Abstract

Presently, product inspection based on vision systems is an important part of the steel-manufacturing industry. In this work, we focus on the detection of seam cracks in the edge region of steel plates. Seam cracks are generated in the vertical direction, and their width range is 0.2–0.6 mm. Moreover, the gray values of seam cracks are only 20–30 gray levels lower than those of the neighboring surface. Owing to these characteristics, we propose a new algorithm for detecting seam cracks using a Gabor filter combination method. To enhance the performance, we extracted features of seam cracks and employed a support vector machine classifier. The experimental results show that the proposed algorithm is suitable for detecting seam cracks.

© 2014 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. Y. H. Tseng and D. M. Tsai, “Defect detection of uneven brightness in low-contrast images using basis image representation,” Pattern Recogn. 43, 1129–1141 (2010).
    [CrossRef]
  2. J. H. Oh, B. J. Yun, S. Y. Kim, and K. H. Park, “A development of the TFT-LCD image defect inspection method based on human visual system,” IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 91, 1400–1407 (2008).
  3. 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]
  4. C. Chan and G. K. H. Pang, “Fabric defect detection by Fourier analysis,” IEEE Trans. Ind. Appl. 36, 1267–1276 (2000).
    [CrossRef]
  5. L. M. Sanchez-Brea, P. Siegmann, M. A. Rebollo, and E. Bernabeu, “Optical technique for the automatic detection and measurement of surface defects on thin metallic wires,” Appl. Opt. 39, 539–545 (2000).
    [CrossRef]
  6. 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]
  7. J. P. Yun, Y.-J. Jeon, D.-C. Choi, and S. W. Kim, “Real-time defect detection of steel wire rods using orthogonal wavelet filters optimized by univariate dynamic encoding algorithm for searches (uDEAS),” J. Opt. Soc. Am. A 29, 797–807 (2012).
    [CrossRef]
  8. A. Kumar and G. K. H. Pang, “Defect detection in textured materials using Gabor filters,” IEEE Trans. Ind. Appl. 38, 425–440 (2002).
    [CrossRef]
  9. J. P. Yun, S. H. Choi, J. W. Kim, and S. W. Kim, “Automatic detection of cracks in raw steel block using Gabor filter optimized by univariate dynamic encoding algorithm for searches (uDEAS),” NDT and E Int. 42, 389–397 (2009).
  10. N. A. Kaliteevsky, V. E. Semenov, V. D. Glezer, and V. E. Gauselman, “Algorithm of invariant image description by the use of a modified Gabor transform,” Appl. Opt. 33, 5256–5261 (1994).
    [CrossRef]
  11. D. Gabor, “Theory of communication,” J. Inst. Electr. Eng. London 93, 429–457 (1946).
  12. J. G. Daugman, “Uncertainty relation for resolution in space, spatial-frequency and orientation optimized by two-dimensional visual cortical filter,” J. Opt. Soc. Am. A 2, 1160–1169 (1985).
    [CrossRef]
  13. A. Bodnarova, M. Bennamoun, and S. Latham, “Optimal Gabor filters for textile flaw detection,” Pattern Recogn. 35, 2973–2991 (2002).
    [CrossRef]
  14. D. Casasent and J. Smokelin, “Real, imaginary, and clutter Gabor filter fusion for detection with reduced false alarms,” Opt. Eng. 33, 2255–2263 (1994).
    [CrossRef]
  15. C. Cortes and V. Vapnik, “Support-vector network,” Mach. Learn. 20, 273–297 (1995).
  16. C.-W. Hsu, C.-C. Chang, and C.-J. Lin, “A practical guide to support vector classification,” 2003, http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf .

2012

2011

2010

Y. H. Tseng and D. M. Tsai, “Defect detection of uneven brightness in low-contrast images using basis image representation,” Pattern Recogn. 43, 1129–1141 (2010).
[CrossRef]

2009

J. P. Yun, S. H. Choi, J. W. Kim, and S. W. Kim, “Automatic detection of cracks in raw steel block using Gabor filter optimized by univariate dynamic encoding algorithm for searches (uDEAS),” NDT and E Int. 42, 389–397 (2009).

2008

J. H. Oh, B. J. Yun, S. Y. Kim, and K. H. Park, “A development of the TFT-LCD image defect inspection method based on human visual system,” IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 91, 1400–1407 (2008).

2005

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]

2002

A. Bodnarova, M. Bennamoun, and S. Latham, “Optimal Gabor filters for textile flaw detection,” Pattern Recogn. 35, 2973–2991 (2002).
[CrossRef]

A. Kumar and G. K. H. Pang, “Defect detection in textured materials using Gabor filters,” IEEE Trans. Ind. Appl. 38, 425–440 (2002).
[CrossRef]

2000

1995

C. Cortes and V. Vapnik, “Support-vector network,” Mach. Learn. 20, 273–297 (1995).

1994

N. A. Kaliteevsky, V. E. Semenov, V. D. Glezer, and V. E. Gauselman, “Algorithm of invariant image description by the use of a modified Gabor transform,” Appl. Opt. 33, 5256–5261 (1994).
[CrossRef]

D. Casasent and J. Smokelin, “Real, imaginary, and clutter Gabor filter fusion for detection with reduced false alarms,” Opt. Eng. 33, 2255–2263 (1994).
[CrossRef]

1985

1946

D. Gabor, “Theory of communication,” J. Inst. Electr. Eng. London 93, 429–457 (1946).

Bennamoun, M.

A. Bodnarova, M. Bennamoun, and S. Latham, “Optimal Gabor filters for textile flaw detection,” Pattern Recogn. 35, 2973–2991 (2002).
[CrossRef]

Bernabeu, E.

Bodnarova, A.

A. Bodnarova, M. Bennamoun, and S. Latham, “Optimal Gabor filters for textile flaw detection,” Pattern Recogn. 35, 2973–2991 (2002).
[CrossRef]

Casasent, D.

D. Casasent and J. Smokelin, “Real, imaginary, and clutter Gabor filter fusion for detection with reduced false alarms,” Opt. Eng. 33, 2255–2263 (1994).
[CrossRef]

Chan, C.

C. Chan and G. K. H. Pang, “Fabric defect detection by Fourier analysis,” IEEE Trans. Ind. Appl. 36, 1267–1276 (2000).
[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.-C.

Choi, S. H.

J. P. Yun, S. H. Choi, J. W. Kim, and S. W. Kim, “Automatic detection of cracks in raw steel block using Gabor filter optimized by univariate dynamic encoding algorithm for searches (uDEAS),” NDT and E Int. 42, 389–397 (2009).

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]

Cortes, C.

C. Cortes and V. Vapnik, “Support-vector network,” Mach. Learn. 20, 273–297 (1995).

Daugman, J. G.

Gabor, D.

D. Gabor, “Theory of communication,” J. Inst. Electr. Eng. London 93, 429–457 (1946).

Gauselman, V. E.

Glezer, V. D.

Jeon, Y.-J.

Kaliteevsky, N. A.

Kim, J. W.

J. P. Yun, S. H. Choi, J. W. Kim, and S. W. Kim, “Automatic detection of cracks in raw steel block using Gabor filter optimized by univariate dynamic encoding algorithm for searches (uDEAS),” NDT and E Int. 42, 389–397 (2009).

Kim, S. W.

Kim, S. Y.

J. H. Oh, B. J. Yun, S. Y. Kim, and K. H. Park, “A development of the TFT-LCD image defect inspection method based on human visual system,” IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 91, 1400–1407 (2008).

Kumar, A.

A. Kumar and G. K. H. Pang, “Defect detection in textured materials using Gabor filters,” IEEE Trans. Ind. Appl. 38, 425–440 (2002).
[CrossRef]

Latham, S.

A. Bodnarova, M. Bennamoun, and S. Latham, “Optimal Gabor filters for textile flaw detection,” Pattern Recogn. 35, 2973–2991 (2002).
[CrossRef]

Oh, J. H.

J. H. Oh, B. J. Yun, S. Y. Kim, and K. H. Park, “A development of the TFT-LCD image defect inspection method based on human visual system,” IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 91, 1400–1407 (2008).

Pang, G. K. H.

A. Kumar and G. K. H. Pang, “Defect detection in textured materials using Gabor filters,” IEEE Trans. Ind. Appl. 38, 425–440 (2002).
[CrossRef]

C. Chan and G. K. H. Pang, “Fabric defect detection by Fourier analysis,” IEEE Trans. Ind. Appl. 36, 1267–1276 (2000).
[CrossRef]

Park, K. H.

J. H. Oh, B. J. Yun, S. Y. Kim, and K. H. Park, “A development of the TFT-LCD image defect inspection method based on human visual system,” IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 91, 1400–1407 (2008).

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]

Rebollo, M. A.

Sanchez-Brea, L. M.

Semenov, V. E.

Siegmann, P.

Smokelin, J.

D. Casasent and J. Smokelin, “Real, imaginary, and clutter Gabor filter fusion for detection with reduced false alarms,” Opt. Eng. 33, 2255–2263 (1994).
[CrossRef]

Tsai, D. M.

Y. H. Tseng and D. M. Tsai, “Defect detection of uneven brightness in low-contrast images using basis image representation,” Pattern Recogn. 43, 1129–1141 (2010).
[CrossRef]

Tseng, Y. H.

Y. H. Tseng and D. M. Tsai, “Defect detection of uneven brightness in low-contrast images using basis image representation,” Pattern Recogn. 43, 1129–1141 (2010).
[CrossRef]

Vapnik, V.

C. Cortes and V. Vapnik, “Support-vector network,” Mach. Learn. 20, 273–297 (1995).

Yun, B. J.

J. H. Oh, B. J. Yun, S. Y. Kim, and K. H. Park, “A development of the TFT-LCD image defect inspection method based on human visual system,” IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 91, 1400–1407 (2008).

Yun, J. P.

Appl. Opt.

IEEE Trans. Ind. Appl.

C. Chan and G. K. H. Pang, “Fabric defect detection by Fourier analysis,” IEEE Trans. Ind. Appl. 36, 1267–1276 (2000).
[CrossRef]

A. Kumar and G. K. H. Pang, “Defect detection in textured materials using Gabor filters,” IEEE Trans. Ind. Appl. 38, 425–440 (2002).
[CrossRef]

IEEE Trans. Ind. Electron.

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]

IEICE Trans. Fundam. Electron. Commun. Comput. Sci.

J. H. Oh, B. J. Yun, S. Y. Kim, and K. H. Park, “A development of the TFT-LCD image defect inspection method based on human visual system,” IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 91, 1400–1407 (2008).

J. Inst. Electr. Eng. London

D. Gabor, “Theory of communication,” J. Inst. Electr. Eng. London 93, 429–457 (1946).

J. Opt. Soc. Am. A

Mach. Learn.

C. Cortes and V. Vapnik, “Support-vector network,” Mach. Learn. 20, 273–297 (1995).

NDT and E Int.

J. P. Yun, S. H. Choi, J. W. Kim, and S. W. Kim, “Automatic detection of cracks in raw steel block using Gabor filter optimized by univariate dynamic encoding algorithm for searches (uDEAS),” NDT and E Int. 42, 389–397 (2009).

Opt. Eng.

D. Casasent and J. Smokelin, “Real, imaginary, and clutter Gabor filter fusion for detection with reduced false alarms,” Opt. Eng. 33, 2255–2263 (1994).
[CrossRef]

Pattern Recogn.

A. Bodnarova, M. Bennamoun, and S. Latham, “Optimal Gabor filters for textile flaw detection,” Pattern Recogn. 35, 2973–2991 (2002).
[CrossRef]

Y. H. Tseng and D. M. Tsai, “Defect detection of uneven brightness in low-contrast images using basis image representation,” Pattern Recogn. 43, 1129–1141 (2010).
[CrossRef]

Other

C.-W. Hsu, C.-C. Chang, and C.-J. Lin, “A practical guide to support vector classification,” 2003, http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf .

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 (8)

Fig. 1.
Fig. 1.

Structure of automated inspection system.

Fig. 2.
Fig. 2.

Surface image with seam cracks.

Fig. 3.
Fig. 3.

(a) Steel plate image and (b) profile after gradient filtering.

Fig. 4.
Fig. 4.

Block diagram of the proposed algorithm.

Fig. 5.
Fig. 5.

Images after segmentation.

Fig. 6.
Fig. 6.

(a) Artificial defect and noise and (b) Gabor-filtered image.

Fig. 7.
Fig. 7.

Stepwise resultant images: (a) segmented image after gray-level intensity transformation; (b) Gabor-filtered image; (c) binary image with high threshold value after size filtering; (d) binary image with low threshold value; (e) binary image with double threshold value.

Fig. 8.
Fig. 8.

(a) Image after ROI selection and (b) orientation, bounding box, and major and minor axis lengths.

Tables (3)

Tables Icon

Table 1. Parameters of Two Gabor Filters

Tables Icon

Table 2. Training Result of SVM

Tables Icon

Table 3. Experimental Results

Equations (12)

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

f(x,y)=12πσxσyexp[12(x2σx2+y2σy2)]exp(2πju0x).
f(x,y)=12πσxσyexp[12{(xσx)2+(yσy)2}]cos(2πjfx),
x=xcosθ+ysinθ,y=xsinθ+ycosθ.
P(x)=1Ny=1NI(x,y),
IfF(x,y)<T,thenT(x,y)=F(x,y)elseT(x,y)=T,
Gi(x,y)=T(x,y)*gi(x,y)=m=1M1n=1N1gi(m,n)T(xm,yn),
Ei=meantop0.1{Gi(x,y)},
G(x,y)=α×G1(x,y)+(1α)×G2(x,y),
α=11+exp{(α0.5)/C}
α=E1E1+E2,
Thigh=mean{G(x,y)}+αhigh×std{G(x,y)},Tlow=mean{G(x,y)}+αlow×std{G(x,y)},
Conver=mean{HPP>0},Conhor=mean{VPP>0},

Metrics