Abstract

One of the most commonly used optical methods for defect detection is radiographic inspection. Compared with methods that extract defects directly from the radiography image, model-based methods deal with the case of an object with complex structure well. However, detection of small low-contrast defects in nonuniformly illuminated images is still a major challenge for them. In this paper, we present a new method based on the grayscale arranging pairs (GAP) feature to detect casting defects in radiography images automatically. First, a model is built using pixel pairs with a stable intensity relationship based on the GAP feature from previously acquired images. Second, defects can be extracted by comparing the difference of intensity-difference signs between the input image and the model statistically. The robustness of the proposed method to noise and illumination variations has been verified on casting radioscopic images with defects. The experimental results showed that the average computation time of the proposed method in the testing stage is 28 ms per image on a computer with a Pentium Core 2 Duo 3.00 GHz processor. For the comparison, we also evaluated the performance of the proposed method as well as that of the mixture-of-Gaussian-based and crossing line profile methods. The proposed method achieved 2.7% and 2.0% false negative rates in the noise and illumination variation experiments, respectively.

© 2013 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. D. Mery and D. Filbert, “Automated flaw detection in aluminum castings based on the tracking of potential defects in a radioscopic image sequence,” IEEE Trans. Robot. Autom. 18, 890–901 (2002).
    [CrossRef]
  3. D. Mery, R. da Silva, L. P. Caloba, and J. M. A. Rebello, “Pattern recognition in the automatic inspection of aluminium castings,” Insight 45, 475–483 (2003).
  4. V. Rebuffel, S. Sood, and B. Blakeley, “Defect detection method in digital radiography for porosity in magnesium castings,” in European Conference on Non-destructive Testing (ECNDT), Berlin, 2006.
  5. I. G. Kazantseva, I. Lemahieub, G. I. Salova, and R. Denysc, “Statistical detection of defects in radiographic images in nondestructive testing,” Signal Process. 82, 791–801 (2002).
    [CrossRef]
  6. Alaknanda, R. S. Anand, and P. Kumar, “Flaw detection in radiographic weld images using morphological approach,” NDT&E International 39, 29–33 (2006).
    [CrossRef]
  7. J. Shao, D. Dua, B. Chang, and H. Shi, “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence,” NDT&E International 46, 14–21 (2012).
    [CrossRef]
  8. H. F. Ng, “Automatic thresholding for defect detection,” Pattern Recogn. Lett. 27, 1644–1649 (2006).
    [CrossRef]
  9. J. C. Liu and G. Pok, “Texture edge detection by feature encoding and predictive model,” in Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (1999), pp. 1105–1108.
  10. J. M. Kosanetzky and H. Putzbach, “Modern x-ray inspection in the automotive industry,” in Proceedings of the 14th World Conference of NDT (Ashgate Publishing Company, 1996), Vol. 3, pp. 1325–1328.
  11. V. Kaftandjian, A. Joly, T. Odievre, M. Courbiere, and C. Hantrais, “Automatic detection and characterization of aluminum weld defects: comparison between radiography, radioscopy and human interpretation,” in Proceedings of the Seventh European Conference on Nondestructive Testing (1998), pp. 1179–1186.
  12. D. Mery, T. Jaeger, and D. Filbert, “A review of methods for automated recognition of casting defects,” Insight 44, 428–436 (2002).
  13. G. Wang and T. Liao, “Automatic identification of different types of welding defects in radiographic images,” NDT&E International 35, 519–528 (2002).
    [CrossRef]
  14. D. H. Shi, T. Gang, S. Y. Yang, and Y. Yuan, “Research on segmentation and distribution features of small defects in precision weldments with complex structure,” NDT&E International 40, 397–404 (2007).
    [CrossRef]
  15. V. Lashkiam, “Defect detection in x-ray images using fuzzy reasoning,” Image Vis. Comput. 19, 261–269 (2001).
    [CrossRef]
  16. X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
    [CrossRef]
  17. X. Zhao, Y. Satoh, H. Takauji, and S. Kaneko, “Robust tracking using particle filter with a hybrid feature,” IEICE Trans. 95, 646–657 (2012).
  18. D. Mery, “Crossing line profile: a new approach to detecting defects in aluminium castings,” in Proceedings of the Scandinavian Conference on Image Analysis (SCIA) (Springer-Verlag, 2003), pp. 725–732.
  19. Balu toolbox MATLAB, http://dmery.ing.puc.cl/index.php/balu/ .
  20. C. Stauffer and W. E. L. Grimson, “Learning patterns of activity using realtime tracking,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 747–757 (2000).
    [CrossRef]

