Skip to Main content Skip to Navigation
New interface
Journal articles

Open‐source deep learning‐based air‐voids detection algorithm for concrete microscopic images

Abstract : Analysing concrete microscopic images is difficult because of its highly heterogeneous composition and the different scales involved. This article presents an open-source deep learning-based algorithm dedicated to air-void detection in concrete microscopic images. The model, whose strategy is presented alongside concrete compositions information, is built using the Mask R-CNN model. Model performances are then discussed and compared to the manual air-void enhancement technique. Finally, the selected open-source strategy is exposed. Overall, the model shows a good precision (mAP = 0.6452), and the predicted air void percentage agrees with experimental measurements highlighting the model's potential to assess concrete durability in the future.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03618068
Contributor : Benoit Hilloulin Connect in order to contact the contributor
Submitted on : Thursday, March 24, 2022 - 2:16:39 PM
Last modification on : Monday, July 18, 2022 - 8:24:00 AM
Long-term archiving on: : Saturday, June 25, 2022 - 6:18:46 PM

File

Hilloulin_Journal_of_microscop...
Files produced by the author(s)

Identifiers

Collections

Citation

Benoit Hilloulin, Imane Bekrine, Emmanuel Schmitt, Ahmed Loukili. Open‐source deep learning‐based air‐voids detection algorithm for concrete microscopic images. Journal of Microscopy, inPress, ⟨10.1111/jmi.13098⟩. ⟨hal-03618068⟩

Share

Metrics

Record views

68

Files downloads

5