Crack defects detection in radiographic weldment images using FSVM and beamlet transform

  • Authors:

  • Zheng Sun;Dianxu Ruan;Yun Ma;Xiaolei Hu;Xiao-guang Zhang

  • Affiliations:

  • College of Mechanical and Electrical Engineering, China University of Mining and Technology, Xuzhou, China;College of Mechanical and Electrical Engineering, China University of Mining and Technology, Xuzhou, China;College of Mechanical and Electrical Engineering, China University of Mining and Technology, Xuzhou, China;College of Mechanical and Electrical Engineering, China University of Mining and Technology, Xuzhou, China;College of Mechanical and Electrical Engineering, China University of Mining and Technology, Xuzhou, China and Department of Electronic Science and Engineering, Nanjing University, Nanjing, China

  • Venue:
  • FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 3
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In order to solve the problem of crack defects detection in radiographic weldment images, this paper proposes a new detection method using fuzzy support vector machine (FSVM) and Beamlet transform. FSVM gives small weights to samples which contain noise and isolated points, which overcomes the disadvantage that SVM is sensitive to noise and isolated points in samples on some extent. Firstly, wavelet transform and morphological method are applied to denoise and eliminate the image background, which will enhance the defect features; Secondly, FSVM is used to recognize and locate the rough region containing crack defects; Finally, the crack defects are extracted through Beamlet transform in the rough region. The experimental results show that the proposed method can detect the crack defects in weldment images successfully.