Skip to main content
SpringerLink
Log in

FPGA-accelerated textured surface defect segmentation based on complete period Fourier reconstruction

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

Real-time detection of surface defects in high-generation, large-size Liquid Crystal Display (LCD) panels is a serious challenge for both image algorithms and processing speed. For the defect detection of Thin Film Transistor-Liquid Crystal Display (TFT-LCD) images, effectively processing the periodic texture composed of gate lines and data lines is a prerequisite for the success of the algorithm. The traditional one-dimensional Fourier reconstruction algorithm uses a filter-based method to remove most of the texture, but due to the spectral leakage problem, the image boundary cannot be effectively processed. The compensation based on the period extension introduces a more complex ringing effect at the image connection. Starting from the implicit periodic principle of Fourier transform, we propose a strategy of complete period truncation based on subpixel period, which completely eliminates the boundary texture. Furthermore, we fully exploit the potential of parallel execution of the algorithm, resampling the liquid crystal segments truncated in the complete period to an integer power length of 2. The FPGA structure of one-dimensional Fourier reconstruction defect segmentation algorithm with dual-task parallelism and two-pixel parallelism is designed and the calculation bandwidth of 500 MB/s can be realized at 125-MHz clock frequency. We demonstrate the superiority of the proposed method qualitatively and quantitatively. The one-dimensional Fourier reconstruction algorithm based on the complete period truncation can effectively detect various defects such as spots, scratches, fibers and dirt, and the false-positive rate of defects has been reduced by half. The resampling-based Fourier transform speeds up the computational process and the FPGA parallel acceleration architecture is three times faster than comparable server CPUs, reducing the scan detection time of the entire 8.5-generation LCD panel to 8.5 s.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Notes

  1. The fast Fourier transform IP core was provided by Silicon Software GmbH.

  2. https://ark.intel.com/content/www/us/en/ark/products/93814/intel-xeon-processor-e7-4820-v4-25m-cache-2-00-ghz.html.

  3. https://www.xilinx.com/support/documentation/data_sheets/ds150.pdf.

References

  1. Pratt, W.K., Hawthorne, J.A.: Machine vision methods for automatic defect detection in liquid crystal displays. Adv. Imaging 13, 52–54 (1998)

    Google Scholar 

  2. Ko, J., Rheem, J.: Defect detection of polycrystalline solar wafers using local binary mean. Int. J. Adv. Manuf. Technol. 82(9), 1753–1764 (2016)

    Article  Google Scholar 

  3. Zhu, Z., Qian, X., Zhao, Q., Zhou, Q., Ni, K., Wang, X.: TFT-LCD uneven brightness correction and recognition of MURA area based on EMD method. In: 2016 International Conference on Audio, Language and Image Processing (ICALIP), 11–12 July 2016, pp. 366–369

  4. Nguyen, V.H., Pham, V.H., Cui, X., Ma, M., Kim, H.: Design and evaluation of features and classifiers for OLED panel defect recognition in machine vision. J. Inf. Telecommun. 1(4), 334–350 (2017)

    Google Scholar 

  5. Mak, K.L., Peng, P., Yiu, K.F.C.: Fabric defect detection using morphological filters. Image Vis. Comput. 27(10), 1585–1592 (2009)

    Article  Google Scholar 

  6. Luo, Q., He, Y.: A cost-effective and automatic surface defect inspection system for hot-rolled flat steel. Robot. Comput. Manuf. 38, 16–30 (2016)

    Article  Google Scholar 

  7. Smith, M.L., Stamp, R.J.: Automated inspection of textured ceramic tiles. Comput. Ind. 43(1), 73–82 (2000)

    Article  Google Scholar 

  8. Tsai, D.-M., Wu, S.-C., Li, W.-C.: Defect detection of solar cells in electroluminescence images using Fourier image reconstruction. Sol. Energy Mater. Sol. Cells 99, 250–262 (2012)

    Article  Google Scholar 

  9. Sindagi, V.A., Srivastava, S.: Domain adaptation for automatic OLED panel defect detection using adaptive support vector data description. Int. J. Comput. Vis. 122(2), 193–211 (2017)

