Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Geometric Scheme Analysis and Region Segmentation for Industrial CR Images

산업용 CR영상의 기하학적 구도분석과 영역분할

  • Hwang, Jung-Won (Dept. of Electronics Computer Engin., Hanyang University) ;
  • Hwang, Jae-Ho (Dept. of Electronic Engin., Hanbat University)
  • 황중원 (한양대학교 대학원 전자컴퓨터통신공학과) ;
  • 황재호 (한밭대학교 전자공학과)
  • Published : 2009.07.25
Download PDF
⟨ Previous Next ⟩

Abstract

A reliable detection of regions in radiography is one of the most important task before the evaluation of defects on welded joints. The extracted features is to be classified into distinctive clusters for each segmented region. But conventional segmentation techniques give unsatisfactory results for this task due to the spatial superposition of intensity and low signal-to-ratio(SNR) in radiographic images. The usage of global or local processes not only provide the necessary noise resistance but also fail in classification of regions. In this paper, we presents an appropriate approach for segmentation of region-based indications in industrial Computed Radiography(CR) images. The geometric differences between welded and non-welded area which is generated on radiography as the representative regions(background, thickness, middle and welded region in steel tube image) have constructed the hierarchical structure. Although this structure is contaminated by noise, the scheme between regions can be selected by the help of local clustering based on distinctive geometric property of each region. Because of the geometric nature of the considered region and so that the region is selected layer by layer, and that the real class represents the boundary between regions, the vertical and horizontal clustering process in each layer must be judicious. In order to show the effectiveness of this approach, a comparative experiment of various segmentation method is performed on industrial steel tube CR images.

방사선영상의 신뢰할 만한 영역검출은 용접부위 결함탐지 이전의 중요한 작업 중의 하나이다. 추출되는 특징들은 각 분할된 영상에 대하여 서로 다른 군집으로 분류되어야한다. 그러나 종래의 분할 기법으로는 방사선영상 고유의 색도중첩과 낮은 SN비로 인해 만족할 만한 결과를 얻기가 쉽지 않다. 전체나 국부처리로는 잡음제거에 취약할 뿐만 아니라 영역분류도 어렵다. 이 논문은 산업용 CR 영상에서 영역기반실현의 분할을 위한 적절한 기법을 제시한다. 강판튜브에서 용접과 비용접 구간의 기하학적 차이가 영상화 과정을 통해 배경부, 두께부, 중간부 및 용접부 영역을 생성하고 계층 구조적 배열을 형성한다. 비록 그 구조가 잡음에 훼손되기는 하지만 영역구분 구도 각 영역의 차별된 기하학적 특성에 근거한 국부군집화에 의해 선별이 가능하다. 관련 영역의 기하학적 속성에 의해 그에 따른 영역이 계층별로 선별되어 실제 구분이 영역간 경계를 반영하기 때문에 직경과 길이방향의 군집화는 각 계층의 구별을 명확케 한다. 그리고 산업용 강판튜브 CR영상에 다양한 분할 방식으로 비교 실험을 실시하여 이 기법의 효과를 보였다.

Keywords

References

  1. R. J. Patei, "Digital applications of radiography," in Proc. of 3rd MENDT, Manama, Barain, Nov. 2005
  2. E. Deprins, "Computed radiography in NDT applications," in Proc. of 16th WCNDT, Montreal, Canada, Aug. 2004
  3. H. H. Barrett and W. Swindell, Radiographic imaging, Academic Press, 1981
  4. C. Melvin and K. Sbdel-Hadi, "A simulated comparison of turnstile and Poisson photons for X-ray imaging," in Proc. of IEEE CCECE, pp. 1165-1170, Manitoba, Canada, May 2002
  5. E. R. Williams, J. E. Faller and H. A. Hill, "New Experimental Test of Coulomb's Law: A Laboratory Upper Limit on the Photon Rest Mass," Physical Review Letters, Physical Review Letters, Vol. 26, pp. 721-724, March 1971 https://doi.org/10.1103/PhysRevLett.26.721
  6. C. Gueudre, J. Moysan and G. Corneloup, "Weld quality control by radioscopy using edge and area segmentation method," in Proc. of 15th WCNDT, Roma, Italy, Oct. 2000
  7. N. Nafaa, D. Redouane and B. Amar, “Weld defect extraction and classification in radiographic testing based artificial neural networks,” in Proc. of 15th WCNDT, Roma, Italy, Oct. 2000
  8. X. Zhang and J. Xu and Y. Li, "The research of defect recongition for radiographic weld image based on fuzzy neural network," in Proc. of 5th WCICA, Hangzhou, China, June 2004
  9. Y. Kabir and R. Drai, "A new co-operative segmentation method applied to X-ray images," in Proc. of 15th WCNDT, Roma, Italy, Oct. 2000
  10. H. Jagannathan, N. Bhaskar, P. Sriraman and N. A. Vijay, "A step towards automatic defect pattern analysis and evaluation in industrial radiography using digital image processing," in Proc. of 15th WCNDT, Roma, Italy, Oct. 2000
  11. D. Redouane, K. Yacine, A. Amal, A. Farid and B. Amar, "Evaluation of corroded pipelines wall thickness using image processing in industrial radiography," in Proc. of 15th WCNDT, Roma, Italy, Oct. 2000
  12. 황중원, 황재호, "선군집분할방식의 강판튜브 엑스선 영상에의 적용성 판별," 대한전자공학회 하계종합학술회의논문집I, 397-398쪽, 부산, 한국, 2007년 7월
  13. J. H. Hwang and J. W. Hwang, "Image analysis for specific region segmentation of steel-tube radiographic Images," in Proc. of ITC-CSCC 2007, pp. 365-366, Busan, Korea, July 2007
  14. C. Daniel and F. S. Wood, Fitting Equations to Data, John Wiley & Sons, New York, 1980
  15. J. Besag, "On the statistical analysis of dirty pictures," J. R. Statist. Soc., Vol. 48, no. 3, pp. 259-302, 1986
  16. 황재호, "변형된 ICM 방식에 의한 영역판별", 전자공학회논문지 제43권 SP편, 제5호, 37-44쪽, 2006년 9월