Higher-Order Statistics for Automatic Weld Defect Detection


Image processing and image analysis are the main aspects for obtaining information from digital image owing to the fact that this techniques give the desired details in most of the applications generally and Non-Destructive testing specifically. This paper presents a proposed method for the automatic detection of weld defects in radiographic images. Firstly, the radiographic images were enhanced using adaptive histogram equalization and are filtered using mean and wiener filters. Secondly, the welding area is selected from the radiography image. Thirdly, the Cepstral features are extracted from the Higher-Order Spectra (Bispectrum and Trispectrum). Finally, neural networks are used for feature matching. The proposed method is tested using 100 radiographic images in the presence of noise and image blurring. Results show that in spite of time consumption, the proposed method yields best results for the automatic detection of weld defects in radiography images when the features were extracted from the Trispectrum of the image.

Share and Cite:

S. Saber and G. Selim, "Higher-Order Statistics for Automatic Weld Defect Detection," Journal of Software Engineering and Applications, Vol. 6 No. 5, 2013, pp. 251-258. doi: 10.4236/jsea.2013.65031.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] J. T. Karlsen, G. Farrants, T. Torgrimsen and A. Reith, “Chemical Composition and Morphology of Welding Fume Particles and Grinding Dusts,” American Industrial Hygiene Association Journal, Vol. 53, No. 5, 1992, pp. 290-297. doi:10.1080/15298669291359681
[2] C. Hayes, “The ABC’s of Nondestructive Weld Examination,” Welding Journal, Vol. 76, No. 5, 1998, pp. 46-51.
[3] W. K. F. Thai, “Development of a Computed Radiography-Based Weld Defect Detection and Classification System,” M.Sc. Thesis, University of Sains, Penang, 2008.
[4] H. R. Sim, M. B. Rabello, R. Camargo and M. S. Pereira, “Digital Radiography for the Inspection of Weld Seams of Pipelines—Better Sensitivity,” Welding International, Vol. 24, No. 4, 2010, pp. 249-257. doi:10.1080/09507110902844022
[5] G. Wang and T. W. Liao, “Automatic Identification of Different Types of Welding Defects in Radiographic Images,” Nondestructive Testing and Evaluation: An Intertional Journal, Vol. 35, No. 8, 2002, pp. 519-528.
[6] H. I. Shafeek, E. S. Gadelmawla, A. A. Abdel-Shafy and I. M. Elewa, “Automatic Inspection of Gas Pipeline Welding Defects Using an Expert Vision System,” Nondestructive Testing and Evaluation: An International Journal, Vol. 37, No. 4, 2004, pp. 301-307.
[7] T. Saravanan, S. Bagavathiappan, J. Philip, T. Jayakumar and B. Raj, “Segmentation of Defects from Radiographic Images by the Histogram Concavity Threshold Method,” Insight, Vol. 49, No. 10, 2007, pp. 578-584. doi:10.1784/insi.2007.49.10.578
[8] S. S. L. Eong, Z. Samad, M. M. Ratnam and M. A. Khalid, “Weld Extraction from Digitized Radiographs Using Graphical Analysis of Weld Intensity Profiles,” Journal of Technology, Vol. 45, No. D, 2006, pp. 167180.
[9] J. Zapata, R. Vilar and R. Ruiz, “An Adaptive-NetworkBased Fuzzy Inference System for Classification of Welding Defects,” Nondestructive Testing and Evaluation: An International Journal, Vol. 43, No. 3, 2010, pp. 191-199.
[10] R. Vilar, J. Zapat and R. Ruiz, “Classification of Welding Defects in Radiographic Images Using an ANN with Modified Performance Function,” Springer Berlin, Heidelberg, 2009, pp. 284-293.
[11] J. Zapata, R. Vilar and R. Ruiz, “Automatic Inspection System of Welding Radiographic Images Based on ANN Under a Regularisation Process,” Journal of Nondestructive Evaluation, Vol. 31, No. 1, 2012, pp. 34-45
