Classification of Welding Defects in Radiographic Images Using an ANN with Modified Performance Function
In this paper, we describe an automatic classification system of welding defects in radiographic images. In a first stage, image processing techniques, including noise reduction, contrast enhancement, thresholding and labelling, were implemented to help in the recognition of weld regions and the detection of weld defects. In a second stage, a set of geometrical features which characterise the defect shape and orientation was proposed and extracted between defect candidates. In a third stage, an artificial neural network for weld defect classification was used under a regularisation process with different architectures for the input layer and the hidden layer. Our aim is to analyse this ANN modifying the performance function for differents neurons in the input and hidden layer in order to obtain a better performance on the classification stage.
KeywordsHide Layer Performance Function Radiographic Image Weld Region Welding Defect
Unable to display preview. Download preview PDF.
- 1.Sofia, M., Redouane, D.: Shapes recognition system applied to the non destructive testing. In: Proceedings of the 8th European Conference on Non-Destructive Testing (ECNDT 2002), Barcelona, June 17-21 (2002)Google Scholar
- 2.Vieira, et al.: Characterization of welding defects by fractal analysis of ultrasonic signals. Chaos Solitons & Fractals (2008)Google Scholar
- 3.da Silva, R.R., Siqueira, M.H.S., Calhoba, L.P., Rebello, J.M.A.: Radiographics pattern recognition of welding defects using linear classifier. Proceedings 43(10) (2001)Google Scholar
- 4.da Silva, R.R., Siqueira, M.H.S., Calhoba, L.P., da Silva, I.C., de Carvalho, A.A., Rebello, J.M.A.: Contribution to the development of a radiographic inspection automated system. Proceedings (2002)Google Scholar
- 5.Gao, et al.: Binary-tree Multi-Classifier for Welding Defects and Its Application Based on SVM. In: The Sixth World Congress on Intelligent Control and Automation, WCICA 2006, vol. 2, pp. 8509–8513 (2006)Google Scholar
- 6.Mirapeix, J., García-Allende, P.B., Cobo, A., Conde, O.M., López-Higuera, J.M.: Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks. NDT & E International (2007)Google Scholar
- 8.Mery, et al.: Automatic detection of welding defects using texture features. Insight-Non-Destructive Testing and Condition Monitoring (2003)Google Scholar
- 9.Vilar, R., et al.: Weld defects recognition and classification based on ANN. In: Proceedings of the Fifth IASTED International Conference on Signal Processing, Pattern Recognition, and Aplication, Innsbruck, Austria, pp. 470–475 (2008)Google Scholar
- 10.Oja, et al.: Principal component analysis by homogeneous neural networks, Part I: The weighted subspace criterion. IEICE Trans. Inf. and Systems E75-D (3), 366–375 (1992)Google Scholar
- 11.Oja, et al.: Principal component analysis by homogeneous neural networks, Part II: Analysis and extensions of the learning algorithms. IEICE Trans. Inf. and Systems E75-D (3), 376–382 (1992)Google Scholar
- 12.Widrow, et al.: Adaptive switching circuits. In: Proceedings IRE WESCON Convention Record, pp. 96–104 (1960)Google Scholar
- 13.Dennis, et al.: Numerical Methods for Unconstrained Optimization and Nonlinear Equations. Book (1983)Google Scholar