Towards Automatic Crack Detection by Deep Learning and Active Thermography

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11507)


Metal joining processes are crucial in current technological devices. To grant the quality of the weldings is the key to ensure a long life cycle of a component. This work faces crack detection in Electron-Bean Welding (EBW) and Tungsten Inert Gas (TIG) weldings using Inductive Thermography with the aim to substitute traditional Non-Destructive Testing (NDT) inspection techniques. The novel method presented in this work can be divided up into two main phases. The first one corresponds to the thermographic inspection, where the thermographic recordings are reconstructed and processed, whereas the second one deals with cracks detection. Last phase is a Convolutional Neural Network inspired in the well-known VGG model which segments the thermographic information, detecting accurately where the cracks are. The thermographic inspection has been complemented with measurements in an optical microscope, showing a good correlation between the experimental and the prediction of this novel solution.


Deep learning Cracks detection Image segmentation Thermography Induction EBW TIG NDT 



This work has been funded by the project KK-2018/00104 (Departamento de Desarrollo Económico e Infraestructuras del Gobierno Vasco, Programa ELKARTEK-Convovatoria 2018).


  1. 1.
    Stankovičová, Z., Dekýš, V., Nový, F., Novák, P.: Nondestructive testing of metal parts by using infrared camera. Procedia Eng. 177, 562–567 (2017). XXI Polish-Slovak Scientific Conference Machine Modeling and Simulations MMS 2016. September 6–8, 2016, Hucisko, PolandCrossRefGoogle Scholar
  2. 2.
    Srajbr, C., Dillenz, A., Bräutigam, K.: Crack detection at aluminum fuselages by induction excited thermography. In: 4th International Symposium on NDT in Aerospace 2012 - Th.3.A.3 (2012)Google Scholar
  3. 3.
    Srajbr, C.: Induction excited thermography in industrial applications. In: 19th World Conference on Non-Destructive Testing 2016 (2016)Google Scholar
  4. 4.
    Netzelmann, U., Walle, G., Lugin, S., Ehlen, A., Bessert, S., Valeske, B.: Induction thermography: principle, applications and first steps towards standardisation. Quant. InfraRed Thermography J. 13(2), 170–181 (2016)CrossRefGoogle Scholar
  5. 5.
    Gorostegui-Colinas, E., Muniategui, A., de Uralde, P.L., Gorosmendi, I., Hériz, B., Sabalza, X.: A novel automatic defect detection method for electron beam welded inconel 718 components using inductive thermography. In: 14th Quantitative InfraRed Thermography Conference (2018)Google Scholar
  6. 6.
    Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Martinez-Gonzalez, P., Garcia-Rodriguez, J.: A survey on deep learning techniques for image and video semantic segmentation. Appl. Soft Comput. 70, 41–65 (2018)CrossRefGoogle Scholar
  7. 7.
    Gu, J., et al.: Recent advances in convolutional neural networks. Pattern Recogn. 77, 354–377 (2018)CrossRefGoogle Scholar
  8. 8.
    Simpson, A.J.R.: Over-sampling in a deep neural network. CoRR, vol. abs/1502.03648 (2015)Google Scholar
  9. 9.
    Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? CoRR, vol. abs/1411.1792 (2014)Google Scholar
  10. 10.
    Oswald-Tranta, B.: Thermoinductive investigations of magnetic materials for surface cracks. Quant. InfraRed Thermography J. 1(1), 33–46 (2004)CrossRefGoogle Scholar
  11. 11.
    Oswald-Tranta, B., Wally, G.: Thermo-Inductive Surface Crack Detection in Metallic Parts (2006)Google Scholar
  12. 12.
    Oswald-Tranta, B., Sorger, M.: Localizing surface cracks with inductive thermographical inspection: from measurement to image processing. Quant. InfraRed Thermography J. 8(2), 149–164 (2011)CrossRefGoogle Scholar
  13. 13.
    JM, T., TJ, G., RM, G.: Retinopathy. JAMA 298(8), 944 (2007)CrossRefGoogle Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, vol. abs/1409.1556 (2014)Google Scholar
  15. 15.
    Park, B., Matsushita, M.: Estimating comic content from the book cover information using fine-tuned VGG model for comic search. In: Kompatsiaris, I., Huet, B., Mezaris, V., Gurrin, C., Cheng, W.-H., Vrochidis, S. (eds.) MMM 2019. LNCS, vol. 11296, pp. 650–661. Springer, Cham (2019). Scholar
  16. 16.
    Sengupta, A., Ye, Y., Wang, R., Liu, C., Roy, K.: Going deeper in spiking neural networks: VGG and residual architectures. Front. Neurosci. 13, 95–95 (2019)CrossRefGoogle Scholar
  17. 17.
    Wu, S., Liu, C., Wang, Z., Wu, S., Xiao, K.: Regression with support vector machines and VGG neural networks. In: Hassanien, A.E., Azar, A.T., Gaber, T., Bhatnagar, R., F. Tolba, M. (eds.) AMLTA 2019. AISC, vol. 921, pp. 301–311. Springer, Cham (2020). Scholar
  18. 18.
    Mateen, M., Wen, J., Nasrullah, Song, S., Huang, Z.: Fundus image classification using VGG-19 architecture with PCA and SVD. Symmetry 11, 1 (2019)CrossRefGoogle Scholar
  19. 19.
    Liskowski, P., Krawiec, K.: Segmenting retinal blood vessels with deep neural networks. IEEE Trans. Med. Imaging 35, 2369–2380 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.LORTEK, Arranomendia Kalea 4AOrdiziaSpain

Personalised recommendations