A Method for Segmentation Radiographic Images with Case Study on Welding Defects

  • Alireza AzariMoghaddam
  • Lalitha Rangarajan
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 222)


Segmentation is one of the most difficult tasks in image processing, particularly in the case of noisy or low contrast images such as radiographic images of welds. In the present study we have segmented defects in radiographic images of weld. The method applied for detecting and discriminating discontinuities in the radiographic weld images. Two Dimensional Left Median Filter (2D-LMF) has been used for enhancing the images. We compared the performance of this method with Mean Shift. Results exhibited the applied method was more effective than Mean Shift in noisy and low contrasted radiographic images of weld.


Segmentation Radiographic Image Weld defect Mean shift 


  1. 1.
    Vijay RR, Anand RS (2010) Comparison of different segmentation techniques in detection of flaws in weldments. IEEE 2:673–677Google Scholar
  2. 2.
    Ioannis V, Dimitrios K (2010) Multiclass defect detection and classification in weld radiographic images using geometric and texture features. Expert Syst Appl 37(12):7606–7614CrossRefGoogle Scholar
  3. 3.
    Faiza M, Naraa N, Archa BG (2007) Unsupervised algorithm for radiographic image segmentation based on the gaussian mixture model. The international conference on computer as a tool, Warsaw, pp 289–293Google Scholar
  4. 4.
    Qin AA, David AC (2010) Multivariate image segmentation using semantic region growing with adaptive edge penalty. IEEE Trans Image Proc 19(8):2157–2170CrossRefGoogle Scholar
  5. 5.
    Damin L, Warren TL (1996) Applications of fuzzy K-NN in weld recognition and tool failure monitoring. IEEE 222–226Google Scholar
  6. 6.
    Gang W, Liao WT (2002) Automatic identification of different types of welding defects in radiographic images. NDT and E International 35:519–528Google Scholar
  7. 7.
    Miguel C, Domingo M (2004) Segmentation of welding defects using a robust algorithm. Mater Eval 62:1142–1147Google Scholar
  8. 8.
    Nacereddine N, Zelmat M, Belarfa SS, Tridi M (2005) Weld defect detection in industrial radiography based digital image processing world Academy of science, engineering and technology, PWASET 2:145–148Google Scholar
  9. 9.
    Gao W, Tang N, Mu X (2007) A novel algorithm for detecting air holes in steel pipe welding based on hopfield neural network, eighth acis international conference on software engineering, artificial intelligence, networking, and parallel/distributed computing, Las Vegas, pp 79–83Google Scholar
  10. 10.
    Amin ES (2008) Application of artificial neural networks to evaluate weld defects of nuclear components. J Nucl Radiat Phys 3(2):83–92Google Scholar
  11. 11.
    Abdelhak M, Fakhita R (2009) Fast segmentation method for defects detection in radiographic images of welds. IEEE 857–860Google Scholar
  12. 12.
    Juna Z, Rafael V, Ramon R (2010) An adaptive-network-based fuzzy inference system for classification of welding defects. NDT E Int 43(3):191–199CrossRefGoogle Scholar
  13. 13.
    Romeu RS, Marcio HSS, Ivan CS, Antonio AC, Joao MAR (2002) Contribution to the development of a radiographic inspection automated system. J Nondestr Test 7(12):1–8Google Scholar
  14. 14.
    Elineudo PM, Romeu RS, Antonio AC, Marcio HSS, Joao MAR (2003) Welding defecets pattern recognition. In: TOFD signals using linear classifier implemented by neural networks, The 3th Pan-American conference for nondestructive testing RioGoogle Scholar
  15. 15.
    Alireza AM, Lalitha R (2011) Enhancing radiographic images using two dimensional left median filter, Third national conference on computer vision, pattern recognition, image processing and graphics (NCVPRIPG2011) Hubli, pp 204–206Google Scholar
  16. 16.
    Alireza AM, Lalitha R (2012) A novel algorithm for de-noising radiographic images. Int J Image Graph Signal Proc 4(6):22–28CrossRefGoogle Scholar
  17. 17.
    Keinosuke F, Larry DH (1975) The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans Inf Theory 21(1):32–40MATHCrossRefGoogle Scholar
  18. 18.
    Amod PR, Ravindran VR (2009) Comparison of different ANN techniques for automatic defect detection in X-ray images, international conference of emerging trends in electronic and photonic devices and systems(ELECTRO) Varanasi, pp 193–197Google Scholar
  19. 19.
    Ashraf A, Hassan M, Ashour M, El Mashade M (2009) Image denoising based on spatial filters an analytical study. IEEE 245–250Google Scholar
  20. 20.
    Alireza AM, Lalitha R (2011) A method for detection welding defects in radiographic images. Int J Mach Intell, 3:307–309Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  1. 1.Department of Study in Computer ScienceUniversity of MysoreMysoreIndia

Personalised recommendations