EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Towards Enhancing Automated Defect Recognition (ADR) in Digital X-ray Radiography Applications: Synthesizing Training Data through X-ray Intensity Distribution Modeling for Deep Learning Algorithms

Bata Hena, Ziang Wei, Luc Perron, Clemente Ibarra Castanedo, Xavier Maldague

Information · 27.12.2023 · 15 (1) · 16

DOI: 10.3390/info15010016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 27.12.2023. Verfasst von Bata Hena und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Council of Canada (NSERC), Mitacs Acceleration program, Canada Research Chair in Multi-polar Infrared Vision (MIVIM).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Conventional human-based approaches, however, are prone to challenges in defect detection accuracy and efficiency, primarily due to the high inspection demand from manufacturing industries with high production throughput. To solve this challenge, numerous computer-based alternatives have been developed, including Automated Defect Recognition (ADR) using deep learning algorithms. At the core of training, these algorithms demand large volumes of data that should be representative of real-world cases. However, the availability of digital X-ray radiography data for open research is limited by non-disclosure contractual terms in the industry. This study presents a pipeline that is capable of modeling synthetic images based on statistical information acquired from X-ray intensity distribution from real digital X-ray radiography images. Through meticulous analysis of the intensity distribution in digital X-ray images, the unique statistical patterns associated with the exposure conditions used during image acquisition, type of component, thickness variations, beam divergence, anode heel effect, etc., are extracted. The realized synthetic images were utilized to train deep learning models, yielding an impressive model performance with a mean intersection over union (IoU) of 0.93 and a mean dice coefficient of 0.96 on real unseen digital X-ray radiography images. This methodology is scalable and adaptable, making it suitable for diverse industrial applications.

Förderung

  • Natural Sciences and Engineering Council of Canada (NSERC)
  • Mitacs Acceleration program
  • Canada Research Chair in Multi-polar Infrared Vision (MIVIM)
  • Canada Foundation for Innovation

Zitieren

APA

Hena, B., Wei, Z., Perron, L., Castanedo, C. I., & Maldague, X. (2023). Towards Enhancing Automated Defect Recognition (ADR) in Digital X-ray Radiography Applications: Synthesizing Training Data through X-ray Intensity Distribution Modeling for Deep Learning Algorithms. Information, 15(1), 16. https://doi.org/10.3390/info15010016

Vancouver

Hena B, Wei Z, Perron L, Castanedo CI, Maldague X. Towards Enhancing Automated Defect Recognition (ADR) in Digital X-ray Radiography Applications: Synthesizing Training Data through X-ray Intensity Distribution Modeling for Deep Learning Algorithms. Information. 2023;15(1):16. doi:10.3390/info15010016

BibTeX
@article{Hena2023,
  author = {Hena, Bata and Wei, Ziang and Perron, Luc and Castanedo, Clemente Ibarra and Maldague, Xavier},
  title = {Towards Enhancing Automated Defect Recognition (ADR) in Digital X-ray Radiography Applications: Synthesizing Training Data through X-ray Intensity Distribution Modeling for Deep Learning Algorithms},
  journal = {Information},
  year = {2023},
  volume = {15},
  number = {1},
  pages = {16},
  doi = {10.3390/info15010016}
}
Kostenlos starten →