Advertisement

An Image-Based Approach for Defect Detection on Decorative Sheets

  • Boyu Zhou
  • Xin He
  • Zhongyi Zhou
  • Xinyi LeEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11304)

Abstract

In this paper, we propose a novel image-based approach for defect detection on decorative sheets. First, an image-based data augmentation approach is applied to deal with imbalanced image sets and severely rare defeat images. Two deep convolutional neural networks (CNNs) are then trained on augmented image sets using feature-extraction-based transfer learning techniques. Finally two CNNs are combined to classify defects through a multi-model ensemble framework, aiming to reduce the false negative rate (FNR) as much as possible. Extensive experiments on augmented artificial images and realistic defeat images both achieve surprisingly FNR accuracy results, which substantiate the proposed approach is promising for defect detection on decorative sheets.

Keywords

Data augmentation Convolutional neural network Transfer learning Multi-model ensemble Defect detection 

References

  1. 1.
    Cun, Y.L., Jackel, L.D., Boser, B.E., Denker, J.S., Graf, H.P., Guyon, I., Henderson, D., Howard, R.E., Hubbard, W.: Handwritten digit recognition: applications of neural network chips and automatic learning. IEEE Commun. Mag. 27(11), 41–46 (1989)CrossRefGoogle Scholar
  2. 2.
    Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. CoRR abs/1310.1531 (2013)Google Scholar
  3. 3.
    Gao, Y., Wang, M., Tao, D., Ji, R., Dai, Q.: 3-D object retrieval and recognition with hypergraph analysis. IEEE Trans. Image Process. 21(9), 4290–4303 (2012)MathSciNetCrossRefGoogle Scholar
  4. 4.
    He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)CrossRefGoogle Scholar
  5. 5.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)Google Scholar
  6. 6.
    Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR abs/1704.04861 (2017)Google Scholar
  7. 7.
    Hu, G.H.: Automated defect detection in textured surfaces using optimal elliptical gabor filters. Optik Int. J. Light Electron Optics 126(14), 1331–1340 (2015)CrossRefGoogle Scholar
  8. 8.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deepconvolutional neural networks, pp. 1097–1105 (2012)Google Scholar
  9. 9.
    Sanghadiya, F., Mistry, D.: Surface defect detection in a tile using digital image processing: analysis and evaluation. Int. J. Comput. Appl. 116(10), 33–35 (2015)Google Scholar
  10. 10.
    Sharif Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2014Google Scholar
  11. 11.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)Google Scholar
  12. 12.
    Soukup, D., Hubermork, R.: Convolutional neural networks for steel surface defect detection from photometric stereo images, pp. 668–677 (2014)Google Scholar
  13. 13.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, vol. 4, pp. 12 (2017)Google Scholar
  14. 14.
    Szegedy, C., et al.: Going deeper with convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015Google Scholar
  15. 15.
    Tsai, D.M., Luo, J.Y.: Mean shift-based defect detection in multicrystalline solar wafer surfaces. IEEE Trans. Ind. Inf. 7(1), 125–135 (2011)CrossRefGoogle Scholar
  16. 16.
    Wang, T., Chen, Y., Qiao, M., Snoussi, H.: A fast and robust convolutional neural network-based defect detection model in product quality control. Int. J. Adv. Manuf. Technol. 94(5–8), 1–7 (2017)Google Scholar
  17. 17.
    Zhang, X., Le, X., Panotopoulou, A., Whiting, E., Wang, C.C.: Perceptual models of preference in 3D printing direction. ACM Trans. Graph. (TOG), 34(6), p. 215 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Shanghai Key Laboratory of Advanced Manufacturing Environment, School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations