Abstract

Presently, automatic inspection algorithms are widely used to ensure high-quality products and achieve high productivity in the steelmaking industry. In this paper, we propose a vision-based method for detecting corner cracks on the surface of steel billets. Because of the presence of scales composed of oxidized substances, the billet surfaces are not uniform and vary considerably with the lighting conditions. To minimize the influence of scales and improve the accuracy of detection, a detection method based on a visual inspection algorithm is proposed. Wavelet reconstruction is used to reduce the effect of scales. Texture and morphological features are used to identify the corner cracks among the defective candidates. Finally, the experimental results show that the proposed algorithm is effective in detecting corner cracks on the surfaces of the steel billets.

© 2014 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. X. Li, S. K. Tso, X. P. Guan, and Q. Huang, “Improving automatic detection of defects in castings by applying wavelet technique,” IEEE Trans. Ind. Electron. 53, 1927–1934 (2006).
    [CrossRef]
  2. B. R. Suresh, R. A. Fundakowski, T. S. Levitt, and J. E. Overland, “Real-time automated visual inspection system for hot steel slabs,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5, 563–572 (1983).
    [CrossRef]
  3. C. R. P. Courtney, B. W. Drinkwater, S. A. Neild, and P. D. Wilcox, “Factors affecting the ultrasonic intermodulation crack detection technique using bispectral analysis,” NDT&E Int. 41, 223–234 (2008).
    [CrossRef]
  4. Z. F. Zhou and Y. Cheng, “Magneto-optic microscope for visually detecting subsurface defects,” Appl. Opt. 47, 3463–3466 (2008).
    [CrossRef]
  5. V. Lashkia, “Defect detection in X-ray images using fuzzy reasoning,” Image Vis. Comput. 19, 261–269 (2001).
    [CrossRef]
  6. H. Kim, K. Jhang, M. Shin, and J. Kim, “A noncontact NDE method using a laser generated focused-Lamb wave with enhanced defect-detection ability and spatial resolution,” NDT&E Int. 39, 312–319 (2006).
    [CrossRef]
  7. S. C. Kim and T. J. Kang, “Automated defect detection system using wavelet packet frame and Gaussian mixture model,” J. Opt. Soc. Am. A 23, 2690–2701 (2006).
    [CrossRef]
  8. M. Ralló, M. S. Millán, and J. Escofet, “Unsupervised novelty detection using Gabor filters for defect segmentation in textures,” J. Opt. Soc. Am. A 26, 1967–1976 (2009).
    [CrossRef]
  9. Y. Han and P. Shi, “An adaptive level-selecting wavelet transform for texture defect detection,” Image Vis. Comput. 25, 1239–1248 (2007).
    [CrossRef]
  10. A. Kumar, “Neural network based detection of local textile defects,” Pattern Recogn. 36, 1645–1659 (2003).
    [CrossRef]
  11. A. Abouelela, H. M. Abbas, H. Eldeeb, A. A. Wahdan, and S. M. Nassar, “Automated vision system for localizing structural defects in textile fabrics,” Pattern Recogn. Lett. 26, 1435–1443 (2005).
    [CrossRef]
  12. C. S. Cho, B. M. Chung, and M. J. Park, “Development of real-time vision-based fabric inspection system,” IEEE Trans. Ind. Electron. 52, 1073–1079 (2005).
    [CrossRef]
  13. Z. Chen, Y. Tao, and X. Chen, “Multiresolution local contrast enhancement of X-ray images for poultry meat inspection,” Appl. Opt. 40, 1195–1200 (2001).
    [CrossRef]
  14. Y. C. Song, D. H. Choi, and K. H. Park, “Wavelet-based image enhancement for defect detection in thin film transistor liquid crystal display panel,” Jpn. J. Appl. Phys. 45, 5069–5072 (2006).
    [CrossRef]
  15. C. J. Lu and D. M. Tsai, “Automatic defect inspection for LCDs using singular value decomposition,” Int. J. Adv. Manuf. Technol. 25, 53–61 (2005).
    [CrossRef]
  16. K. N. Choi, N. K. Park, and S. I. Yoo, “Image restoration for quantifying TFT-LCD defect levels,” IEICE Trans. Inf. Syst. 2, 322–329 (2008).
  17. D. M. Tsai and C. Y. Hung, “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, 4589–4607 (2005).
    [CrossRef]
  18. J. L. C. Sanz and A. K. Jain, “Machine-vision techniques for inspection of printed wiring boards and thick-film circuits,” J. Opt. Soc. Am. A 3, 1465–1482 (1986).
    [CrossRef]
  19. J. P. Yun, Y. J. Jeon, D. Choi, and S. W. Kim, “Real-time defect detection of steel wire rods using wavelet filters optimized by univariate dynamic encoding algorithm for searches,” J. Opt. Soc. Am. A 29, 797–807 (2012).
    [CrossRef]
  20. D. C. Choi, Y. J. Jeon, J. P. Yun, and S. W. Kim, “Pinhole detection in steel slab images using Gabor filter and morphological features,” Appl. Opt. 50, 5122–5129 (2011).
    [CrossRef]
  21. J. P. Yun, S. H. Choi, and S. W. Kim, “Vision-based defect detection of scale-covered steel billet surfaces,” Opt. Eng. 48, 037205 (2009).
    [CrossRef]
  22. R. T. Chin and C. A. Harlow, “Automated visual inspection: a survey,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 557–573 (1982).
    [CrossRef]
  23. H. Zhang, G. Wu, X. Sun, J. Xu, and K. Xu, “A new fast border search algorithm and its expansion,” in Proceedings of the IEEE International Conference on Automation and Logistics (IEEE, 2007), pp. 1886–1890.
  24. S. G. Mallat, “Theory for multiresolution signal decomposition: the wavelet representation,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 674–693 (1989).
    [CrossRef]
  25. W. Sun, R. Mukherjee, P. Stroeve, A. Palazoglu, and J. A. Romagnoli, “A multi-resolution approach for line-edge roughness detection,” Microelectron. Eng. 86, 340–351 (2009).
    [CrossRef]
  26. D. M. Tsai and C. H. Chiang, “Automatic band selection for wavelet reconstruction in the application of defect detection,” Image Vis. Comput. 21, 413–431 (2003).
    [CrossRef]
  27. D. M. Tsai and B. Hsiao, “Automatic surface inspection using wavelet reconstruction,” Pattern Recogn. 34, 1285–1305 (2001).
    [CrossRef]
  28. H. Y. T. Ngan, G. K. H. Pang, S. P. Yung, and M. K. Ng, “Wavelet based methods on patterned fabric defect detection,” Pattern Recogn. 38, 559–576 (2005).
    [CrossRef]
  29. W. C. Li and D. M. Tsai, “Wavelet-based defect detection in solar wafer images with inhomogeneous texture,” Pattern Recogn. 45, 742–756 (2012).
  30. W. K. Wong, C. W. M. Yuen, D. D. Fan, L. K. Chan, and E. H. F. Fung, “Stitching defect detection and classification using wavelet transform and BP neural network,” Expert Syst. Appl. 36, 3845–3856 (2009).
    [CrossRef]
  31. R. C. Gonzalez and R. E. Woods, Digital Image Processing (Prentice Hall, 2008).
  32. T. Chang and C. C. J. Kuo, “Texture analysis and classification with tree-structured wavelet transform,” IEEE Trans. Image Process. 2, 429–441 (1993).
    [CrossRef]
  33. C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Min. Knowl. Discov. 2, 121–167 (1998).
    [CrossRef]
  34. B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
    [CrossRef]
  35. X. Xie, “A review of recent advances in surface defect detection using texture analysis techniques,” Electron Lett. Comput. Vis. Image Anal. 7, 1–22 (2008).

