Abstract
There exist crack, bar and round defects in the weld joints of pressure vessels and pipes, which are detected by the X radiographic inspection system. The check and evaluation for defects in the radiographic images are often done manually and the work efficiency is low, the evaluation has artificial subjectivity. The automatic detection method of defects in weld joints based on Poisson fusion and deep learning is proposed. The defects in weld joints are typical industrial weak objects because of their small size, distinct edge erosion, and small SNR in radiographic images. The training images should be augmented for the application of deep learning in the object detection of industrial images. The augmentation method based on Poisson image fusion is given to simulate the edge erosion in radiographic images. The histogram is used to find a suitable position for the Poisson fusion of the object defect and background region. The detection model is obtained in the framework of Faster R-CNN with the pre-trained ResNet50. Feature Pyramid Network is integrated for its strong detection capacity for industrial weak objects. The results show that our Poisson image fusion has a much greater contribution to the detection model than the general data augmentation in geometry transform in terms of AP and Recall.
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
References
Xiao, H.: Research on automatic detection and recognition system of welding defect ray DR image. Nanchang Hangkong University (2017)
Ye, Z.: Research on automatic welding defect detection based on image processing. Nanjing University of Aeronautics and Astronautics (2017)
Mahmoudi, A., Regragui, F.: Fast segmentation method for defects detection in radiographic images of welds. In: IEEE/ACS International Conference on Computer Systems & Applications. IEEE (2009)
Alaknanda, Anand, R.S., Kumar, P.: Flaw detection in radiographic weld images using morphological approach. NDT & E Int. 39(1), 29–33 (2006)
Daum, W., Rose, P., Heidt, H.: Automatic recognition of weld defects in X radiographic-inspection. Materialpruefung 28(6), 177–180 (1986)
Zou, Y., Du, D., Chang, B., et al.: Automatic weld defect detection method based on Kalman filtering for real-time radiographic inspection of spiral pipe. NDT and E Int. 72, 1–9 (2015)
Shao, J., Du, D., Wang, L., et al.: Detection of low contrast thin line defect in X radiographic film digitized image of weld seam. Nondestructive 2010(12)
Da Silva, R.R., Calôba, L.P., Siqueira, M.H.S., et al.: Evaluation of the relevant characteristic parameters of welding defects and probability of correct classification using linear classifiers. Insight 44(10), 616–622 (2002)
Kumar, J., Anand, R.S., Srivastava, S.P.: Flaws classification using ANN for radiographic weld images. In: 2014 International Conference on Signal Processing and Integrated Networks (SPIN). IEEE, pp. 145–150 (2014)
Wang, Y., Sun, Y., Lv, P., et al.: Detection of line weld defects based on multiple thresholds and support vector machine. NDT and E Int. 41(7), 517–524 (2008)
Boaretto, N., Centeno, T.M.: Automated detection of welding defects in pipelines from radiographic images DWDI. NDT and E Int. 86, 7–13 (2017)
Liu, H., Guo, R.: Detection and identification of weld defects in petroleum steel pipes based on X radiographic image and convolutional neural network. J. Instrum. 2018(4)
Chen, F.C., Jahanshahi, R.M.R.: NB-CNN: deep learning-based crack detection using convolutional neural network and Naïve Bayes data fusion. IEEE Trans. Ind. Electron. 65, 4392–4400 (2017)
Suyama, F.M., Delgado, M.R., da Silva, R.D., et al.: Deep neural networks based approach for welded joint detection of oil pipelines in radiographic images with Double Wall Double Image exposure. NDT E Int. 105, 46–55 (2019)
Qiang, T.: Radiographic Inspection. China Labor and Social Security press, Beijing (2007)
Pérez, P., Gangnet, M., Blake, A.: Poisson image editing. ACM Trans. Graph. (TOG) 22(3), 313–318 (2003)
Sun, J., Li, L., Xiao, Z.: Image seamless Mosaic method based on adaptive gradient domain fusion. Comput. Appl. Res. 32(09) (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(2), 2012 (2017)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. Comput. Vis. Pattern Recognit. (2016)
Yun, R., Changren, Z., Shunping, X.: Small object detection in optical remote sensing images via modified faster R-CNN. Appl. Sci. 8(5), 813 (2018)
Lin, T.Y., Dollár, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, X. et al. (2019). Detection of Weak Defects in Weld Joints Based on Poisson Fusion and Deep Learning. In: Ning, H. (eds) Cyberspace Data and Intelligence, and Cyber-Living, Syndrome, and Health. CyberDI CyberLife 2019 2019. Communications in Computer and Information Science, vol 1137. Springer, Singapore. https://doi.org/10.1007/978-981-15-1922-2_21
Download citation
DOI: https://doi.org/10.1007/978-981-15-1922-2_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1921-5
Online ISBN: 978-981-15-1922-2
eBook Packages: Computer ScienceComputer Science (R0)