Deep learning-based automated image segmentation for concrete petrographic analysis. (September 2020)

• Record Type: Journal Article
• Authors: Song, Yu; Huang, Zilong; Shen, Chuanyue; Shi, Humphrey; Lange, David A.
• Is Part Of: Cement and concrete research. Volume 135(2020)
• Publication Date: 2020-09
• Subjects: Concrete petrography -- Machine learning -- Deep learning -- Semantic segmentation -- Hardened air void analysis; Cement -- Periodicals; Cement -- Research -- Periodicals; Concrete -- Periodicals; Concrete -- Research -- Periodicals; Ciment -- Périodiques; Béton -- Périodiques; Cement; Concrete; Periodicals; 620.135
• DOI: 10.1016/j.cemconres.2020.106118
• Languages: English
• ISSNs: 0008-8846

Abstract

Abstract: 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.