[12] H. Kasban, O. Zahran, H. Arafa, M. El-Kordy, S. M. S. Elaraby and F. E. A. El-Samie, “Welding Defect Detection from Radiographic Image Using Cepstral Approach,” Nondestructive Testing and Evaluation: An International Journal, Vol. 44, No. 2, 2011, pp. 226-231.
[13] H. Kasban, “Applying Advanced Digital Signal Processing Techniques in Industrial Radioisotopes Applications,” Ph.D. Thesis, Faculty of Electronic Engineering, Menofia University, Shibin Al Kawm, 2012.
[14] D. Coltuc, P. Bolon and J. M. Chassery, “Exact Histogram Specification,” IEEE Transactions on Image Processing, Vol. 15, No. 5, 2006, pp.1143-1152. doi:10.1109/TIP.2005.864170
[15] I. Frosio and N. A. Borghese, “Statistical Based Impulsive Noise Removal in Digital Radiography,” IEEE Transactions on Medical Imaging, Vol. 28, No. 1, 2009, pp. 3-16. doi:10.1109/TMI.2008.922698
[16] T. W. Liao, D. M. Li and Y. M. Li, “Extraction of Welds from Radiographic Images Using Fuzzy Classifiers,” Informatics and Computer Science: An International Journal, Vol. 126, No. 1-4, 2000, pp. 21-42.
[17] M. A. Carrasco and D. Mery, “Segmentation of Welding Defects Using a Robust Algorithm,” Materials Evaluation, Vol. 62, No. 11, 2004, pp. 1142-1147.
[18] O. Zahran, H. Kasban, F. E. A. El-Samie and M. ElKordy, “Power Density Spectrum for the Identification of Residence Time Distribution Signals,” Applied Radiation and Isotopes, Vol. 70, No. 11, 2012, pp. 2638-2645. doi:10.1016/j.apradiso.2012.05.006
[19] W. B. Collis, P. R. White and J. K. Hammond, “HigherOrder Spectra: The Bispectrum and Trispectrum,” Mechanical Systems and Signal Processing, Vol. 12, No. 3, 1998, pp. 375-394. doi:10.1006/mssp.1997.0145
[20] M. G. Kang, K.-T. Lay and A. K. Katsaggelos, “Phase Estimation Using the Bispectrum and Its Application to Image Restoration,” Optical Engineering, Vol. 30, No. 7, 1991, pp. 976-985. doi:10.1117/12.55893
[21] J. F. McAloon, “Comparison of Higher Order Moment Spectrum Estimation Techniques,” M.Sc. Thesis, Electrical Engineering, University of South Florida, Tampa, 1983.
[22] N. Nafaa, D. Redouane and B. Amar, “Weld Defect Extraction and Classification in Radiographic Testing Based Artificial Neural Networks,” 15th WCNDT, Roma, 2000. http://www.ndt.net/ article/wcndt00/papers/ idn575/idn575.htm
[23] E. S. Amin, “Application of Artificial Neural Networks to Evaluate Weld Defects of Nuclear Components,” Journal of Nuclear and Radiation Physics, Vol. 3, No. 2, 2008, pp. 83-92.
[24] C. M. Bishop, “Neural Networks for Pattern Recognition”, Clarendon Press, Oxford, 1995.
[25] J. Starck, F. Murtagh and A. Bijaoui, “Image Processing and Data Analysis: The Multiscale Approach,” Cambridge University Press, Cambridge, 1998. doi:10.1017/CBO9780511564352
[26] P. Gravel, G. Beaudoin and J. A. De Guise, “A Method for Modeling Noise in Medical Images,” IEEE Transactions on Medical Imaging, Vol. 23, No. 10, 2004, pp. 1221-1232. doi:10.1109/TMI. 2004.832656
[27] J. Harikiran, B. Saichandana and B. Divakar, “Impulse Noise Removal in Digital Images,” International Journal of Computer Applications, Vol. 10, No. 8, 2010, pp. 39-42.
[28] P. R. Deshmukh and M. V. Sarode, “Reduction of Speckle Noise and Image Enhancement of Images Using Filtering Technique,” International Journal of Advancements in Technology, Vol. 2, No. 1, 2011, pp. 30-38.
[29] R. J. Ferrari and R. Winsor, “Digital Radiographic Image Denoising via Wavelet-Based Hidden Markov Model Estimation,” Journal of Digital Imaging, Vol. 18, No. 2, 2005, pp. 154-167. doi:10.1007/s10278-004-1908-3

Copyright © 2022 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.