Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지
DOI QR코드

DOI QR Code

A Learning-based Visual Inspection System for Part Verification in a Panorama Sunroof Assembly Line using the SVM Algorithm

SVM 학습 알고리즘을 이용한 자동차 썬루프의 부품 유무 비전검사 시스템

  • Kim, Giseok (Department of Computer Science & Engineering, Korea University of Technology and Education) ;
  • Lee, Saac (Department of Computer Science & Engineering, Korea University of Technology and Education) ;
  • Cho, Jae-Soo (Department of Computer Science & Engineering, Korea University of Technology and Education)
  • 김기석 (한국기술교육대학교 컴퓨터공학부) ;
  • 이삭 (한국기술교육대학교 컴퓨터공학부) ;
  • 조재수 (한국기술교육대학교 컴퓨터공학부)
  • Received : 2013.08.20
  • Accepted : 2013.10.04
  • Published : 2013.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a learning-based visual inspection method that addresses the need for an improved adaptability of a visual inspection system for parts verification in panorama sunroof assembly lines. It is essential to ensure that the many parts required (bolts and nuts, etc.) are properly installed in the PLC sunroof manufacturing process. Instead of human inspectors, a visual inspection system can automatically perform parts verification tasks to assure that parts are properly installed while rejecting any that are improperly assembled. The proposed visual inspection method is able to adapt to changing inspection tasks and environmental conditions through an efficient learning process. The proposed system consists of two major modules: learning mode and test mode. The SVM (Support Vector Machine) learning algorithm is employed to implement part learning and verification. The proposed method is very robust for changing environmental conditions, and various experimental results show the effectiveness of the proposed method.

Keywords

References

  1. AIA (Automated Imaging Association), n.d., veiwed January 2010, , 2010.
  2. S. Lee, G. Kim, and J. S. Cho, "The inspection for volts on vehicle frames using polar coordinated histogram," The 25 th Workshop on Image Procesesing and Image Understanding (in Korean), p. 106, Jeju, 2013.
  3. C. Cortes and V. N. Vapnik, Support-Vector Networks, Machine Learning, 20, 1995.
  4. V. Vapnik, The Nature of Statistical Learning Theory, New York:Springer-Verlag, 1995.
  5. C.-X. Dong, S.-Q. Yang, X. Rao, and J.-L. Tang, "An algorithm of estimating the generalization performance of RBF-SVM," Proc. of the Fifth International Conference on Computational Intelligence and Multimedia Applications (ICCIMA'03), pp. 61-66, Sep. 2003.
  6. X. Liang, "Effective method of pruning support vector machine classifiers," Neural Networks, IEEE Transactions on, vol. 21, no. 1, pp. 26-38, Dec. 2009.
  7. C. H. Park, H. M. Bae, J. P. Yun, and S. W. Yun, "Automated surface inspection systm for black resin coated steel," International Conference on Control Automation and Systems (ICCAS), Oct. 2012.
  8. S. J. Lee and S. W. Kim, "Classifying scrach defects on billets using image processing and SVM," Journal of Institute of Control, Robotics and Systems (ICROS) (in Korean), vol. 19, no. 3, pp. 256-261, Mar. 2013. https://doi.org/10.5302/J.ICROS.2013.12.1849

Cited by

  1. Auto Parts Visual Inspection in Severe Changes in the Lighting Environment vol.21, pp.12, 2015, https://doi.org/10.5302/J.ICROS.2015.15.0134