2012 (2)

2011 (1)

2009 (4)

M. Ralló, M. S. Millán, and J. Escofet, “Unsupervised novelty detection using Gabor filters for defect segmentation in textures,” J. Opt. Soc. Am. A 26, 1967–1976 (2009).
[CrossRef]

W. K. Wong, C. W. M. Yuen, D. D. Fan, L. K. Chan, and E. H. F. Fung, “Stitching defect detection and classification using wavelet transform and BP neural network,” Expert Syst. Appl. 36, 3845–3856 (2009).
[CrossRef]

W. Sun, R. Mukherjee, P. Stroeve, A. Palazoglu, and J. A. Romagnoli, “A multi-resolution approach for line-edge roughness detection,” Microelectron. Eng. 86, 340–351 (2009).
[CrossRef]

J. P. Yun, S. H. Choi, and S. W. Kim, “Vision-based defect detection of scale-covered steel billet surfaces,” Opt. Eng. 48, 037205 (2009).
[CrossRef]

2008 (4)

K. N. Choi, N. K. Park, and S. I. Yoo, “Image restoration for quantifying TFT-LCD defect levels,” IEICE Trans. Inf. Syst. 2, 322–329 (2008).

C. R. P. Courtney, B. W. Drinkwater, S. A. Neild, and P. D. Wilcox, “Factors affecting the ultrasonic intermodulation crack detection technique using bispectral analysis,” NDT&E Int. 41, 223–234 (2008).
[CrossRef]

X. Xie, “A review of recent advances in surface defect detection using texture analysis techniques,” Electron Lett. Comput. Vis. Image Anal. 7, 1–22 (2008).

Z. F. Zhou and Y. Cheng, “Magneto-optic microscope for visually detecting subsurface defects,” Appl. Opt. 47, 3463–3466 (2008).
[CrossRef]

2007 (1)

Y. Han and P. Shi, “An adaptive level-selecting wavelet transform for texture defect detection,” Image Vis. Comput. 25, 1239–1248 (2007).
[CrossRef]

2006 (4)

X. Li, S. K. Tso, X. P. Guan, and Q. Huang, “Improving automatic detection of defects in castings by applying wavelet technique,” IEEE Trans. Ind. Electron. 53, 1927–1934 (2006).
[CrossRef]

Y. C. Song, D. H. Choi, and K. H. Park, “Wavelet-based image enhancement for defect detection in thin film transistor liquid crystal display panel,” Jpn. J. Appl. Phys. 45, 5069–5072 (2006).
[CrossRef]

H. Kim, K. Jhang, M. Shin, and J. Kim, “A noncontact NDE method using a laser generated focused-Lamb wave with enhanced defect-detection ability and spatial resolution,” NDT&E Int. 39, 312–319 (2006).
[CrossRef]

