Journal of Nuclear Science, Engineering and Technology (JONSAT)
In cooperation with the Iranian Nuclear Society

Quality Improvement of Defects Region in Weld Radiography Image by the Wavelet Method Based on Adaptive Thresholding

Document Type : Research Paper

Authors

A Movafeghi
E Yahaghi
N Mohammadzadeh
B Rokrok
https://doi.org/10.24200/nst.2019.736
Abstract
In this paper, adaptive thresholding at the wavelet transform is utilized for improving the industrial radiography images. The quality of radiographic images is a very effective parameter in the defect determining by the experts. Therefore, the defect detection capabilities can be improved by the image processing algorithms. In this research, two-stage adaptive thresholding method has been used to improve the contrast of the inspected areas. The radiographic image is decomposed to several sub-bands using the wavelet function and the obtained coefficients are corrected by the threshold function. Then, the inverse wavelet transform is applied for obtaining the corrected image. Unlike the usual methods, in the threshold function of this method, the coefficient of under the threshold level is not zero and weakened by the multi-polyminal function. The advantages of this method are the continuity and derivability at threshold level. The proposed algorithm is implemented to the several radiographs of standard welded objects with known defects. The results have been evaluated by industrial radiography experts and show that the defect regions are clearer in reconstructed images than the original radiograph according to the operator perception analysis. Mean while, the dimensions and style of defects can be evaluated more precisely by this method.

Highlights

[1] H.I. Shafeek, E.S. Gadelmava, A.A. Bdel-Shafy, I.M. Elewa, Assessment of welding defects for gas pipeline radiographs using computer vision, NDT & E International, 37 (2004) 291-299.

 

[2] T.Y. Lim, M.M. Ratnam, M.A. Khalid, Automatic classification of weld defects using simulated data and an MLP neural network, Insight, 49 (March 2007) 154-159.

 

[3] R.R. Da Silva, L.P. Galoba, M.H.S. Siqueira, J.M.A. Rebello, Pattern recognition of weld defects detected by radiographic tests, NDT & E International, 37 (2004) 461-470.

 

[4] A. Karimian, S. Yazdani, A. Movafeghi, Corrosion Detection Improvement of Oil and Gas Pipelines with Industrial Radiography Method by using Image Processing, International Conference on Recent Developments and Applications of Nuclear Technologies, Bialowieza, Poland, (Sep 2008) 14-17.

 

[5] M.A. Carrasco, D. Mery, Segmentation of welding defects using a robust algorithm, Materials Evaluation, (2004) 1142-1147.

 

[6] N. Nacereddine, L. Hamami, M. Tridi, N. Oucief, Histogram-based and locally adaptive  thresholding techniques for weld defect  extraction in digital  radiography, 35th  International  Conference  and  NDT  Technique Exposition, Defectoscopy, Znojmo, Czech  Republic, (Nov 2005) 8-10.

 

[7] M.K. Felisberto, H.S. Lopes, T.M. Centeno, L.V.R. Arruda, An object detection and recognition system for weld bead extraction from digital radiographs, Coputer Vision and Image Understanding, (2006) 238-249.

 

[8] D. Mery, M.A. Berti, Automatic detection of welding defects using texture features, Insight, 45 (October 2003) 676-680.

 

[9] R.C. Gonzalez, R.E. Woods, S.I. Eddins, Digital image processing using matlab, 1st edition, Prentice hall, (2004) 57-119.

 

 

[10] B.J. Yoon, P.P. Vaidyanathan, Wavelet-based denoising by customized thresholding, in Proc. ICASSP’04, 2 (May 2004) 925-928.

 

[11] Z.D. Zhao, Wavelet shrinkage denoising by generalized thresholding function, in Proc. Fourth Int. Conf. on Machine Learning and Cybernetic, 9 (Aug 2005) 5501-5506.

 

[12]      C. Jacobsen, U. Zscherpel, Crack detection in digitized radiographs with neural networks, Proceedings of the Seventh European conference on Non-Destructive Testing, 3, 8 (1998) 26-29.

 

[13]      M. Torabian, A. Karimian, M. Yazdchi, Optimization of Interpretation of Industrial Radiographs for Defect Detection in Oil and Gas Pipeline Welds, The 2nd International Conference on Technical Inspection and NDT, Iran, (2008).

 

[14] U. Lotric, Wavelet based denoising integrated into multilayered perceptron, Neurocomputing, 62 (Dec. 2004) 179-196.

 

[15] X.P. Zhang, Thresholding neural network for adaptive noise reduction, IEEE Tran. IEEE, 12, 3 (2001).

 

[16] Microtek, Operation manual of Scanmaker-1000 scanner, Microtek Co, (2005).

 

[17]      EN 14096-1, Non-destructive testing-Qualification of radiographic film digitization systems-part 1: Definitions, qualitative measurements of image quality parameters, standard reference film and qualitative control, European Norm, (2004).

 

[18]      EN 14096-2, Non-destructive testing- Qualification of radiographic film digitization systems-part 2: Minimum requirement, European Norm, (2004).

 

[19]      AEOI, Basic Radiation Safety Standards, Iranian Nuclear Regulatory Authority, Atomic Energy Organization of Iran, in Persian, (2001).

 

[20]      ISIRI-7751, Protection Against Ionization Radiation and the Safety of the Radiation Sources, Institute of Standards and Industrial Research of Iran, in Persian, (2004).

