XCTPore: An Open Source Database for Porosity in X-ray CT scanned Components Bisma Mutiargo ,1* Andrew A.Malcolm 1 , Zheng Zheng Wong 1 , Bryan Wei Kang Siow 2 , Richie Rui Xin Goh 1 1 Advanced Remanufacturing and Technology Centre, A*STAR (Agency for Science, Technology and Research) 2 National University of Singapore † mutiargob@artc.a-star.edu.sg Abstract The fourth industrial revolution has brought many benefits to the mechanical engineering world. Through data revolution, defect segmentation in complex XCT images can now be automated in a shorter time while achieving more accurate results. Prior work [1] proves that a deep learning approach can extract pores from every voxel of 3D XCT data and calculate its porosity with high accuracy. However, it was established that training a deep learning model with limited data can cause the model to overfit or have inferior segmentation performance than models that are trained with a larger dataset. This overfit issue is a common issue in all sorts of data-driven inspections. Often, obtaining raw data and annotating these raw data for machine learning inspection can take significant resources, shifting the focus away from the network design and training. We present XCTPore, an open source database of X-ray CT images containing 2D slices and 3D volumetric data of X-ray CT scanned additively manufactured components with varying porosity and image quality. This database is currently maintained by the Advanced Remanufacturing and Technology Centre (ARTC) and is open to industry practitioners and academic contributors. The content of the database can be queried through our python code found in our GitHub link 1 . 1 https://github.com/BismaMutiargo/XCTPore More info about this article: http://www.ndt.net/?id=27521 © 2022 The Authors. Published by NDT.net under License CC-BY-4.0 https://creativecommons.org/licenses/by/4.0/ 4 th Singapore International Non-destructive Testing Conference and Exhibition (SINCE2022) https://doi.org/10.58286/27521