Journal of Intelligent and Robotic Systems

, Volume 37, Issue 3, pp 321–336 | Cite as

Statistical Pattern Modeling in Vision-Based Quality Control Systems

  • Jose M. Armingol
  • Javier Otamendi
  • Arturo de la Escalera
  • Jose M. Pastor
  • Francisco J. Rodriguez


Machine vision technology improves productivity and quality management and provides a competitive advantage to industries that employ this technology. In this article, visual inspection and quality control theory are combined to develop a robust inspection system with manufacturing applications. The inspection process might be defined as the one used to determine if a given product fulfills a priori specifications, which are the quality standard. In the case of visual inspection, these specifications include the absence of defects, such as lack (or excess) of material, homogeneous visual aspect, required color, predetermined texture, etc. The characterization of the visual aspect of metallic surfaces is studied using quality control chars, which are a graphical technique used to compare on-line capabilities of a product with respect to these specifications. Original algorithms are proposed for implementation in automated visual inspection applications with on-line execution requirements. The proposed artificial vision method is a hybrid between the two usual methods of pattern comparison and theoretical decision. It incorporates quality control theory to statistically model the pattern for defect-free products. Specifically, individual control charts with 6-sigma limits are set so the inspection error is minimized. Experimental studies with metallic surfaces help demonstrate the efficacy and robustness of the proposed methodology.

quality control charts automated visual inspection image processing statistical pattern recognition steel surfaces 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bahlmann, C., Heidemann, G., and Ritter, H.: Artificial neural networks for automated quality control of textile seams, Pattern Recognition 32 (1999), 1049–1060.Google Scholar
  2. 2.
    Caelly, T.: A brief overview of texture processing in machine vision, in: Early Vision and Beyond, MIT Press, Cambridge, MA, 1994, pp. 79–86.Google Scholar
  3. 3.
    Chung, Y. K., Kim, K. H., and Kim, H. B.: Extracting of line features for automated inspection of vehicle doors, in: Internat. Conf. on Signal Processing Applications and Technology, San Diego, CA, 1997.Google Scholar
  4. 4.
    Cootes, T. F., Page, G. J., Jackson, C. B., and Taylor, C. J.: Statistical grey-level models for objects location and identification, Image Vision Computing 14 (1996), 533–540.Google Scholar
  5. 5.
    D'Agostino, R. B. and Stevens,M. A.: Goodness-of-Fit Techniques, Marcel Dekker, New York, 1986.Google Scholar
  6. 6.
    Fernández, J., Fernández, C., and Aracil, R.: On-line integral quality control of ceramic tiles by artificial vision, in: Proc. of the Internat. Conf. on Quality Control by Artificial Vision, Vol. 1, France, 1997.Google Scholar
  7. 7.
    Grant, E. L. and Leavenworth, R. S.: Statistical Quality Control, McGraw-Hill, New York, 1988.Google Scholar
  8. 8.
    Hirvonen, J.: Measurement of the quality of mechanical pulp by machine vision, Machine Vision News 5 (2000).Google Scholar
  9. 9.
    Kennedy, S.W. and Hoffman, E. G.: Inspection and Ganging, Industrial Press, New York, 1987.Google Scholar
  10. 10.
    Kim, K. H., Kim, Y.W., and Suh, S.W.: Automatic visual inspections system to detect wrongly attached components, in: Internat. Conf. on Signal Processing Applications and Technology, Toronto, Canada, 1998.Google Scholar
  11. 11.
    Nelson, L. S.: Control charts for individual measurements, J. Quality Technol. 14(3) (1982).Google Scholar
  12. 12.
    Niemi, A.: Machine vision based control of the paper machine solution of a 200-year old problem, Machine Vision News 5 (2000).Google Scholar
  13. 13.
    Noble, A., Nguye, V., Marinos, C., and Mundy, J.: Template guided visual inspection, in: Proc. of the 2nd European Conf. on Computer Vision, 1992, pp. 893–901.Google Scholar
  14. 14.
    Parker, J. R.: Algorithms for Image Processing and Computer Vision, Wiley Computer, New York, 1997.Google Scholar
  15. 15.
    Rioux, M., Goldin, G., and Blais, F.: Differential inspection of shapes using 3D optical measurements, in: Proc. of Optical 3D Measurement Techniques II: Applications in Robotics. Quality Control and Robotics, SPIE 2252, 1993, pp. 493–501.Google Scholar
  16. 16.
    Silven, O. and Kauppinen, H.: Recent developments in wood inspection, Internat. J. Pattern Recognition Artificial Intelligence 10(1) (1996), 83–95.Google Scholar
  17. 17.
    Smith, B.: Making war on defects: Six-sigma design, IEEE Spectrum 30(9) (1993), 43–47.Google Scholar
  18. 18.
    Veistinen, M. and Simomaa, K.: Machine vision reveals defective magnets and qualify parts for assembling, Machine Vision News 4 (1999).Google Scholar
  19. 19.
    Winchell, W.: Inspection and measurement in manufacturing, Society of Manufacturing Engineers, 1996.Google Scholar

Copyright information

© Kluwer Academic Publishers 2003

Authors and Affiliations

  • Jose M. Armingol
    • 1
  • Javier Otamendi
    • 1
  • Arturo de la Escalera
    • 1
  • Jose M. Pastor
    • 1
  • Francisco J. Rodriguez
    • 1
  1. 1.Department of Systems Engineering and AutomationUniversidad Carlos III de MadridMadridSpain

Personalised recommendations