    Article  MathSciNet  Google Scholar 

  10. Haraclick, R.M.: Texture features for image classification. IEEE Trans. SMC 6, 610–621 (1973)

    Google Scholar 

  11. Tsai, D.M., Chuang, S.T.: 1D-based defect detection in patterned TFT-LCD panels using characteristic fractal dimension and correlations. Mach. Vis. Appl. 20(6), 423–434 (2009)

    Article  Google Scholar 

  12. Mei, S., Yang, H., Yin, Z.: Unsupervised-learning-based feature-level fusion method for mura defect recognition. IEEE Trans. Semicond. Manuf. 30(1), 105–113 (2017)

    Article  Google Scholar 

  13. Ren, R., Hung, T., Tan, K.C.: A generic deep-learning-based approach for automated surface inspection. IEEE Trans. Cybern. 48(3), 929–940 (2018)

    Article  Google Scholar 

  14. Lu, C.-H., Tsai, D.-M.: Independent component analysis-based defect detection in patterned liquid crystal display surfaces. Image Vis. Comput. 26(7), 955–970 (2008)

    Article  Google Scholar 

  15. Cen, Y.-G., Zhao, R.-Z., Cen, L.-H., Cui, L.-H., Miao, Z.-J., Wei, Z.: Defect inspection for TFT-LCD images based on the low-rank matrix reconstruction. Neurocomputing 149, 1206–1215 (2015)

    Article  Google Scholar 

  16. Alex, K., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates, Inc., New York (2012)

    Google Scholar 

  17. Perng, D.-B., Chen, S.-H.: Directional textures auto-inspection using discrete cosine transform. Int. J. Prod. Res. 49(23), 7171–7187 (2011)

    Article  Google Scholar 

  18. Wang, F.-L., Zuo, B.: Detection of surface cutting defect on magnet using Fourier image reconstruction. J Cent. South Univ. 23(5), 1123–1131 (2016)

    Article  MathSciNet  Google Scholar 

  19. Yeh, C., Wu, F., Ji, W., Huang, C.: A wavelet-based approach in detecting visual defects on semiconductor wafer dies. IEEE Trans. Semicond. Manuf. 23(2), 284–292 (2010)

    Article  Google Scholar 

  20. Tsai, D.M., Hung, C.Y.: Automatic defect inspection of patterned thin film transistor-liquid crystal display (TFT-LCD) panels using one-dimensional Fourier reconstruction and wavelet decomposition. Int. J. Prod. Res. 43(21), 4589–4607 (2005)

    Article  Google Scholar 

  21. Tsai, D.M., Chuang, S.T., Tseng, Y.H.: One-dimensional-based automatic defect inspection of multiple patterned TFT-LCD panels using Fourier image reconstruction. Int. J. Prod. Res. 45(6), 1297–1321 (2007)

    Article  Google Scholar 

  22. Zhang, T., Lu, R.: Automatic period selection for DFT method in the application of TFT-LCD panel detection. J. Electron. Meas. Instrum. 30(3), 361–373 (2016)

    Google Scholar 

  23. Zhang, T., Lu, R., Dang, X.: Automatic neighbor r selection for one-dimensional DFT method in the surface defect inspection of TFT-LCD. China Mech. Eng. 27(21), 2895–2901 (2016)

    Google Scholar 

  24. Donald, G.B.: Design for Embedded Image Processing on FPGAs. Publishing House of Electronics Industry, Beijing (2013)

    Google Scholar 

  25. Matteo F., Steven G.J.: FFTW. http://www.fftw.org/ (2018). Accessed 29 Apr 2019

Download references

Funding

This work was supported by the National Key Research and Development Program of China (No. 2018YFB2003801), the National Natural Science Foundation of China (NSFC) (Grant no. 51875164) and the National Key Scientific Instrument and Equipment Development Project of China (No. 2013YQ220749).

Author information

Authors and Affiliations

  1. Department of Instrument Science and Opto-Electronics Engineering, Hefei University of Technology, No. 193 Tunxi Road, Hefei, Anhui, China

    Yinfei Pan, Rongsheng Lu & Tengda Zhang

Authors
  1. Yinfei Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rongsheng Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tengda Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rongsheng Lu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pan, Y., Lu, R. & Zhang, T. FPGA-accelerated textured surface defect segmentation based on complete period Fourier reconstruction. J Real-Time Image Proc 17, 1659–1673 (2020). https://doi.org/10.1007/s11554-019-00927-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-019-00927-1

Keywords

Search

Navigation