2012 (2)

J. Shao, D. Dua, B. Chang, and H. Shi, “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence,” NDT&E International 46, 14–21 (2012).
[CrossRef]

X. Zhao, Y. Satoh, H. Takauji, and S. Kaneko, “Robust tracking using particle filter with a hybrid feature,” IEICE Trans. 95, 646–657 (2012).

2011 (1)

X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
[CrossRef]

2007 (1)

D. H. Shi, T. Gang, S. Y. Yang, and Y. Yuan, “Research on segmentation and distribution features of small defects in precision weldments with complex structure,” NDT&E International 40, 397–404 (2007).
[CrossRef]

2006 (3)

Alaknanda, R. S. Anand, and P. Kumar, “Flaw detection in radiographic weld images using morphological approach,” NDT&E International 39, 29–33 (2006).
[CrossRef]

H. F. Ng, “Automatic thresholding for defect detection,” Pattern Recogn. Lett. 27, 1644–1649 (2006).
[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]

2003 (1)

D. Mery, R. da Silva, L. P. Caloba, and J. M. A. Rebello, “Pattern recognition in the automatic inspection of aluminium castings,” Insight 45, 475–483 (2003).

2002 (4)

I. G. Kazantseva, I. Lemahieub, G. I. Salova, and R. Denysc, “Statistical detection of defects in radiographic images in nondestructive testing,” Signal Process. 82, 791–801 (2002).
[CrossRef]

D. Mery and D. Filbert, “Automated flaw detection in aluminum castings based on the tracking of potential defects in a radioscopic image sequence,” IEEE Trans. Robot. Autom. 18, 890–901 (2002).
[CrossRef]

D. Mery, T. Jaeger, and D. Filbert, “A review of methods for automated recognition of casting defects,” Insight 44, 428–436 (2002).

G. Wang and T. Liao, “Automatic identification of different types of welding defects in radiographic images,” NDT&E International 35, 519–528 (2002).
[CrossRef]

2001 (1)

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

2000 (1)

C. Stauffer and W. E. L. Grimson, “Learning patterns of activity using realtime tracking,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 747–757 (2000).
[CrossRef]

Alaknanda,

Alaknanda, R. S. Anand, and P. Kumar, “Flaw detection in radiographic weld images using morphological approach,” NDT&E International 39, 29–33 (2006).
[CrossRef]

Anand, R. S.

Alaknanda, R. S. Anand, and P. Kumar, “Flaw detection in radiographic weld images using morphological approach,” NDT&E International 39, 29–33 (2006).
[CrossRef]

Blakeley, B.

V. Rebuffel, S. Sood, and B. Blakeley, “Defect detection method in digital radiography for porosity in magnesium castings,” in European Conference on Non-destructive Testing (ECNDT), Berlin, 2006.

Caloba, L. P.

D. Mery, R. da Silva, L. P. Caloba, and J. M. A. Rebello, “Pattern recognition in the automatic inspection of aluminium castings,” Insight 45, 475–483 (2003).

Chang, B.

J. Shao, D. Dua, B. Chang, and H. Shi, “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence,” NDT&E International 46, 14–21 (2012).
[CrossRef]

Courbiere, M.

V. Kaftandjian, A. Joly, T. Odievre, M. Courbiere, and C. Hantrais, “Automatic detection and characterization of aluminum weld defects: comparison between radiography, radioscopy and human interpretation,” in Proceedings of the Seventh European Conference on Nondestructive Testing (1998), pp. 1179–1186.

da Silva, R.

D. Mery, R. da Silva, L. P. Caloba, and J. M. A. Rebello, “Pattern recognition in the automatic inspection of aluminium castings,” Insight 45, 475–483 (2003).

Denysc, R.

I. G. Kazantseva, I. Lemahieub, G. I. Salova, and R. Denysc, “Statistical detection of defects in radiographic images in nondestructive testing,” Signal Process. 82, 791–801 (2002).
[CrossRef]

Dua, D.

J. Shao, D. Dua, B. Chang, and H. Shi, “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence,” NDT&E International 46, 14–21 (2012).
[CrossRef]

Filbert, D.

D. Mery and D. Filbert, “Automated flaw detection in aluminum castings based on the tracking of potential defects in a radioscopic image sequence,” IEEE Trans. Robot. Autom. 18, 890–901 (2002).
[CrossRef]

D. Mery, T. Jaeger, and D. Filbert, “A review of methods for automated recognition of casting defects,” Insight 44, 428–436 (2002).

Gang, T.

D. H. Shi, T. Gang, S. Y. Yang, and Y. Yuan, “Research on segmentation and distribution features of small defects in precision weldments with complex structure,” NDT&E International 40, 397–404 (2007).
[CrossRef]

Grimson, W. E. L.

C. Stauffer and W. E. L. Grimson, “Learning patterns of activity using realtime tracking,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 747–757 (2000).
[CrossRef]

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]

Hantrais, C.

V. Kaftandjian, A. Joly, T. Odievre, M. Courbiere, and C. Hantrais, “Automatic detection and characterization of aluminum weld defects: comparison between radiography, radioscopy and human interpretation,” in Proceedings of the Seventh European Conference on Nondestructive Testing (1998), pp. 1179–1186.

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]

Iwata, K.

X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
[CrossRef]

Jaeger, T.

D. Mery, T. Jaeger, and D. Filbert, “A review of methods for automated recognition of casting defects,” Insight 44, 428–436 (2002).

Joly, A.

V. Kaftandjian, A. Joly, T. Odievre, M. Courbiere, and C. Hantrais, “Automatic detection and characterization of aluminum weld defects: comparison between radiography, radioscopy and human interpretation,” in Proceedings of the Seventh European Conference on Nondestructive Testing (1998), pp. 1179–1186.

Kaftandjian, V.

V. Kaftandjian, A. Joly, T. Odievre, M. Courbiere, and C. Hantrais, “Automatic detection and characterization of aluminum weld defects: comparison between radiography, radioscopy and human interpretation,” in Proceedings of the Seventh European Conference on Nondestructive Testing (1998), pp. 1179–1186.

Kaneko, S.

X. Zhao, Y. Satoh, H. Takauji, and S. Kaneko, “Robust tracking using particle filter with a hybrid feature,” IEICE Trans. 95, 646–657 (2012).

X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
[CrossRef]

Kazantseva, I. G.

I. G. Kazantseva, I. Lemahieub, G. I. Salova, and R. Denysc, “Statistical detection of defects in radiographic images in nondestructive testing,” Signal Process. 82, 791–801 (2002).
[CrossRef]

Kosanetzky, J. M.

J. M. Kosanetzky and H. Putzbach, “Modern x-ray inspection in the automotive industry,” in Proceedings of the 14th World Conference of NDT (Ashgate Publishing Company, 1996), Vol. 3, pp. 1325–1328.

Kumar, P.

Alaknanda, R. S. Anand, and P. Kumar, “Flaw detection in radiographic weld images using morphological approach,” NDT&E International 39, 29–33 (2006).
[CrossRef]

Lashkiam, V.

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

Lemahieub, I.

I. G. Kazantseva, I. Lemahieub, G. I. Salova, and R. Denysc, “Statistical detection of defects in radiographic images in nondestructive testing,” Signal Process. 82, 791–801 (2002).
[CrossRef]

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]

Liao, T.

G. Wang and T. Liao, “Automatic identification of different types of welding defects in radiographic images,” NDT&E International 35, 519–528 (2002).
[CrossRef]

Liu, J. C.

J. C. Liu and G. Pok, “Texture edge detection by feature encoding and predictive model,” in Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (1999), pp. 1105–1108.

Mery, D.

D. Mery, R. da Silva, L. P. Caloba, and J. M. A. Rebello, “Pattern recognition in the automatic inspection of aluminium castings,” Insight 45, 475–483 (2003).

D. Mery and D. Filbert, “Automated flaw detection in aluminum castings based on the tracking of potential defects in a radioscopic image sequence,” IEEE Trans. Robot. Autom. 18, 890–901 (2002).
[CrossRef]

D. Mery, T. Jaeger, and D. Filbert, “A review of methods for automated recognition of casting defects,” Insight 44, 428–436 (2002).

D. Mery, “Crossing line profile: a new approach to detecting defects in aluminium castings,” in Proceedings of the Scandinavian Conference on Image Analysis (SCIA) (Springer-Verlag, 2003), pp. 725–732.

Ng, H. F.

H. F. Ng, “Automatic thresholding for defect detection,” Pattern Recogn. Lett. 27, 1644–1649 (2006).
[CrossRef]

Odievre, T.

V. Kaftandjian, A. Joly, T. Odievre, M. Courbiere, and C. Hantrais, “Automatic detection and characterization of aluminum weld defects: comparison between radiography, radioscopy and human interpretation,” in Proceedings of the Seventh European Conference on Nondestructive Testing (1998), pp. 1179–1186.

Ozaki, R.

X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
[CrossRef]

Pok, G.

J. C. Liu and G. Pok, “Texture edge detection by feature encoding and predictive model,” in Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (1999), pp. 1105–1108.

Putzbach, H.

J. M. Kosanetzky and H. Putzbach, “Modern x-ray inspection in the automotive industry,” in Proceedings of the 14th World Conference of NDT (Ashgate Publishing Company, 1996), Vol. 3, pp. 1325–1328.

Rebello, J. M. A.

D. Mery, R. da Silva, L. P. Caloba, and J. M. A. Rebello, “Pattern recognition in the automatic inspection of aluminium castings,” Insight 45, 475–483 (2003).

Rebuffel, V.

V. Rebuffel, S. Sood, and B. Blakeley, “Defect detection method in digital radiography for porosity in magnesium castings,” in European Conference on Non-destructive Testing (ECNDT), Berlin, 2006.

Salova, G. I.

I. G. Kazantseva, I. Lemahieub, G. I. Salova, and R. Denysc, “Statistical detection of defects in radiographic images in nondestructive testing,” Signal Process. 82, 791–801 (2002).
[CrossRef]

Satoh, Y.

X. Zhao, Y. Satoh, H. Takauji, and S. Kaneko, “Robust tracking using particle filter with a hybrid feature,” IEICE Trans. 95, 646–657 (2012).

X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
[CrossRef]

Shao, J.

J. Shao, D. Dua, B. Chang, and H. Shi, “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence,” NDT&E International 46, 14–21 (2012).
[CrossRef]

Shi, D. H.

D. H. Shi, T. Gang, S. Y. Yang, and Y. Yuan, “Research on segmentation and distribution features of small defects in precision weldments with complex structure,” NDT&E International 40, 397–404 (2007).
[CrossRef]

Shi, H.

J. Shao, D. Dua, B. Chang, and H. Shi, “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence,” NDT&E International 46, 14–21 (2012).
[CrossRef]

Sood, S.

V. Rebuffel, S. Sood, and B. Blakeley, “Defect detection method in digital radiography for porosity in magnesium castings,” in European Conference on Non-destructive Testing (ECNDT), Berlin, 2006.

Stauffer, C.

C. Stauffer and W. E. L. Grimson, “Learning patterns of activity using realtime tracking,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 747–757 (2000).
[CrossRef]

Takauji, H.

X. Zhao, Y. Satoh, H. Takauji, and S. Kaneko, “Robust tracking using particle filter with a hybrid feature,” IEICE Trans. 95, 646–657 (2012).

X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
[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]

Wang, G.

G. Wang and T. Liao, “Automatic identification of different types of welding defects in radiographic images,” NDT&E International 35, 519–528 (2002).
[CrossRef]

Yang, S. Y.

D. H. Shi, T. Gang, S. Y. Yang, and Y. Yuan, “Research on segmentation and distribution features of small defects in precision weldments with complex structure,” NDT&E International 40, 397–404 (2007).
[CrossRef]

Yuan, Y.

D. H. Shi, T. Gang, S. Y. Yang, and Y. Yuan, “Research on segmentation and distribution features of small defects in precision weldments with complex structure,” NDT&E International 40, 397–404 (2007).
[CrossRef]

Zhao, X.

X. Zhao, Y. Satoh, H. Takauji, and S. Kaneko, “Robust tracking using particle filter with a hybrid feature,” IEICE Trans. 95, 646–657 (2012).

X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
[CrossRef]

IEEE Trans. Ind. Electron. (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]

IEEE Trans. Pattern Anal. Mach. Intell. (1)

C. Stauffer and W. E. L. Grimson, “Learning patterns of activity using realtime tracking,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 747–757 (2000).
[CrossRef]

IEEE Trans. Robot. Autom. (1)

D. Mery and D. Filbert, “Automated flaw detection in aluminum castings based on the tracking of potential defects in a radioscopic image sequence,” IEEE Trans. Robot. Autom. 18, 890–901 (2002).
[CrossRef]

IEICE Trans. (1)

X. Zhao, Y. Satoh, H. Takauji, and S. Kaneko, “Robust tracking using particle filter with a hybrid feature,” IEICE Trans. 95, 646–657 (2012).

Image Vis. Comput. (1)

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

Insight (2)

D. Mery, T. Jaeger, and D. Filbert, “A review of methods for automated recognition of casting defects,” Insight 44, 428–436 (2002).

D. Mery, R. da Silva, L. P. Caloba, and J. M. A. Rebello, “Pattern recognition in the automatic inspection of aluminium castings,” Insight 45, 475–483 (2003).

NDT&E International (4)

Alaknanda, R. S. Anand, and P. Kumar, “Flaw detection in radiographic weld images using morphological approach,” NDT&E International 39, 29–33 (2006).
[CrossRef]

J. Shao, D. Dua, B. Chang, and H. Shi, “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence,” NDT&E International 46, 14–21 (2012).
[CrossRef]

G. Wang and T. Liao, “Automatic identification of different types of welding defects in radiographic images,” NDT&E International 35, 519–528 (2002).
[CrossRef]

D. H. Shi, T. Gang, S. Y. Yang, and Y. Yuan, “Research on segmentation and distribution features of small defects in precision weldments with complex structure,” NDT&E International 40, 397–404 (2007).
[CrossRef]

Pattern Recogn. (1)

X. Zhao, Y. Satoh, H. Takauji, S. Kaneko, K. Iwata, and R. Ozaki, “Object detection based on a robust and accurate statistical multi-point-pair model,” Pattern Recogn. 44, 1296–1311 (2011).
[CrossRef]

Pattern Recogn. Lett. (1)

H. F. Ng, “Automatic thresholding for defect detection,” Pattern Recogn. Lett. 27, 1644–1649 (2006).
[CrossRef]

Signal Process. (1)

I. G. Kazantseva, I. Lemahieub, G. I. Salova, and R. Denysc, “Statistical detection of defects in radiographic images in nondestructive testing,” Signal Process. 82, 791–801 (2002).
[CrossRef]

Other (6)

D. Mery, “Crossing line profile: a new approach to detecting defects in aluminium castings,” in Proceedings of the Scandinavian Conference on Image Analysis (SCIA) (Springer-Verlag, 2003), pp. 725–732.

Balu toolbox MATLAB, http://dmery.ing.puc.cl/index.php/balu/ .

J. C. Liu and G. Pok, “Texture edge detection by feature encoding and predictive model,” in Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (1999), pp. 1105–1108.

J. M. Kosanetzky and H. Putzbach, “Modern x-ray inspection in the automotive industry,” in Proceedings of the 14th World Conference of NDT (Ashgate Publishing Company, 1996), Vol. 3, pp. 1325–1328.

V. Kaftandjian, A. Joly, T. Odievre, M. Courbiere, and C. Hantrais, “Automatic detection and characterization of aluminum weld defects: comparison between radiography, radioscopy and human interpretation,” in Proceedings of the Seventh European Conference on Nondestructive Testing (1998), pp. 1179–1186.

V. Rebuffel, S. Sood, and B. Blakeley, “Defect detection method in digital radiography for porosity in magnesium castings,” in European Conference on Non-destructive Testing (ECNDT), Berlin, 2006.

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.

X-ray inspection system in castings.

Fig. 2.
Fig. 2.

Flowchart of the GAP technology.

Fig. 3.
Fig. 3.

GAP feature.

Fig. 4.
Fig. 4.

Real distributions of one multipixel pair.

Fig. 5.
Fig. 5.

Probability maps. (a) shows the original input image, (b) shows the detected result, (c) shows the probability distribution of ξ+, and (d) shows the probability distribution of ξ.

Fig. 6.
Fig. 6.

Schematic block diagram for the proposed method.

Fig. 7.
Fig. 7.

Probability density function of I(P)I(Q+). I¯(P)I¯(Q+)=22σ and pixels P, Q+ are affected by noise ZN(0,σ2).

Fig. 8.
Fig. 8.

Defect detection with varying WG=3, 10, 20, and 30, giving WP=0.9. (a) shows the detection results of the crack defect image, (b), (c) show the detection results of blow hole defect images, and (d), (e) show the detection results of shrinkage porosity defect images.

Fig. 9.
Fig. 9.

Defect detection with varying WP=0.2, 0.4, 0.6, and 0.9, giving WG=10. (a) shows the detection results of the crack defect image, (b), (c) show the detection results of blow hole defect images, and (d), (e) show the detection results of shrinkage porosity defect images.

Fig. 10.
Fig. 10.

Defect detection results using the CLP method. The original images of (a)–(e) are shown in the first column of Fig. 8, respectively.

Fig. 11.
Fig. 11.

Experimental results with additive Gaussian noise. (a) Test images, (b) results of the proposed method (without any morphological processing), and (c) results of the MoG-based method.

Fig. 12.
Fig. 12.

Experimental results with the additive uniform noise. (a) Test images, (b) results of the proposed method (without any morphological processing), and (c) results of the MoG-based method.

Fig. 13.
Fig. 13.

Experimental results with nonuniform illumination variations. (a) Test images, (b) results of the proposed method (without any morphological processing), and (c) results of the MoG-based method.

Tables (2)

Tables Icon

Table 1. Detection Results on 60 Test Images under Different Situations (the Correct Number/the Total Number)

Tables Icon

Table 2. Detection Results on 60 Test Images under Different Illumination Variations [the Correct Number/(the Total Number ×2)]

Equations (10)

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

X+(P):={Q|Pr+(P,Q)WP},
X(P):={Q|Pr(P,Q)WP},
Pr+(P,Q):=#{t|It(P)It(Q)WG,t=1,,T}T,
Pr(P,Q):=#{t|It(P)It(Q)WG,t=1,,T}T,
ref+(P):={firstN2elements ofX+(P)respect to<.},
ref(P):={firstN2elements ofX(P)respect to<.},
Mos(P,Qn):={1Qnref+(P),1Qnref(P).
Ins(P,Qn):={1J(P)J(Qn),1J(P)<J(Qn).
ξ+(P)=1#{Qn|Mos(P,Qn)=Ins(P,Qn)=1}#{Qn|Qnref+(P)},
ξ(P)=1#{Qn|Mos(P,Qn)=Ins(P,Qn)=1}#{Qn|Qnref(P)}.

Metrics