|
Title |
Estimation of Concrete Porosity Using Image Segmentation Method
|
|
Authors |
정현준(Hyun-Joon Jeong) ; 정호성(Hoseong Jeong) ; 김재현(Jae Hyun Kim) ; 김강수(Kang-Su Kim) |
|
DOI |
https://doi.org/10.11112/jksmi.2023.27.1.30 |
|
Keywords |
콘크리트; 공극률; 영상분할; 머신러닝; 딥러닝 Concrete; Porosity; Image segmentation; Machine learning; Deep learning |
|
Abstract |
In this study, an image segmentation model that can evaluate surface porosity based on concrete surface images was derived. Three typesof concrete specimens with different water-cement ratios (w/c = 54, 35, and 30%) were prepared, and 2,729 surface images were obtained using anoptical microscope. Benchmarking tests, parameter optimization, and final model derivation were performed using the surface images, and an imagesegmentation model with 97% verification accuracy was obtained. The model was verified by comparing the porosity obtained from the model andX-Ray Microscope (XRM). The model provided similar porosity to that of XRM for the specimens with a high water-cement ratio, but tended to givelower porosity for specimens with a low water-cement ratio.
|