Earticle

초록

영어

Crack inspection is a critical processing step in an AXI (automatic X-ray inspection) system. There are challenges for crack inspection since images are usually with serious noise, non-uniform brightness, etc. This paper proposes a novel line filter that can segment various widths of crack regions in those inhomogeneity brightness and noisy X-ray images. First, the input image is smoothed by the Gaussian functions with different scales, resulting in an image pyramid. Second, the adjacent images in the pyramid are subtracted to generate a Difference of Gaussian (DoG) pyramid and the extreme points from the subtracting result are selected as the output of the method. An edge suppression function is then defined to remove the edge response of the filter. Finally, the output of the proposed filter is defined as the combination of the DoG extreme result and the suppression function. The proposed method was applied to an AXI system and it performed better than the other two exited approaches. Experimental results showed that the proposed filter is robust to the image noise, crack sizes and brightness.

목차

Abstract
 1. Introduction
 2. Related Works
 3. The Proposed Method
  3.1. Line Region Segmentation By the DoG Detector
  3.2. Edge Suppression
 4. Experimental Results
 5. Conclusion
 References

키워드

저자

• Yiqiang Lai [ South China Business College, Guangdong University of Foreign Studies, Guangzhou 510545, China ]
• Shaohu Peng [ School of Mechanical and Electric Engineering, Guangzhou University, Guangzhou 510006, China ] Corresponding author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605