S. C. Kim and T. J. Kang, “Automated defect detection system using wavelet packet frame and Gaussian mixture model,” J. Opt. Soc. Am. A 23, 2690–2701 (2006).
[CrossRef]

2005 (5)

H. Y. T. Ngan, G. K. H. Pang, S. P. Yung, and M. K. Ng, “Wavelet based methods on patterned fabric defect detection,” Pattern Recogn. 38, 559–576 (2005).
[CrossRef]

C. J. Lu and D. M. Tsai, “Automatic defect inspection for LCDs using singular value decomposition,” Int. J. Adv. Manuf. Technol. 25, 53–61 (2005).
[CrossRef]

D. M. Tsai and C. Y. Hung, “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, 4589–4607 (2005).
[CrossRef]

A. Abouelela, H. M. Abbas, H. Eldeeb, A. A. Wahdan, and S. M. Nassar, “Automated vision system for localizing structural defects in textile fabrics,” Pattern Recogn. Lett. 26, 1435–1443 (2005).
[CrossRef]

C. S. Cho, B. M. Chung, and M. J. Park, “Development of real-time vision-based fabric inspection system,” IEEE Trans. Ind. Electron. 52, 1073–1079 (2005).
[CrossRef]

2003 (2)

A. Kumar, “Neural network based detection of local textile defects,” Pattern Recogn. 36, 1645–1659 (2003).
[CrossRef]

D. M. Tsai and C. H. Chiang, “Automatic band selection for wavelet reconstruction in the application of defect detection,” Image Vis. Comput. 21, 413–431 (2003).
[CrossRef]

2001 (3)

D. M. Tsai and B. Hsiao, “Automatic surface inspection using wavelet reconstruction,” Pattern Recogn. 34, 1285–1305 (2001).
[CrossRef]

Z. Chen, Y. Tao, and X. Chen, “Multiresolution local contrast enhancement of X-ray images for poultry meat inspection,” Appl. Opt. 40, 1195–1200 (2001).
[CrossRef]

V. Lashkia, “Defect detection in X-ray images using fuzzy reasoning,” Image Vis. Comput. 19, 261–269 (2001).
[CrossRef]

1998 (1)

C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Min. Knowl. Discov. 2, 121–167 (1998).
[CrossRef]

1997 (1)

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

1993 (1)

T. Chang and C. C. J. Kuo, “Texture analysis and classification with tree-structured wavelet transform,” IEEE Trans. Image Process. 2, 429–441 (1993).
[CrossRef]

1989 (1)

S. G. Mallat, “Theory for multiresolution signal decomposition: the wavelet representation,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 674–693 (1989).
[CrossRef]

1986 (1)

1983 (1)

B. R. Suresh, R. A. Fundakowski, T. S. Levitt, and J. E. Overland, “Real-time automated visual inspection system for hot steel slabs,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5, 563–572 (1983).
[CrossRef]

1982 (1)

R. T. Chin and C. A. Harlow, “Automated visual inspection: a survey,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 557–573 (1982).
[CrossRef]

Abbas, H. M.

A. Abouelela, H. M. Abbas, H. Eldeeb, A. A. Wahdan, and S. M. Nassar, “Automated vision system for localizing structural defects in textile fabrics,” Pattern Recogn. Lett. 26, 1435–1443 (2005).
[CrossRef]

Abouelela, A.

A. Abouelela, H. M. Abbas, H. Eldeeb, A. A. Wahdan, and S. M. Nassar, “Automated vision system for localizing structural defects in textile fabrics,” Pattern Recogn. Lett. 26, 1435–1443 (2005).
[CrossRef]

Burges, C. J. C.

C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Min. Knowl. Discov. 2, 121–167 (1998).
[CrossRef]

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

Chan, L. K.

W. K. Wong, C. W. M. Yuen, D. D. Fan, L. K. Chan, and E. H. F. Fung, “Stitching defect detection and classification using wavelet transform and BP neural network,” Expert Syst. Appl. 36, 3845–3856 (2009).
[CrossRef]

Chang, T.

T. Chang and C. C. J. Kuo, “Texture analysis and classification with tree-structured wavelet transform,” IEEE Trans. Image Process. 2, 429–441 (1993).
[CrossRef]

Chen, X.

Chen, Z.

Cheng, Y.

Chiang, C. H.

D. M. Tsai and C. H. Chiang, “Automatic band selection for wavelet reconstruction in the application of defect detection,” Image Vis. Comput. 21, 413–431 (2003).
[CrossRef]

Chin, R. T.

R. T. Chin and C. A. Harlow, “Automated visual inspection: a survey,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 557–573 (1982).
[CrossRef]

Cho, C. S.

C. S. Cho, B. M. Chung, and M. J. Park, “Development of real-time vision-based fabric inspection system,” IEEE Trans. Ind. Electron. 52, 1073–1079 (2005).
[CrossRef]

Choi, D.

Choi, D. C.

Choi, D. H.

Y. C. Song, D. H. Choi, and K. H. Park, “Wavelet-based image enhancement for defect detection in thin film transistor liquid crystal display panel,” Jpn. J. Appl. Phys. 45, 5069–5072 (2006).
[CrossRef]

Choi, K. N.

