Abstract
In this work, a multiclass segmentation of defects on industrial CT data is performed. The segmentation is implemented by using artificial neural networks (ANNs). Different architectures are evaluated and compared to find the best model architecture for this task. Different metrics for segmentation and classification analysis are used to evaluate the networks. The three best models are presented in this paper. All of them obtained positive results; the model with the U-Net architecture achieved the best results with a remarkable segmentation performance of 90.18% and a classification performance of 95.77%.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Research and Review Journal of Nondestructive Testing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
