Weld Defect Classification in Radiographic Film Using Statistical Texture and Support Vector Machine

Abstract:

Weld defect identification requires radiographic operator experience, so the interpretation of weld defect type could potentially bring subjectivity and human error factor. This paper proposes Statistical Texture and Support Vector Machine method for weld defect type classification in radiographic film. Digital image processing technique applied in this paper implements noise reduction using median filter, contrast stretching, and image sharpening using Laplacian filter. Statistical method feature extraction based on image histogram was proposed for describing weld defects texture characteristic of a radiographic film digital image. Multiclass Support Vector Machine (SVM) algorithm was used to perform classification of weld defects type. The result of classification testing shows that the proposed method can classify 83.3% correctly from 60 testing data of weld defects radiographic films.

• Periodical: Advanced Materials Research (Volume 896)
• Pages: 695-700
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.896.695
• Online since: February 2014
• Authors: Muhtadan Muhtadan*, Risanuri Hidayat, Widyawan Widyawan, Fahmi Amhar
• Keywords: Image Processing, Radiographic Weld Defect, Statistical Texture, Support Vector Machine (SVM)

References

[1] E. M. A. Hussein, Handbook on Radiation Probing, Gauging, Imaging and Analysis, Volume II: Applications and Design: Kluwer Academic Publisher, (2004).

[2] E. S. Amin, Aplication of Artificial Neural Network to evaluate weld defect of nuclear components, Journal of Nuclear and Radiation Physics, vol. 3, pp.83-92, (2008).

[3] H. Luo, H. Zeng, L. Hu, X. Hu, and Z. Zhou, Application of artificial neural network in laser welding defect diagnosis, Journal of Materials Processing Technology, vol. 170, pp.403-411, (2005).

DOI: 10.1016/j.jmatprotec.2005.06.008

[4] G. Weixin, T. Nan, and M. Xiangyang, A Novel Algorithm for Detecting Air Holes in Steel Pipe Welding Based on Hopfield Neural Network, pp.79-83, (2007).

DOI: 10.1109/snpd.2007.425

[5] E. P. Moura, R. R. Silva, M. H. S. Siqueira, and J. o. M. A. Rebello, Pattern Recognition of Weld Defects in Preprocessed TOFD Signals Using Linear Classifiers, Journal of Nondestructive Evaluation, vol. 23, pp.163-172, (2004).

DOI: 10.1007/s10921-004-0822-4

[6] R. C. Gonzalez and R. E. Woods, Digital Image Processing Third Edition: Pearson Prentice Hall, (2010).

[7] X. Wang, B. S. Wong, and C. Tan, Recognition of Welding Defects in Radiographic Images using Support Vector Machine Classifier, Research Journal of Applied Sciences, Engineering and Technology, vol. 2, pp.295-301, (2010).

[8] R. Behroozmand and F. Almasganj, Comparison of Neural Networks and Support Vector Machines Applied to Optimized Features Extracted from Patients' Speech Signal for Classification of Vocal Fold Inflammation, presented at the IEEE International Symposium on Signal Processing and Information Technology, (2005).

DOI: 10.1109/isspit.2005.1577209

[9] N. Nacereddine, M. Zelmat, S. S. Belaïfa, and M. Tridi, Weld defect detection in industrial radiography based digital image processing, in World Academy of Science, Engineering and Technology, (2005).

[10] Y. Wang, Y. Sun, P. Lv, and H. Wang, Detection of line weld defects based on multiple thresholds and support vector machine, NDT&E International, vol. 41, p.517–524, (2008).

DOI: 10.1016/j.ndteint.2008.05.004