNN) have achieved unprecedented segmentation performance on image testing benchmarks. In this study, we investigated the feasibility of using CNN to conduct concrete segmentation without the use of color treatment. The CNN demonstrated a strong potential to process a wide range of concretes, including those not involved in model training. The experimental results showed that CNN outperforms the color-based segmentation by a considerable margin, and has comparable accuracy to human experts. Furthermore, the segmentation time is reduced to mere seconds.