K. N. Choi, N. K. Park, and S. I. Yoo, “Image restoration for quantifying TFT-LCD defect levels,” IEICE Trans. Inf. Syst. 2, 322–329 (2008).

Choi, S. H.

J. P. Yun, S. H. Choi, and S. W. Kim, “Vision-based defect detection of scale-covered steel billet surfaces,” Opt. Eng. 48, 037205 (2009).
[CrossRef]

Chung, B. M.

C. S. Cho, B. M. Chung, and M. J. Park, “Development of real-time vision-based fabric inspection system,” IEEE Trans. Ind. Electron. 52, 1073–1079 (2005).
[CrossRef]

Courtney, C. R. P.

C. R. P. Courtney, B. W. Drinkwater, S. A. Neild, and P. D. Wilcox, “Factors affecting the ultrasonic intermodulation crack detection technique using bispectral analysis,” NDT&E Int. 41, 223–234 (2008).
[CrossRef]

Drinkwater, B. W.

C. R. P. Courtney, B. W. Drinkwater, S. A. Neild, and P. D. Wilcox, “Factors affecting the ultrasonic intermodulation crack detection technique using bispectral analysis,” NDT&E Int. 41, 223–234 (2008).
[CrossRef]

Eldeeb, H.

A. Abouelela, H. M. Abbas, H. Eldeeb, A. A. Wahdan, and S. M. Nassar, “Automated vision system for localizing structural defects in textile fabrics,” Pattern Recogn. Lett. 26, 1435–1443 (2005).
[CrossRef]

Escofet, J.

Fan, D. D.

W. K. Wong, C. W. M. Yuen, D. D. Fan, L. K. Chan, and E. H. F. Fung, “Stitching defect detection and classification using wavelet transform and BP neural network,” Expert Syst. Appl. 36, 3845–3856 (2009).
[CrossRef]

Fundakowski, R. A.

B. R. Suresh, R. A. Fundakowski, T. S. Levitt, and J. E. Overland, “Real-time automated visual inspection system for hot steel slabs,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5, 563–572 (1983).
[CrossRef]

Fung, E. H. F.

W. K. Wong, C. W. M. Yuen, D. D. Fan, L. K. Chan, and E. H. F. Fung, “Stitching defect detection and classification using wavelet transform and BP neural network,” Expert Syst. Appl. 36, 3845–3856 (2009).
[CrossRef]

Girosi, F.

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

Gonzalez, R. C.

R. C. Gonzalez and R. E. Woods, Digital Image Processing (Prentice Hall, 2008).

Guan, X. P.

X. Li, S. K. Tso, X. P. Guan, and Q. Huang, “Improving automatic detection of defects in castings by applying wavelet technique,” IEEE Trans. Ind. Electron. 53, 1927–1934 (2006).
[CrossRef]

Han, Y.

Y. Han and P. Shi, “An adaptive level-selecting wavelet transform for texture defect detection,” Image Vis. Comput. 25, 1239–1248 (2007).
[CrossRef]

Harlow, C. A.

R. T. Chin and C. A. Harlow, “Automated visual inspection: a survey,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 557–573 (1982).
[CrossRef]

Hsiao, B.

D. M. Tsai and B. Hsiao, “Automatic surface inspection using wavelet reconstruction,” Pattern Recogn. 34, 1285–1305 (2001).
[CrossRef]

Huang, Q.

X. Li, S. K. Tso, X. P. Guan, and Q. Huang, “Improving automatic detection of defects in castings by applying wavelet technique,” IEEE Trans. Ind. Electron. 53, 1927–1934 (2006).
[CrossRef]

Hung, C. Y.

D. M. Tsai and C. Y. Hung, “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, 4589–4607 (2005).
[CrossRef]

Jain, A. K.

Jeon, Y. J.

Jhang, K.

H. Kim, K. Jhang, M. Shin, and J. Kim, “A noncontact NDE method using a laser generated focused-Lamb wave with enhanced defect-detection ability and spatial resolution,” NDT&E Int. 39, 312–319 (2006).
[CrossRef]

Kang, T. J.

Kim, H.

H. Kim, K. Jhang, M. Shin, and J. Kim, “A noncontact NDE method using a laser generated focused-Lamb wave with enhanced defect-detection ability and spatial resolution,” NDT&E Int. 39, 312–319 (2006).
[CrossRef]

Kim, J.

H. Kim, K. Jhang, M. Shin, and J. Kim, “A noncontact NDE method using a laser generated focused-Lamb wave with enhanced defect-detection ability and spatial resolution,” NDT&E Int. 39, 312–319 (2006).
[CrossRef]

Kim, S. C.

Kim, S. W.

Kumar, A.

A. Kumar, “Neural network based detection of local textile defects,” Pattern Recogn. 36, 1645–1659 (2003).
[CrossRef]

Kuo, C. C. J.

T. Chang and C. C. J. Kuo, “Texture analysis and classification with tree-structured wavelet transform,” IEEE Trans. Image Process. 2, 429–441 (1993).
[CrossRef]

Lashkia, V.

V. Lashkia, “Defect detection in X-ray images using fuzzy reasoning,” Image Vis. Comput. 19, 261–269 (2001).
[CrossRef]

Levitt, T. S.

B. R. Suresh, R. A. Fundakowski, T. S. Levitt, and J. E. Overland, “Real-time automated visual inspection system for hot steel slabs,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5, 563–572 (1983).
[CrossRef]

Li, W. C.

