Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Defect classification in additive manufacturing using CNN-based vision processing

Liu, Xiao, Mileo, Alessandra orcid logoORCID: 0000-0002-6614-6462 and Smeaton, Alan F. orcid logoORCID: 0000-0003-1028-8389 (2023) Defect classification in additive manufacturing using CNN-based vision processing. In: 25th Irish Machine Vision and Image Processing Conference, 30 Aug - 1 Sept 2023, Galway, Ireland.

Abstract
The development of computer vision and in-situ monitoring using visual sensors allows the collection of large datasets from the additive manufacturing (AM) process. Such datasets could be used with machine learning techniques to improve the quality of AM. This paper examines two scenarios: first, using convolutional neural networks (CNNs) to accurately classify defects in an image dataset from AM and second, applying active learning techniques to the developed classification model. This allows the construction of a human-in-the-loop mechanism to reduce the size of the data required to train and generate training data.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Convolutional neural networks; additive manufacturing; defect classification; active learning
Subjects:Computer Science > Artificial intelligence
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Research Initiatives and Centres > I-Form
Copyright Information:© 2023 The Authors.
Funders:Science Foundation Ireland
ID Code:28761
Deposited On:20 Sep 2023 08:48 by Alan Smeaton . Last Modified 12 Feb 2024 16:03
Documents

Full text available as:

[thumbnail of dcbhqfhvhjhzxrcdjxbvhwdkxzjcqfsn.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial 4.0
177kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record