Nondestructive testing based weld defect classification using tetrolet transform
Abstract
The process of visual inspection of weld elements is an important task for providing a safe and reliable outsource in most of the industrial sectors. As most of the industries are still using only the human vision process of manually operation that makes the test results look more subjective. Due to this an image processing algorithm based on the Non-Destructive Testing (NDT) method is introduced to test the welding surface for recognizing the external and internal flaws without disturbing its suitability for service. The proposed system is implemented by using the GD X-ray weld image database. Due to less number of input images, the sub images are extracted and are separated as the normal and the defected images and are used as training and testing set of input images. Then the tetrolet transform is applied for both the testing and training process in order to obtain the maximum coefficients from which the features like energy and entropy features are extracted. Then the testing can be done by using the Support Vector Machines (SVM) classifier for the classification purpose and are validated using the k-fold algorithm. Result shows that the proposed system produces promising results with 100% of classification accuracy
About this article
Keywords
- Energy
- Entropy
- GD X-Ray Weld Images
- Non-Destructive Testing
- SVM.
References
[1] G. Ye, J. Guo, Z. Sun, C. Li, and S. Zhong, “Weld bead recognition using laser vision with model-based classification”, Robotics and Computer-Integrated Manufacturing, vol. 52, pp. 9-16, Aug 2018.https://doi.org/10.1016/j.rcim.2018.01.006.
[2] Khumaidi, E. M. Yuniarno, and M. H. Purnomo, “Welding defect classification based on convolution neural network (CNN) and Gaussian kernel”, IEEE International Seminar on Intelligent Technology and Its Applications, pp. 261-265, 2017.
[3] F. Mekhalfa, and N. Nacereddine, “Gentle Adaboost algorithm for weld defect classification”, IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, pp. 301-306, 2017.
[4] K. Ali, M. Awan, A. Jalil, and F. Mustansar, “Localization and classification of welding defects using genetic algorithm based optimal feature set”, IEEE International Conference on Information and Communication Technologies, pp. 1-6, 2015.https://doi.org/10.1109/ICICT.2015.7469485.
[5] A. Moghaddam, “Image processing techniques for classification of linear welding defects”, IEEE 2nd International Conference on Knowledge-Based Engineering and Innovation, pp. 978-981, 2015.
[6] J. Kumar, R. S. Anand, and S. P. Srivastava, “Multi-class welding flaws classification using texture feature for radiographic images”, IEEE International Conference on Advances in Electrical Engineering, pp. 1-4, 2014.
[7] Valavanis, and D. Kosmopoulos, “Multiclass defect detection and classification in weld radiographic images using geometric and texture features”, Expert Systems with Applications, vol. 37, no. 12, pp. 7606-7614, Dec 2010.https://doi.org/10.1016/j.eswa.2010.04.082.
[8] Kumar, R. S. Anand, and S. P. Srivastava, “Flaws classification using ANN for radiographic weld images”, IEEE International Conference on Signal Processing and Integrated Networks, pp. 145-150, 2014.https://doi.org/10.1109/SPIN.2014.6776938.
[9] Hassan, A. M. Awan, and A. Jalil, “Welding defect detection and classification using geometric features”, IEEE 10th International Conference on Frontiers of Information Technology, pp. 139-144, 2012.
[10] R. Vilar, J. Zapata, and R. Ruiz, “An automatic system of classification of weld defects in radiographic images”, NDT & E International, vol. 42, no. 5, pp. 467-476, jul 2010.https://doi.org/10.1016/j.ndteint.2009.02.004.
[11] W. Mu, J. Gao, H. Jiang, Z. Wang, F. Chen, and C. Dang, “Automatic classification approach to weld defects based on PCA and SVM”, Insight-Non-Destructive Testing and Condition Monitoring, vol. 55, no. 10, pp. 535-539, Oct 2013.https://doi.org/10.1784/insi.2012.55.10.535.
[12] Y. Wang, and H. Guo, “Weld defect detection of X-ray images based on support vector machine”, IETE Technical Review, vol. 31, no. 2, pp. 137-142,Mar 2014.https://doi.org/10.1080/02564602.2014.892739.
[13] F. Mekhalfa, and N. Nacereddine, “Multiclass Classification of Weld Defects in Radiographic Images Based on Support Vector Machines”, 10th International Conference on Signal-Image Technology and Internet-Based Systems, pp. 1-6, 2014.https://doi.org/10.1109/SITIS.2014.72.
[14] S. M. Vali, K. N. Kishore, and G. Prathibha, “Robust image watermarking using tetrolet transform”, IEEE International Conference on Electrical, Electronics, Signals, Communication and Optimization, pp. 1-5.
[15] Iyyanarappan, and G. Tamilpavai, “Glaucomatous Image Classification Using Wavelet Based Energy Features and PNN”, International journal of technology enhancements and emerging engineering research pp. 2-4, 2014.