W. C. Li and D. M. Tsai, “Wavelet-based defect detection in solar wafer images with inhomogeneous texture,” Pattern Recogn. 45, 742–756 (2012).

Li, X.

X. Li, S. K. Tso, X. P. Guan, and Q. Huang, “Improving automatic detection of defects in castings by applying wavelet technique,” IEEE Trans. Ind. Electron. 53, 1927–1934 (2006).
[CrossRef]

Lu, C. J.

C. J. Lu and D. M. Tsai, “Automatic defect inspection for LCDs using singular value decomposition,” Int. J. Adv. Manuf. Technol. 25, 53–61 (2005).
[CrossRef]

Mallat, S. G.

S. G. Mallat, “Theory for multiresolution signal decomposition: the wavelet representation,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 674–693 (1989).
[CrossRef]

Millán, M. S.

Mukherjee, R.

W. Sun, R. Mukherjee, P. Stroeve, A. Palazoglu, and J. A. Romagnoli, “A multi-resolution approach for line-edge roughness detection,” Microelectron. Eng. 86, 340–351 (2009).
[CrossRef]

Nassar, S. M.

A. Abouelela, H. M. Abbas, H. Eldeeb, A. A. Wahdan, and S. M. Nassar, “Automated vision system for localizing structural defects in textile fabrics,” Pattern Recogn. Lett. 26, 1435–1443 (2005).
[CrossRef]

Neild, S. A.

C. R. P. Courtney, B. W. Drinkwater, S. A. Neild, and P. D. Wilcox, “Factors affecting the ultrasonic intermodulation crack detection technique using bispectral analysis,” NDT&E Int. 41, 223–234 (2008).
[CrossRef]

Ng, M. K.

H. Y. T. Ngan, G. K. H. Pang, S. P. Yung, and M. K. Ng, “Wavelet based methods on patterned fabric defect detection,” Pattern Recogn. 38, 559–576 (2005).
[CrossRef]

Ngan, H. Y. T.

H. Y. T. Ngan, G. K. H. Pang, S. P. Yung, and M. K. Ng, “Wavelet based methods on patterned fabric defect detection,” Pattern Recogn. 38, 559–576 (2005).
[CrossRef]

Niyogi, P.

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

Overland, J. E.

B. R. Suresh, R. A. Fundakowski, T. S. Levitt, and J. E. Overland, “Real-time automated visual inspection system for hot steel slabs,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5, 563–572 (1983).
[CrossRef]

Palazoglu, A.

W. Sun, R. Mukherjee, P. Stroeve, A. Palazoglu, and J. A. Romagnoli, “A multi-resolution approach for line-edge roughness detection,” Microelectron. Eng. 86, 340–351 (2009).
[CrossRef]

Pang, G. K. H.

H. Y. T. Ngan, G. K. H. Pang, S. P. Yung, and M. K. Ng, “Wavelet based methods on patterned fabric defect detection,” Pattern Recogn. 38, 559–576 (2005).
[CrossRef]

Park, K. H.

Y. C. Song, D. H. Choi, and K. H. Park, “Wavelet-based image enhancement for defect detection in thin film transistor liquid crystal display panel,” Jpn. J. Appl. Phys. 45, 5069–5072 (2006).
[CrossRef]

Park, M. J.

C. S. Cho, B. M. Chung, and M. J. Park, “Development of real-time vision-based fabric inspection system,” IEEE Trans. Ind. Electron. 52, 1073–1079 (2005).
[CrossRef]

Park, N. K.

K. N. Choi, N. K. Park, and S. I. Yoo, “Image restoration for quantifying TFT-LCD defect levels,” IEICE Trans. Inf. Syst. 2, 322–329 (2008).

Poggio, T.

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

Ralló, M.

Romagnoli, J. A.

W. Sun, R. Mukherjee, P. Stroeve, A. Palazoglu, and J. A. Romagnoli, “A multi-resolution approach for line-edge roughness detection,” Microelectron. Eng. 86, 340–351 (2009).
[CrossRef]

Sanz, J. L. C.

Schölkopf, B.

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

Shi, P.

Y. Han and P. Shi, “An adaptive level-selecting wavelet transform for texture defect detection,” Image Vis. Comput. 25, 1239–1248 (2007).
[CrossRef]

Shin, M.

H. Kim, K. Jhang, M. Shin, and J. Kim, “A noncontact NDE method using a laser generated focused-Lamb wave with enhanced defect-detection ability and spatial resolution,” NDT&E Int. 39, 312–319 (2006).
[CrossRef]

Song, Y. C.

Y. C. Song, D. H. Choi, and K. H. Park, “Wavelet-based image enhancement for defect detection in thin film transistor liquid crystal display panel,” Jpn. J. Appl. Phys. 45, 5069–5072 (2006).
[CrossRef]

Stroeve, P.

W. Sun, R. Mukherjee, P. Stroeve, A. Palazoglu, and J. A. Romagnoli, “A multi-resolution approach for line-edge roughness detection,” Microelectron. Eng. 86, 340–351 (2009).
[CrossRef]

Sun, W.

W. Sun, R. Mukherjee, P. Stroeve, A. Palazoglu, and J. A. Romagnoli, “A multi-resolution approach for line-edge roughness detection,” Microelectron. Eng. 86, 340–351 (2009).
[CrossRef]

Sun, X.

H. Zhang, G. Wu, X. Sun, J. Xu, and K. Xu, “A new fast border search algorithm and its expansion,” in Proceedings of the IEEE International Conference on Automation and Logistics (IEEE, 2007), pp. 1886–1890.

Sung, K. K.

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

Suresh, B. R.

B. R. Suresh, R. A. Fundakowski, T. S. Levitt, and J. E. Overland, “Real-time automated visual inspection system for hot steel slabs,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5, 563–572 (1983).
[CrossRef]

Tao, Y.

Tsai, D. M.

W. C. Li and D. M. Tsai, “Wavelet-based defect detection in solar wafer images with inhomogeneous texture,” Pattern Recogn. 45, 742–756 (2012).

C. J. Lu and D. M. Tsai, “Automatic defect inspection for LCDs using singular value decomposition,” Int. J. Adv. Manuf. Technol. 25, 53–61 (2005).
[CrossRef]

D. M. Tsai and C. Y. Hung, “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, 4589–4607 (2005).
[CrossRef]

D. M. Tsai and C. H. Chiang, “Automatic band selection for wavelet reconstruction in the application of defect detection,” Image Vis. Comput. 21, 413–431 (2003).
[CrossRef]

D. M. Tsai and B. Hsiao, “Automatic surface inspection using wavelet reconstruction,” Pattern Recogn. 34, 1285–1305 (2001).
[CrossRef]

Tso, S. K.

X. Li, S. K. Tso, X. P. Guan, and Q. Huang, “Improving automatic detection of defects in castings by applying wavelet technique,” IEEE Trans. Ind. Electron. 53, 1927–1934 (2006).
[CrossRef]

Vapnik, V.

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

Wahdan, A. A.

A. Abouelela, H. M. Abbas, H. Eldeeb, A. A. Wahdan, and S. M. Nassar, “Automated vision system for localizing structural defects in textile fabrics,” Pattern Recogn. Lett. 26, 1435–1443 (2005).
[CrossRef]

Wilcox, P. D.

C. R. P. Courtney, B. W. Drinkwater, S. A. Neild, and P. D. Wilcox, “Factors affecting the ultrasonic intermodulation crack detection technique using bispectral analysis,” NDT&E Int. 41, 223–234 (2008).
[CrossRef]

Wong, W. K.

W. K. Wong, C. W. M. Yuen, D. D. Fan, L. K. Chan, and E. H. F. Fung, “Stitching defect detection and classification using wavelet transform and BP neural network,” Expert Syst. Appl. 36, 3845–3856 (2009).
[CrossRef]

Woods, R. E.

R. C. Gonzalez and R. E. Woods, Digital Image Processing (Prentice Hall, 2008).

Wu, G.

H. Zhang, G. Wu, X. Sun, J. Xu, and K. Xu, “A new fast border search algorithm and its expansion,” in Proceedings of the IEEE International Conference on Automation and Logistics (IEEE, 2007), pp. 1886–1890.

Xie, X.

X. Xie, “A review of recent advances in surface defect detection using texture analysis techniques,” Electron Lett. Comput. Vis. Image Anal. 7, 1–22 (2008).

Xu, J.

H. Zhang, G. Wu, X. Sun, J. Xu, and K. Xu, “A new fast border search algorithm and its expansion,” in Proceedings of the IEEE International Conference on Automation and Logistics (IEEE, 2007), pp. 1886–1890.

Xu, K.

H. Zhang, G. Wu, X. Sun, J. Xu, and K. Xu, “A new fast border search algorithm and its expansion,” in Proceedings of the IEEE International Conference on Automation and Logistics (IEEE, 2007), pp. 1886–1890.

Yoo, S. I.

K. N. Choi, N. K. Park, and S. I. Yoo, “Image restoration for quantifying TFT-LCD defect levels,” IEICE Trans. Inf. Syst. 2, 322–329 (2008).

Yuen, C. W. M.

W. K. Wong, C. W. M. Yuen, D. D. Fan, L. K. Chan, and E. H. F. Fung, “Stitching defect detection and classification using wavelet transform and BP neural network,” Expert Syst. Appl. 36, 3845–3856 (2009).
[CrossRef]

Yun, J. P.

Yung, S. P.

H. Y. T. Ngan, G. K. H. Pang, S. P. Yung, and M. K. Ng, “Wavelet based methods on patterned fabric defect detection,” Pattern Recogn. 38, 559–576 (2005).
[CrossRef]

Zhang, H.

H. Zhang, G. Wu, X. Sun, J. Xu, and K. Xu, “A new fast border search algorithm and its expansion,” in Proceedings of the IEEE International Conference on Automation and Logistics (IEEE, 2007), pp. 1886–1890.

Zhou, Z. F.

Appl. Opt. (3)

Data Min. Knowl. Discov. (1)

C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Min. Knowl. Discov. 2, 121–167 (1998).
[CrossRef]

Electron Lett. Comput. Vis. Image Anal. (1)

X. Xie, “A review of recent advances in surface defect detection using texture analysis techniques,” Electron Lett. Comput. Vis. Image Anal. 7, 1–22 (2008).

Expert Syst. Appl. (1)

W. K. Wong, C. W. M. Yuen, D. D. Fan, L. K. Chan, and E. H. F. Fung, “Stitching defect detection and classification using wavelet transform and BP neural network,” Expert Syst. Appl. 36, 3845–3856 (2009).
[CrossRef]

IEEE Trans. Image Process. (1)

T. Chang and C. C. J. Kuo, “Texture analysis and classification with tree-structured wavelet transform,” IEEE Trans. Image Process. 2, 429–441 (1993).
[CrossRef]

IEEE Trans. Ind. Electron. (2)

C. S. Cho, B. M. Chung, and M. J. Park, “Development of real-time vision-based fabric inspection system,” IEEE Trans. Ind. Electron. 52, 1073–1079 (2005).
[CrossRef]

X. Li, S. K. Tso, X. P. Guan, and Q. Huang, “Improving automatic detection of defects in castings by applying wavelet technique,” IEEE Trans. Ind. Electron. 53, 1927–1934 (2006).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell. (3)

B. R. Suresh, R. A. Fundakowski, T. S. Levitt, and J. E. Overland, “Real-time automated visual inspection system for hot steel slabs,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5, 563–572 (1983).
[CrossRef]

S. G. Mallat, “Theory for multiresolution signal decomposition: the wavelet representation,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 674–693 (1989).
[CrossRef]

R. T. Chin and C. A. Harlow, “Automated visual inspection: a survey,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 557–573 (1982).
[CrossRef]

IEEE Trans. Signal Process. (1)

B. Schölkopf, K. K. Sung, C. J. C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Process. 45, 2758–2765 (1997).
[CrossRef]

IEICE Trans. Inf. Syst. (1)

K. N. Choi, N. K. Park, and S. I. Yoo, “Image restoration for quantifying TFT-LCD defect levels,” IEICE Trans. Inf. Syst. 2, 322–329 (2008).

Image Vis. Comput. (3)

V. Lashkia, “Defect detection in X-ray images using fuzzy reasoning,” Image Vis. Comput. 19, 261–269 (2001).
[CrossRef]

Y. Han and P. Shi, “An adaptive level-selecting wavelet transform for texture defect detection,” Image Vis. Comput. 25, 1239–1248 (2007).
[CrossRef]

D. M. Tsai and C. H. Chiang, “Automatic band selection for wavelet reconstruction in the application of defect detection,” Image Vis. Comput. 21, 413–431 (2003).
[CrossRef]

Int. J. Adv. Manuf. Technol. (1)

C. J. Lu and D. M. Tsai, “Automatic defect inspection for LCDs using singular value decomposition,” Int. J. Adv. Manuf. Technol. 25, 53–61 (2005).
[CrossRef]

Int. J. Prod. Res. (1)

D. M. Tsai and C. Y. Hung, “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, 4589–4607 (2005).
[CrossRef]

J. Opt. Soc. Am. A (4)

Jpn. J. Appl. Phys. (1)

Y. C. Song, D. H. Choi, and K. H. Park, “Wavelet-based image enhancement for defect detection in thin film transistor liquid crystal display panel,” Jpn. J. Appl. Phys. 45, 5069–5072 (2006).
[CrossRef]

Microelectron. Eng. (1)

W. Sun, R. Mukherjee, P. Stroeve, A. Palazoglu, and J. A. Romagnoli, “A multi-resolution approach for line-edge roughness detection,” Microelectron. Eng. 86, 340–351 (2009).
[CrossRef]

NDT&E Int. (2)

H. Kim, K. Jhang, M. Shin, and J. Kim, “A noncontact NDE method using a laser generated focused-Lamb wave with enhanced defect-detection ability and spatial resolution,” NDT&E Int. 39, 312–319 (2006).
[CrossRef]

C. R. P. Courtney, B. W. Drinkwater, S. A. Neild, and P. D. Wilcox, “Factors affecting the ultrasonic intermodulation crack detection technique using bispectral analysis,” NDT&E Int. 41, 223–234 (2008).
[CrossRef]

Opt. Eng. (1)

J. P. Yun, S. H. Choi, and S. W. Kim, “Vision-based defect detection of scale-covered steel billet surfaces,” Opt. Eng. 48, 037205 (2009).
[CrossRef]

Pattern Recogn. (4)

D. M. Tsai and B. Hsiao, “Automatic surface inspection using wavelet reconstruction,” Pattern Recogn. 34, 1285–1305 (2001).
[CrossRef]

H. Y. T. Ngan, G. K. H. Pang, S. P. Yung, and M. K. Ng, “Wavelet based methods on patterned fabric defect detection,” Pattern Recogn. 38, 559–576 (2005).
[CrossRef]

W. C. Li and D. M. Tsai, “Wavelet-based defect detection in solar wafer images with inhomogeneous texture,” Pattern Recogn. 45, 742–756 (2012).

A. Kumar, “Neural network based detection of local textile defects,” Pattern Recogn. 36, 1645–1659 (2003).
[CrossRef]

Pattern Recogn. Lett. (1)

A. Abouelela, H. M. Abbas, H. Eldeeb, A. A. Wahdan, and S. M. Nassar, “Automated vision system for localizing structural defects in textile fabrics,” Pattern Recogn. Lett. 26, 1435–1443 (2005).
[CrossRef]

Other (2)

H. Zhang, G. Wu, X. Sun, J. Xu, and K. Xu, “A new fast border search algorithm and its expansion,” in Proceedings of the IEEE International Conference on Automation and Logistics (IEEE, 2007), pp. 1886–1890.

R. C. Gonzalez and R. E. Woods, Digital Image Processing (Prentice Hall, 2008).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (13)

Fig. 1.
Fig. 1.

SDD system.

Fig. 2.
Fig. 2.

Billet images: (a) image obtained at 1600×1024 pixel resolution, (b) Sobel image and edge points calculated by DP, (c) final boundary points calculated by LBSA, and (d) image segmented by the proposed method.

Fig. 3.
Fig. 3.

Billet surface images: (a) billet surface image without defects; (b)–(c) billet surface images with various shapes and size of scales; (d)–(f) billet surface images with various size of cracks: (d) small-sized cracks, (e) medium-sized cracks, and (f) large-sized crack.

Fig. 4.
Fig. 4.

Conceptual diagram of LBSA.

Fig. 5.
Fig. 5.

2D analysis wavelet filter bank.

Fig. 6.
Fig. 6.

Reconstucted wavelet images with five-level decompositon: (a) original image; (b) restored image from approximation; (c)–(e) are restored image from horizontal, vertical, and diagonal detail, respectively.

Fig. 7.
Fig. 7.

Wavelet energy distributions obtained from experimental samples (solid line: corner cracks; dashed line: scales): (a) horizontal energy; (b) vertical energy; (c) diagonal energy; and (d)–(f) average energy of (a)–(c), respectively.

Fig. 8.
Fig. 8.

2D synthesis wavelet filter bank with reconstruction weights.

Fig. 9.
Fig. 9.

Wavelet-reconstructed images: (a) and (c) billet surface images containing corner cracks; (e) billet surface image containing scales; (b), (d), and (f) wavelet reconstructed images of (a), (c), and (e), respectively.

Fig. 10.
Fig. 10.

Stepwise result of the binarization: (a) billet surface image, (b) wavelet reconstructed image, (c) binary image with low thresholding value, (d) binary image with high thresholding value, and (e) binary image with double thresholding.

Fig. 11.
Fig. 11.

Defective blobs and normal blobs (scales): (a)–(c) are defective blob images; (d)–(f) are normal blob images.

Fig. 12.
Fig. 12.

Flowchart of the wavelet-reconstruction-based inspection algorithm for corner cracks in steel billets.

Fig. 13.
Fig. 13.

Billet images containing different sizes of corner cracks: (a), (c), and (e) billet surface images; (b), (d), and (f) resulting images after the detection of (a), (c), and (e), respectively.

Tables (5)

Tables Icon

Table 1. Classification Results with the SVM Classifier

Tables Icon

Table 2. Normalized Wavelet Energies for Figs. 4(d)4(f) (Five-level Decomposition)

Tables Icon

Table 3. Weight Coefficients for Wavelet Reconstruction

Tables Icon

Table 4. Effect of the Threshold Values on the Performance of the Defect Detection

Tables Icon

Table 5. Measured Processing Time for Each Step

Equations (26)

Equations on this page are rendered with MathJax. Learn more.

Wφ(j0,k)=1Mxf(x)φj0,k(x),
Wψ(j,k)=1Mxf(x)ψj,k(x),
f(x)=1MkWφ(j0,k)φj0,k(x)+1Mj=j0kWψ(j,k)ψj,k(x).
Wφ(j,k)=mhφ(m2k)Wφ(j+1,m),
Wψ(j,k)=mhψ(m2k)Wφ(j+1,m).
Wφ(j,k)=hφ(n)*Wφ(j+1,n)|n=2k,k0,
Wψ(j,k)=hψ(n)*Wφ(j+1,n)|n=2k,k0,
W¯A=0.
W¯jH=wjH·WjHW¯jV=wjV·WjVW¯jD=wjD·WjD.
ifD[Hj,Vj,Dj]>N[Hj,Vj,Dj]α[Hj,Vj,Dj]=D[Hj,Vj,Dj]/N[Hj,Vj,Dj]elseα[Hj,Vj,Dj]=0,
wHj=αHj/max[αHj]wVj=αVj/max[αVj]wDj=αDj/max[αDj],
Thigh=mean[R(x,y]αhigh×std[R(x,y)]Tlow=mean[R(x,y]αlow×std[R(x,y)],
ifThigh>C(x,y),thenBhigh(x,y)=1,elseBhigh(x,y)=0,
ifTlow>C(x,y),thenBlow(x,y)=1,elseBlow(x,y)=0,
C(x,y)=R(x+156,y)(x=1,2,,200,y=1,2,,1600).
ifLhigh(n)Llow(m),thenLdouble(n)=Llow(m),elseLdouble(n)=0.
m=i=0L1rip(ri).
σ=i=0L1(rim)2p(ri).
R=11/(1+σ2).
U=i=0L1p2(ri).
μ3=i=0L1(rim)3p(ri).
e=i=0L1p(ri)log2p(ri).
AB{A:Area of BlobB:Area of Bounding Box.
P22πA{A:Area of Blobp:Perimeter of Blob.
AC{A:Area of BlobC:Area of Conver image.
1MinorAxisLengthMajorAxisLength.

Metrics