Deep learning-based automated image segmentation for concrete petrographic analysis

Yu Song, Zilong Huang, Chuanyue Shen, Humphrey Shi, David A. Lange

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish (US)
Article number106118
JournalCement and Concrete Research
StatePublished - Sep 2020


  • Concrete petrography
  • Deep learning
  • Hardened air void analysis
  • Machine learning
  • Semantic segmentation

ASJC Scopus subject areas

  • Building and Construction
  • Materials Science(all)


Dive into the research topics of 'Deep learning-based automated image segmentation for concrete petrographic analysis'. Together they form a unique fingerprint.

Cite this