access icon openaccess Accurate image registration method for PCB defects detection

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 17/07/2018, Accepted 26/07/2018, Published 16/08/2018

Image registration technology has been widely used in many parts of the computer vision system such as the automatic optical inspection system which is used to detect the printed circuit board (PCB) defects. The accuracy of the image registration will deeply influence the system's performance, so this study proposed an accurate image registration algorithm and applied it to the PCB defect detection. Good features to track feature detector and speeded up robust feature descriptor are combined to extract efficient features to achieve the first accurate image registration. Afterwards, cross-correlation functions were used to compute the shift between the reference image and the first-registered image for further accurate registration. Experimental results show that the authors’ algorithm performs a much better registration, with a lower root-mean-square error value between the reference image and transformed image. What is more, they applied it to detect the defects of PCB with a high accuracy.

Inspec keywords: computer vision; automatic optical inspection; feature extraction; image registration; printed circuits; electronic engineering computing

Other keywords: automatic optical inspection system; computer vision system; first-registered image; PCB defects detection; lower root-mean-square error; printed circuit board defects; accurate image registration method; PCB defect detection; feature detector; reference image; robust feature descriptor

Subjects: Printed circuits; Optical, image and video signal processing; Computer vision and image processing techniques; Electronic engineering computing

References

    1. 1)
      • 16. Leta, F.R., Feliciano, F.F., Martins, F.P.R.: ‘Computer vision system for printed circuit board inspection’. ABCM Symp. Series in Mechatronics, 2008, 3, pp. 623–632.
    2. 2)
      • 9. Reddy, B.S., Chatterji, B.N.: ‘An FFT-based technique for translation, rotation, and scale-invariant image registration’, IEEE Trans. Image Process., 1996, 5, (8), pp. 1266–1271.
    3. 3)
      • 2. Mashohor, S, Evans, J.R., Arslan, T.: ‘Image registration of printed circuit boards using hybrid genetic algorithm’. IEEE Int. Conf. Evolutionary Computation, Vancouver, Canada, July 2006, pp. 2685–2690.
    4. 4)
      • 3. Wang, W., Yan, X., Wang, Z., et al: ‘A robust affine invariant point extraction algorithm for image registration’. Int. Symp. Computational Intelligence and Design, Hangzhou, China, December 2017, pp. 79–82.
    5. 5)
      • 13. Harris, C.J.: ‘A combined corner and edge detector’. Proc. Alvey Vision Conf., Manchester, March 1988, pp. 147–151.
    6. 6)
      • 14. Lowe, D.G.: ‘Object recognition from local scale-invariant features’. Int. Conf. Computer Vision, Kerkyra, Corfu, Greece, 2002, pp. 1150.
    7. 7)
      • 12. Larntz, K., Hampel, F.R., Ronchetti, E.M., et al: ‘Robust statistics’, J. Am. Stat. Assoc., 1989, 84, (406), p. 624.
    8. 8)
      • 20. Shi, J., Tomasi, C.: ‘Good features to track’. IEEE Computer Society Conf., Charlottesville, VA, USA, September 2002, pp. 593–600.
    9. 9)
      • 17. Ren, S., Lu, L., Zhao, L., et al: ‘Circuit board defect detection based on image processing’. Int. Congress on Image and Signal Processing (CISP), Shenyang, China, February 2016, pp. 899–903.
    10. 10)
      • 1. Brown, L.G.: ‘A survey of image registration techniques’, ACM Comput. Surv., 1999, 24, (4), pp. 325–376.
    11. 11)
      • 15. Bay, H., Tuytelaars, T., Gool, L.V.: ‘SURF: speeded up robust features’. European Conf. Computer Vision, New York, USA, May 2006, pp. 404–417.
    12. 12)
      • 7. Dubois, E., Mitiche, A.: ‘Digital picture processing’, Proc. IEEE, 1990, 73, (1), pp. 169–170.
    13. 13)
      • 5. Yang, W., Han, C., Sun, H., et al: ‘Registration of high resolution SAR and optical images based on multiple features’. Int. Geoscience and Remote Sensing Symp., Seoul, South Korea, July 2005, pp. 3542–3544.
    14. 14)
      • 4. Brown, M., Lowe, D. G.: ‘Automatic panoramic image stitching using invariant features’, Int. J. Comput. Vis., 2007, 74, (1), pp. 59–73.
    15. 15)
      • 18. Ejiri, M., Uno, T., Mese, M., et al: ‘A process for detecting defects in complicated patterns’, Comput. Graph. Image Process., 1973, 2, (3), pp. 326–339.
    16. 16)
      • 10. Fan, X., Rhody, H., Saber, E.: ‘Automatic registration of multisensor airborne imagery’, Diss. theses – Gradworks, 2011, 12, (3), pp. 6–86.
    17. 17)
      • 19. Mandeville, J.R.: ‘Novel method for analysis of printed circuit images’, IBM J. Res. Dev., 2010, 29, (1), pp. 73–86.
    18. 18)
      • 21. ‘Cross_cor_taylor.pro’. Available at http://solarmuri.ssl.berkeley.edu/~welsch/public/software/cross_cor_taylor.pro, accessed 9 June 2011.
    19. 19)
      • 11. Lazaridis, G., Petrou, M.: ‘Image registration using the Walsh transform’, IEEE Trans. Image Process., 2006, 15, (8), pp. 2343–2357.
    20. 20)
      • 6. Barnea, D.I., Silverman, H.F.: ‘A class of algorithms for fast digital image registration’, IEEE Trans. Comput., 2009, 21, (2), pp. 179–186.
    21. 21)
      • 8. Colerhodes, A., Zavorin, I., Moigne, J.L.: ‘Mutual information as a similarity measure for remote sensing image registration’, Proc. SPIE, 2011, 12, (2), pp. 179–186.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2018.8272
Loading

Related content

content/journals/10.1049/joe.2018.8272
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading