Advertisement

Bayesian Pressure Snake for Weld Defect Detection

  • Aicha Baya Goumeidane
  • Mohammed Khamadja
  • Nafaa Naceredine
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5807)

Abstract

Image Segmentation plays a key role in automatic weld defect detection and classification in radiographic testing. Among the segmentation methods, boundary extraction based on deformable models is a powerful technique to describe the shape and then deduce after the analysis stage, the type of the defect under investigation. This paper describes a method for automatic estimation of the contours of weld defect in radiographic images. The method uses a statistical formulation of contour estimation by exploiting statistical pressure snake based on non-parametric modeling of the image. Here the edge energy is replaced by a region energy which is a function of statistical characteristics of area of interest.

Keywords

Snake images segmentation pdf estimation Radiographic images Non Destructive Inspection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lawrence, E.B.: Non-destructive Testing Handbook. In: Radiography and Radiation Testing, vol. 3. American Society for Non-destructive Testing (1985)Google Scholar
  2. 2.
    Hayes, C.: The ABC’s of Non-destructive Weld Examination. Welding Journal 76(5), 46–51 (1997)MathSciNetGoogle Scholar
  3. 3.
    De Carvallo, A., et al.: Evaluation of the relevant features of Welding Defects in Radiographic Inspection. Materials Research 6(3), 427–432 (2003)CrossRefGoogle Scholar
  4. 4.
    Schwartz, C.: Automatic Evaluation of Welded Joints using Image Processing. In: Conference Proceeding of American Institute of Physics, vol. 657(1), pp. 689–694 (2003)Google Scholar
  5. 5.
    Liao, T.W., Ni, J.: An Automated Radiographic NDT System for Weld Inspection. Part I. Weld Extraction. NDT&E Int. 29(3), 157–162 (1996)Google Scholar
  6. 6.
    González, R., Woods, R.E.: Digital Image Processing. Addison Wesley, USA (1992)Google Scholar
  7. 7.
    Newman, T.S., Jain, A.K.: A survey of automated visual inspection. Computer Vision and Image Understanding 61(2), 231–262 (1995)CrossRefGoogle Scholar
  8. 8.
    Canny, J.: A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 8, 769–798 (1986)Google Scholar
  9. 9.
    Deriche, R.: Using Canny’s Criteria to Derive a Recursively Implemented Optimal edge Detector. International Journal of Computer Vision 1, 167–187 (1987)CrossRefGoogle Scholar
  10. 10.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active Contour Models. Int’l J. Computer Vision, 321–331 (1988)Google Scholar
  11. 11.
    Xu, C., Prince, J.: Snakes, shapes, and gradient vector flow. IEEE Transactions on Images Processing 7(3), 359–369 (1998)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Goumeidane, A.B., Khamadja, M., Nacereddine, N., Mekhalfa, F.: Parametric Active Contour for Weld Defects Boundary Extraction in Radiographic testing. In: Proc. of the 8th QCAV SPIE, vol. 63560R (2007)Google Scholar
  13. 13.
    Jardim, S.M.G.V.B., Figuerido, M.A.T.: Segmentation of Fetal Ultrasound Images. Ultrasound in Med. & Biol. 31(2), 243–250 (2005)CrossRefGoogle Scholar
  14. 14.
    Nacereddine, N., Hamami, L., Ziou, D.: Probabilistic Deformable Model For Weld Defect Contour Estimation in Radiography. Machine Graphics & Vision 3(4), 547–556 (2006)Google Scholar
  15. 15.
    Chesnaud, C., Réfrégier, P., Boulet, V.: Statistical Region Snake-Based Segmentation Adapted to Different Physical Noise Models. IEEE trans. on PAMI 21(11), 1145–1157 (1999)CrossRefGoogle Scholar
  16. 16.
    Cohen, L.D., Cohen, I.: Finite-Element Methods for Active Contour Models and Balloons for 2D and 3D Images. IEEE Trans. Pattern Analysis and Machine Intelligence 15(11), 1131–1147 (1993)CrossRefGoogle Scholar
  17. 17.
    Ivins, J., Porrill, J.: Active region models for segmenting medical images. In: Proceedings of the IEEE Internation Conference on Image Processing (1994)Google Scholar
  18. 18.
    Abd-Almageed, W., Smith, C.E.: Mixture models for dynamic statistical pressure snakes. In: IEEE International Conference on Pattern Recognition, Quebec City, Canada (2002)Google Scholar
  19. 19.
    Abd-Almageed, W., Ramadan, S., Smith, C.E.: Kernel Snakes: Non-parametric Active Contour Models. In: IEEE international conference on systems, man and cybernetics, Washington (2003)Google Scholar
  20. 20.
    Parzen, E.: On the estimation of a probability density function and the mode. Ann. Math. Statistics 33, 1065–1076 (1962)MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Duda, R., Hart, P., Stork, D.: Pattern Classification. Wiley, Chichester (2000)zbMATHGoogle Scholar
  22. 22.
    Härdle, W.: Smoothing Techniques, With Implementations in S. Springer, New York (1991)CrossRefzbMATHGoogle Scholar
  23. 23.
    Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Monographs on Statistics and Applied Probability, vol. 26. Chapman and Hall, London (1986)CrossRefzbMATHGoogle Scholar
  24. 24.
    Goumeidane, A.B., Khamadja, M., Nacereddine, N., Mekhalfa, F.: Statistical Deformable Model Based Weld Defect Contour Estimation in Radiographic Inspection. In: Proceedings of the International Conference on Computational Intelligence for Modelling, Control and Automation (CIMCA 2008), pp. 420–425. IEEE Computer Society, Los Alamitos (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Aicha Baya Goumeidane
    • 1
  • Mohammed Khamadja
    • 2
  • Nafaa Naceredine
    • 1
  1. 1.Welding and NDT Research CentreAlgiersAlgeria
  2. 2.SP_Lab, Electronics DepartmentMentouri UniversityConstantineAlgeria

Personalised recommendations