Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Study on Unsupervised Anomaly Detection and Defect Localization using Generative Model in Ultrasonic Non-Destructive Testing (2405.16580v1)

Published 26 May 2024 in cs.CV, cs.LG, and eess.IV

Abstract: In recent years, the deterioration of artificial materials used in structures has become a serious social issue, increasing the importance of inspections. Non-destructive testing is gaining increased demand due to its capability to inspect for defects and deterioration in structures while preserving their functionality. Among these, Laser Ultrasonic Visualization Testing (LUVT) stands out because it allows the visualization of ultrasonic propagation. This makes it visually straightforward to detect defects, thereby enhancing inspection efficiency. With the increasing number of the deterioration structures, challenges such as a shortage of inspectors and increased workload in non-destructive testing have become more apparent. Efforts to address these challenges include exploring automated inspection using machine learning. However, the lack of anomalous data with defects poses a barrier to improving the accuracy of automated inspection through machine learning. Therefore, in this study, we propose a method for automated LUVT inspection using an anomaly detection approach with a diffusion model that can be trained solely on negative examples (defect-free data). We experimentally confirmed that our proposed method improves defect detection and localization compared to general object detection algorithms used previously.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Automatic detection of concrete surface defects using deep learning and laser ultrasonic visualization testing, PHMAP, 2023.
  2. A Study on Deep CNN Structures for Defect Detection From Laser Ultrasonic Visualization Testing Images, Intelligence, Informatics and Infrastructure, Vol.4, pp.1–11, 2023.
  3. Simulation-aided deep learning for laser ultrasonic visualization testing with style transfer, Intelligence, Informatics and Infrastructure, Vol.5, No.1, pp.25–33, 2024.
  4. Optical methods of laser ultrasonic testing technology in the industrial and engineering applications: A review, Optics & Laser Technology, Vol.176, pp.110876, 2024.
  5. Physics-Informed Neural Network for Ultrasound Nondestructive Quantification of Surface Breaking Cracks, Journal of Nondestructive Evaluation, Vol.39, No.3, pp.1–20, 2020.
  6. Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks, Neurocomputing, Vol.257, pp.128–135, 2017, Machine Learning and Signal Processing for Big Multimedia Analysis.
  7. Autoencoder-based detection of near-surface defects in ultrasonic testing, Ultrasonics, Vol.119, pp.106637, 2022.
  8. AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 650–656, June 2022.
  9. Neural network classification of flaws detected by ultrasonic means, NDT & E International, Vol.29, No.2, pp.87–93, 1996.
  10. The classification of defects from ultrasonic data using neural networks: The Hopfield method, NDT international, Vol.22, No.2, pp.97–105, 1989.
  11. A self-learning neural net for ultrasonic signal analysis, Ultrasonics, Vol.30, No.5, pp.317–324, 1992.
  12. Ultrasonic flaw detection using Support Vector Machine classification, 2015 IEEE International Ultrasonics Symposium (IUS), pp. 1–4, 2015.
  13. Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing, Ultrasonics, Vol.73, pp.1–8, 2017.
  14. Automated Defect Recognition for Welds Using Simulation Assisted TFM Imaging with Artificial Intelligence, Journal of Nondestructive Evaluation, Vol.40, No.1, pp.28, 2 2021.
  15. DefectDet: A deep learning architecture for detection of defects with extreme aspect ratios in ultrasonic images, Neurocomputing, Vol.473, pp.107–115, 2022.
  16. Identification of weld geometry from ultrasound scan data using deep learning, Procedia CIRP, Vol.104, pp.122–127, 2021, 54th CIRP CMS 2021 - Towards Digitalized Manufacturing 4.0.
  17. A Methodology to Automatically Segment 3D Ultrasonic Data Using X-ray Computed Tomography and a Convolutional Neural Network, Applied Sciences, Vol.13, No.10, 2023.
  18. Deep learning-based anomaly detection from ultrasonic images, Ultrasonics, Vol.124, pp.106737, 2022.
  19. Convolutional feature extraction for process monitoring using ultrasonic sensors, Computers & Chemical Engineering, Vol.155, pp.107508, 2021.
  20. CutPaste: Self-Supervised Learning for Anomaly Detection and Localization, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9659–9669, 2021.
  21. DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection, 2023.
  22. SimpleNet: A Simple Network for Image Anomaly Detection and Localization, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20402–20411, June 2023.
  23. PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization, Pattern Recognition. ICPR International Workshops and Challenges, (Ed. by A. Del Bimbo, R. Cucchiara, S. Sclaroff, G. M. Farinella, T. Mei, M. Bertini, H. J. Escalante, and R. Vezzani), pp. 475–489, Cham, 2021, Springer International Publishing.
  24. Towards Total Recall in Industrial Anomaly Detection, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14298–14308, 2022.
  25. Auto-Encoding Variational Bayes, 2022.
  26. Generative adversarial nets, Advances in neural information processing systems, pp. 2672–2680, 2014.
  27. Denoising Diffusion Probabilistic Models, Advances in Neural Information Processing Systems, (Ed. by H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin), Vol. 33, pp. 6840–6851, Curran Associates, Inc., 2020.
  28. f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks, Medical Image Analysis, Vol.54, pp.30–44, 2019.
  29. Improved Denoising Diffusion Probabilistic Models, Proceedings of the 38th International Conference on Machine Learning, (Ed. by M. Meila and T. Zhang), Vol. 139 of Proceedings of Machine Learning Research, pp. 8162–8171, PMLR, 18–24 Jul 2021.
  30. MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain Images, 2024.
  31. A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection, IEEE Journal of Biomedical and Health Informatics, pp. 1–11, 2024.
  32. Autoencoders for unsupervised anomaly segmentation in brain MR images: A comparative study, Medical Image Analysis, Vol.69, pp.101952, 2021.
  33. RTMDet: An Empirical Study of Designing Real-Time Object Detectors, 2022.
  34. Focal Loss for Dense Object Detection, Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017.
  35. YOLOv3: An Incremental Improvement, 2018.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets