Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지
DOI QR코드

DOI QR Code

Welding Bead Detection Inspection Using the Brightness Value of Vertical and Horizontal Direction

수직 및 수평 방향의 밝깃값을 이용한 용접 비드 검출 검사

  • Jae Eun Lee (Division of Computer Engineering and AI, Pukyong National University) ;
  • Jong-Nam Kim (Division of Computer Engineering and AI, Pukyong National University)
  • 이재은 (부경대학교 컴퓨터.인공지능공학부) ;
  • 김종남 (부경대학교 컴퓨터.인공지능공학부)
  • Received : 2022.12.02
  • Accepted : 2022.12.26
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Shear Reinforcement of Dual Anchorage(SRD) is used to reinforce the safety of reinforced concrete structures at construction sites. Welding is used to make shear reinforcement, and welding plays an important role in determining productivity and competitiveness of products. Therefore, a weld bead detection inspection is required. In this paper, we suggest an algorithm for inspecting welding beads using image data of welding beads. First, the proposed algorithm calculates a brightness value in a vertical direction in an image, and then divides a welding bead in a vertical direction by finding a position corresponding to a 50% height point of the brightness value distribution in the image. The welding bead area is also divided in the same way for the horizontal direction, and then the segmentation image is analyzed if there is a welding bead. The proposed algorithm reduced the amount of computation by performing analysis after specifying the region of interest. In addition, accuracy could be improved by using all brightness values in the vertical and horizontal directions using the difference of brightness between the base metal and the welding bead region in the SRD image. The experiment compared the analysis results using five algorithms, such as K-mean and K-neighborhood, as a method to detect if there is a welding bead, and the experimental result proved that the proposed algorithm was the most accurate.

SRD(Shear Reinforcement of Dual Anchorage)는 건축 현장에서 철근 콘크리트 구조물의 안전성을 보강하는 데 사용된다. 전단 보강재를 만들 때에는 용접이 사용되며, 용접은 제품의 생산성 및 경쟁력을 좌우하는 데 중요한 역할을 한다. 따라서 용접 비드 검출 검사가 필요하다. 본 연구에서는 용접 비드의 영상 자료를 이용하여 용접 비드를 검사하는 알고리즘을 제안한다. 제안한 알고리즘은 먼저 영상 내 수직 방향으로 밝깃값을 계산한 뒤, 밝깃값 분포의 50% 높이 지점에 해당하는 위치를 영상에서 찾아서 수직 방향으로 용접 비드를 분할한다. 그리고 수평 방향에 대해서도 동일한 방법으로 용접 비드 영역을 분할한 뒤, 분할 영상을 분석하여 용접비드 유무를 검사한다. 제안한 알고리즘은 관심 영역을 먼저 지정한 뒤 분석을 수행하여 연산량을 감소시켰다. 또한 SRD 영상에서 모재와 용접 비드 영역 사이에 밝깃값의 차이 특징을 이용하여 수직 및 수평 방향의 모든 밝깃값을 이용함으로써 정확도를 높일 수 있었다. 실험에서는 용접 비드 유무를 검출하기 위한 방법들로써 K-평균, k-최근접 이웃 등 5개의 알고리즘을 이용하여 분석 결과들을 비교하였으며, 타 알고리즘들에 비해 제안한 알고리즘의 정확도가 가장 높음을 보였다.

Keywords

Acknowledgement

본 연구는 한국연구재단의 기초연구사업과 부경대학교 링크사업단으로부터 지원을 받아 수행된 연구 결과임.

References

  1. M. Nasor and W. Obaid, "Segmentation of osteosarcoma in MRI images by K-means clustering, Chan-Vese segmentation, and iterative Gaussian filtering," IET Image Processing, Vol. 15, No. 6, pp. 1310-1318, 2021. https://doi.org/10.1049/ipr2.12106
  2. M. R. Hassan, R. R. Ema and T. Islam, "Color image segmentation using automated K-means clustering with RGB and HSV color spaces," Global Journal of Computer Science and Technology, Vol.17, No.2, pp.26-33, 2017.
  3. X. Zheng, Q. Lei, R. Yao, Y. Gong, and Q. Yin, "Image segmentation based on adaptive K-means algorithm," EURASIP Journal on Image and Video Processing, Vol. 68, No. 1, pp. 1-10, 2018.
  4. S. Wazarkar, B. N. Keshavamurthy and A. Hussain, "Region-based segmentation of social images using soft KNN algorithm," Procedia Computer Science, Vol. 125, pp. 93-98, 2018. https://doi.org/10.1016/j.procs.2017.12.014
  5. B. M. S. Rangel, M. A. A. Fernandez, J. C. Murillo, J. C. P. Ortega, and J. M. R. Arreguin. "KNN-based image segmentation for grapevine potassium deficiency diagnosis," International Conference on Electronics, Communications and Computers (CONIELECOMP), pp. 48-53, 2016.
  6. S. Prabu, "Object Segmentation Based on the Integration of Adaptive K-means and GrabCut Algorithm," In 2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET), pp. 213-216, 2022.
  7. M. P. Saranya, V. Praveena, M. B. Dhanalakshmi, M. K. Karpagavadivu and P. Chinnasamy, "Diagnosis of gastric cancer using mask R-CNN and GrabCut segmentation method," Journal of Positive School Psychology, Vol. 6, No. 4, pp. 203-206, 2022.
  8. Y. Li, J. Zhang, P. Gao, L. Jiang, and M. Chen, "Grab cut image segmentation based on image region.," In 2018 IEEE 3rd international conference on image, vision and computing (ICIVC), pp. 311-315, 2018.
  9. D. Huang, S. Liao, A. Sunny, and S. Yu, "A novel automatic surface scratch defect detection for fluid-conveying tube of Coriolis mass flow-meter based on 2D-direction filter," Measurement, Vol. 126, pp. 332-341, 2018. https://doi.org/10.1016/j.measurement.2018.05.060
  10. M. Zhang, S. Cheng, X. Cao, H. Chen, and X. Xu, "Entropy-Based Locally Adaptive Thresholding for Image Segmentation," SSRN, 2022.
  11. C. Zhang, Y. Xie, D. Liu, and L. Wang, "Fast threshold image segmentation based on 2D fuzzy Fisher and random local optimized QPSO," IEEE Trans. Image Process, Vol. 26, No. 3, pp. 1355-1362, Mar. 2017. https://doi.org/10.1109/TIP.2016.2621670
  12. G. Ma, and X. Yue, "An improved whale optimization algorithm based on multilevel threshold image segmentation using the Otsu method," Engineering Applications of Artificial Intelligence, Vol. 113, pp. 104960, 2022.