Abstract
In this chapter, we consider the application of neural network methods of computer vision to solve the problem of detecting various kinds of defects in metal pipes. To enrich the training sample, the problem of creating a generator of synthetic data of 3D objects and automatic marking of such objects is considered. To speed up the process of scene generation, we proposed a mixed shader-polygon method for representing 3D objects. The data obtained using such a generator is mixed with real augmented data, and the process of training deep architectures on such a data set is considered.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Popko, E.A., Vorobyov, A.P., Weinstein, I.A.: Experience in the application of machine vision in optical non-destructive testing systems. In: Proceedings of the Welding and Diagnostics: a Collection of Reports of the International Forum, pp. 401–406. Yekaterinburg, RF (2015). (in Russian)
Ilyasov, B.B., Kakhar, B.K.: The use of classification methods of machine learning in flaw detection. Vestnik Nauki Sibiri 3(13), 40–45 (2014). (in Russian)
Filonov, P., Kitashov, F., Lavrentyev, F.: RNN-based early cyber-attack detection for the tennessee eastman process. CoRR. arXiv:1709.02232 (2017)
Nikolenko, S.I.: Synthetic data for deep learning. CoRR. arXiv:1909.11512 3 (2019)
Xie, Q., Dai, Z., Hovy, E., Luong, M.-T., Le, Q.V.: Unsupervised data augmentation for consistency training. CoRR. arXiv:1904.12848 (2019)
Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence, pp. 13001–13008. New York, USA (2020)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6, 60 (2019)
Zhao, Z.Q., Zheng, P., Xu, S.T., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212–3232 (2019)
Zhang, J., Zhao, X., Chen, Z., Lu, Z.: A review of deep learning-based semantic segmentation for point cloud. IEEE Access 7, 179118–179133 (2019)
Defects Detector CV. Phygitalism. https://phygitalism.com/en/defects-detector-cv-en/. Last accessed 23 Oct 2021
Szymański, P., Kajdanowicz, T.: A network perspective on stratification of multi-label data. In: Proceedings of the First International Workshop on Learning with Imbalanced Domains: Theory and Applications, pp. 22–35. Skopje, Macedonia (2017)
Piegl, L., Tiller, W.: The NURBS Book. Springer-Verlag, New York (1995)
Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Proceedings of the 13th European Conference on Computer Vision, pp. 740–755. Zurich, Switzerland (2014)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. CoRR. arXiv:2004.10934 (2020)
Qiao, S., Chen, L.C., Yuille, A.: Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10213–10224 (2021)
Feng, Z.H., Kittler, J., Awais, M., Huber, P., Wu, X.J.: Wing loss for robust facial landmark localisation with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2235–2245. Salt Lake City, UT, USA (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR. arXiv:1412.6980 (2014)
Wang, Q., Gao, J., Lin, W., Yuan, Y.: Learning from synthetic data for crowd counting in the wild. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8198–8207. Long Beach, CA, USA (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kondarattsev, V.L., Krylov, S.S., Anosova, N.P. (2022). Creating a Synthetic Data Generator for Solving Industrial Flaw Detection Problems Using Deep Learning Methods. In: Favorskaya, M.N., Nikitin, I.S., Severina, N.S. (eds) Advances in Theory and Practice of Computational Mechanics. Smart Innovation, Systems and Technologies, vol 274. Springer, Singapore. https://doi.org/10.1007/978-981-16-8926-0_25
Download citation
DOI: https://doi.org/10.1007/978-981-16-8926-0_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8925-3
Online ISBN: 978-981-16-8926-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)