Detecting Defects in Digital Radiographic Images

W. Al-Hameed, P. D. Picton

Abstract


It has been noticed that digital x-ray images of faulty welds in pipes tend to be darker than the rest of the image. Rather than simple thresholding, in this work a light pixel is converted to white if there are light pixels within its immediate neighborhood. The effect is that the flaw appears black and the background appears white, this enabling the flaw to be easily detected. However, this method will have the effect of eroding any rough edges on the flaw i.e. black pixels that stick out from the main body of the flaw. This method works well for large flaws, while not with fine cracks.

Keywords


Defect Detection;Flaws in the weld; NDT; X-ray image;

Full Text:

PDF

References


Hayward, P. & Zealand, H. N. & Currie, D.," Radiography of Welds Using Selenium 75", 12th A-PCNDT – Asia-Pacific Conference on NDT, 5th – 10th Nov, Auckland, New Zealand, 2006.

Nacereddine, N. &Zelmat, M. &Belaïfa , S.S. &Tridi, M.," Weld defect detection in industrial radiography based digital image processing", Proc. 3rd International Conference: Sciences of Electronic, Technologies of Information and Telecommunications, Tunisia, 27-31, March, 2005.

Silva, R. &Mery, D.," State-of-the-art of weld seam inspection using X ray testing: Part I – image processing", Materials Evaluation 65 (6), pp. 643–647, 2007.

Silva, R. &Mery, D.," State-of-the-art of weld seam inspection using X-ray testing: Part II - Pattern Recognition”, Materials Evaluation, 65(9) .P. 833–838, 2007.X-ray image;

Xiaomeng, W.," Detection of Weld Line Defect for Oil-gas Pipeline Based on X-rays Image Processing. Nanchang", P. R. China, May 22-24.P. 273-275, 2009.

Al-Hameed, W., Picton, P. & Al-Mayali, Y.," Context-Based Image Segmentation of Radiography", International Journal of Engineering Research and Development, 10(1), pp. 27-31, 2014

Mery, D.," Automated Detection of Welding Defects without Segmentation", Pontificia Universidad Catolica de Chile, 2011.

Wang, Y., Sun, Y., Lv, P., & Wang, H.," Detection of line weld defects based on multiple thresholds and support vector machine", NDT & E International, 41(7), 517-524, 2008.

Yin, Y & Tian, G.Y.," Feature Extraction and Optimization for X-ray Weld Image Classification" , 17th World Conference on Nondestructive Testing, 25-28 Oct 2008, Shanghai, China.

Redounane, N.R., " Weld Defect Extraction and Classification in Radiographic Testing Based Artificial Neural Networks", 15th World Conference on Non-Destructive Testing, Rome, 15-21 Octobe,2000.

Wang, G., & Liao, T. W.," Automatic identification of different types of welding defects in radiographic images", Ndt & E International, 35(8), pp.519-528, 2002.

Shao, J., Shi, H., Du, D., Wang, L. and Cao, H. ," Automatic Weld Defect Detection in Real-time X-ray Images Based on Support Vector Machine", 2011 4th international congress on image and signal processing, 1842-1846, 2011

Hassan, J., Awan, A. M & Jalil, A.," Welding Defect Detection and Classification Using Geometric Features", Proceedings of the 10th International Conference on Frontiers of Information Technology, December 17-19, 2012, Islamabad, Pakistan, pp. 139-144, 2012.

Saber, S., & Selim, G. I.," Higher-Order Statistics for Automatic Weld Defect Detection", Journal of Software Engineering & Applications, 6(5), 2013.

Gonzales, R & Woods, R.," Digital Image Processing", By Addison-Wesly publishing company. Inc. USA, 1992.

Weska, J.," A Survey of threshold selection techniques " Computer vision graphics and image processing , pp. 255-265, 1978.

Mery, D.," Database of Group Radiology and Image Analysis", (GRIMA) (Federal Institute for Materials Research and Testing) , 2000 [Online] Available from: www : http://dmery.ing.puc.cl.)


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ISSN: 2180-1843

eISSN: 2289-8131