 

[21] D.L. Donoho, De-noising by soft-thresholding, IEEE Trans. Inform. Theory, 41, 3 (May 1995) 613-627.

 

[22] M. Nasri, H. Nezamabadipour, S. Saryazdi, An Adaptive denoising Method in Wavelate Domain, Iranian Journal of Electrical and Computer Engineering, 6, 1 in Persian, (2008) 15-24.

 

[23] Z. Al-Ameena, Gh. Sulonga, A. Rehmanb, M. Al-Rodhaanc, T. Sabad, A. Al-Dhel, Phase-preserving approach in denoising computed tomography medical images, Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, (2014) http://dx.doi.org/10.1080 /21681163.2014.955615.

Keywords

Radiography
Weld Defects
Wavelet Method
Adaptive Thresholding
[1] H.I. Shafeek, E.S. Gadelmava, A.A. Bdel-Shafy, I.M. Elewa, Assessment of welding defects for gas pipeline radiographs using computer vision, NDT & E International, 37 (2004) 291-299.
 
[2] T.Y. Lim, M.M. Ratnam, M.A. Khalid, Automatic classification of weld defects using simulated data and an MLP neural network, Insight, 49 (March 2007) 154-159.
 
[3] R.R. Da Silva, L.P. Galoba, M.H.S. Siqueira, J.M.A. Rebello, Pattern recognition of weld defects detected by radiographic tests, NDT & E International, 37 (2004) 461-470.
 
[4] A. Karimian, S. Yazdani, A. Movafeghi, Corrosion Detection Improvement of Oil and Gas Pipelines with Industrial Radiography Method by using Image Processing, International Conference on Recent Developments and Applications of Nuclear Technologies, Bialowieza, Poland, (Sep 2008) 14-17.
 
[5] M.A. Carrasco, D. Mery, Segmentation of welding defects using a robust algorithm, Materials Evaluation, (2004) 1142-1147.
 
[6] N. Nacereddine, L. Hamami, M. Tridi, N. Oucief, Histogram-based and locally adaptive  thresholding techniques for weld defect  extraction in digital  radiography, 35th  International  Conference  and  NDT  Technique Exposition, Defectoscopy, Znojmo, Czech  Republic, (Nov 2005) 8-10.
 
[7] M.K. Felisberto, H.S. Lopes, T.M. Centeno, L.V.R. Arruda, An object detection and recognition system for weld bead extraction from digital radiographs, Coputer Vision and Image Understanding, (2006) 238-249.
 
[8] D. Mery, M.A. Berti, Automatic detection of welding defects using texture features, Insight, 45 (October 2003) 676-680.
 
[9] R.C. Gonzalez, R.E. Woods, S.I. Eddins, Digital image processing using matlab, 1st edition, Prentice hall, (2004) 57-119.
 
 
[10] B.J. Yoon, P.P. Vaidyanathan, Wavelet-based denoising by customized thresholding, in Proc. ICASSP’04, 2 (May 2004) 925-928.
 
[11] Z.D. Zhao, Wavelet shrinkage denoising by generalized thresholding function, in Proc. Fourth Int. Conf. on Machine Learning and Cybernetic, 9 (Aug 2005) 5501-5506.
 
[12]      C. Jacobsen, U. Zscherpel, Crack detection in digitized radiographs with neural networks, Proceedings of the Seventh European conference on Non-Destructive Testing, 3, 8 (1998) 26-29.
 
[13]      M. Torabian, A. Karimian, M. Yazdchi, Optimization of Interpretation of Industrial Radiographs for Defect Detection in Oil and Gas Pipeline Welds, The 2nd International Conference on Technical Inspection and NDT, Iran, (2008).
 
[14] U. Lotric, Wavelet based denoising integrated into multilayered perceptron, Neurocomputing, 62 (Dec. 2004) 179-196.
 
[15] X.P. Zhang, Thresholding neural network for adaptive noise reduction, IEEE Tran. IEEE, 12, 3 (2001).
 
[16] Microtek, Operation manual of Scanmaker-1000 scanner, Microtek Co, (2005).
 
[17]      EN 14096-1, Non-destructive testing-Qualification of radiographic film digitization systems-part 1: Definitions, qualitative measurements of image quality parameters, standard reference film and qualitative control, European Norm, (2004).
 
[18]      EN 14096-2, Non-destructive testing- Qualification of radiographic film digitization systems-part 2: Minimum requirement, European Norm, (2004).
 
[19]      AEOI, Basic Radiation Safety Standards, Iranian Nuclear Regulatory Authority, Atomic Energy Organization of Iran, in Persian, (2001).
 
[20]      ISIRI-7751, Protection Against Ionization Radiation and the Safety of the Radiation Sources, Institute of Standards and Industrial Research of Iran, in Persian, (2004).
 
[21] D.L. Donoho, De-noising by soft-thresholding, IEEE Trans. Inform. Theory, 41, 3 (May 1995) 613-627.
 
[22] M. Nasri, H. Nezamabadipour, S. Saryazdi, An Adaptive denoising Method in Wavelate Domain, Iranian Journal of Electrical and Computer Engineering, 6, 1 in Persian, (2008) 15-24.
 
[23] Z. Al-Ameena, Gh. Sulonga, A. Rehmanb, M. Al-Rodhaanc, T. Sabad, A. Al-Dhel, Phase-preserving approach in denoising computed tomography medical images, Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, (2014) http://dx.doi.org/10.1080 /21681163.2014.955615.

Home