Quantitative Analysis of Weld Defect Images in Industrial Radiography Based Invariant Attributes

Authors: N. Nacereddine, M. Tridi, S. S. Belaïfa, M. Zelmat

Abstract:

For the characterization of the weld defect region in the radiographic image, looking for features which are invariant regarding the geometrical transformations (rotation, translation and scaling) proves to be necessary because the same defect can be seen from several angles according to the orientation and the distance from the welded framework to the radiation source. Thus, panoply of geometrical attributes satisfying the above conditions is proposed and which result from the calculation of the geometrical parameters (surface, perimeter, etc.) on the one hand and the calculation of the different order moments, on the other hand. Because the large range in values of the raw features and taking into account other considerations imposed by some classifiers, the scaling of these values to lie between 0 and 1 is indispensable. The principal component analysis technique is used in order to reduce the number of the attribute variables in the aim to give better performance to the further defect classification.

Keywords: Geometric parameters, invariant attributes, principal component analysis, weld defect image.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1056044

References:

[1] N. Nacereddine, “Automated method implementation for detection and classification of weld defects in industrial radiography," M.S. thesis, Dept. Automation and Signal Processing. Boumerdes Univ., Boumerdes, Algeria, 2004.
[2] “Guide for the Non-destructive Inspection of Welds". ANSI, American Welding Society, B1,10-86, USA, 1987.
[3] N. Nacereddine, R. Drai and A. Benchaala, “Weld defect extraction and identification in radiograms based neural networks," in Proc. IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, Crete, Greece, June 2002, pp 38-43.
[4] M. Mjahed, “Reconnaissance de formes planaires d-une scène d-image ├á partir d-une analyse morphologique par la technique des réseaux de neurones," TELECOM-97, Fès, Maroc, 1997.
[5] W.J. Krzanowski and F.H.C. Marriout FHC. Multivariate analysis. Vol 1. Kendall-s library of statistics 1994.
[6] A.K. Jain, R.P.W. Duin, and J. Mao, “Statistical Pattern Recognition: A Review," IEEE Transactions On Pattern Analysis And Machine Intelligence, vol. 22, n┬░ 1, January 2000.
[7] L. Dorst and A.W.M. Smeulders, “Length Estimators for Digitized Contours," Computer Vision, Graphics and Image Processing, vol. 40, pp.311-333, 1987.
[8] J. G. Postaire, De l-image ├á la décision. Edition Dunod. 1987.
[9] M.K. Hu, “Visual Pattern Recognition by Moments Invariants," IRE Trans. Info. Theory, vol. IT-8, 1962.
[10] A.K. Jain. Fundamentals of digital image processing. Prentice-Hall 1989.