Geometric Pattern Matching for Industrial Robot Guidance

  • William Silver


In spite of decades of work on object recognition in both the academic and industrial communities, the majority of industrial robotic applications are not vision guided, relying instead on mechanical fixturing and dead reckoning. The primary reason for this is that object recognition by machine vision simply has not worked well enough to be competitive. Recent developments in object recognition algorithms, driven by increasing demand for flexible automation and enabled by processor architectures well-suited to image analysis, have begun to change this picture. We will discuss requirements that must be satisfied for a method to achieve widespread use, trace the development of industrial object recognition, describe the present method, and mention some applications. Throughout we offer industrial perspective and experience to an academic forum, in hopes of better understanding.


Object Recognition Machine Vision Feature Detection Dead Reckoning Graceful Degradation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Grimson W.E.L., 1990, Object Recognition by Computer. M. I. T. Press, Cambridge.Google Scholar
  2. [2]
    Marr D., 1982, Vision. W.H. Freeman & Co., New York.Google Scholar
  3. [3]
    Havelock D.I., 1989, Geometric Precision in Noise-Free Digital Images. IEEE Trans. Patt. Anal & Mach. Intell., vol. 11, no. 10., pp. 1065–1075.CrossRefGoogle Scholar
  4. [4]
    O’Gorman L., 1996, Subpixel Precision of Straight-Edged Shapes for Registration and Measurement. IEEE Trans. Patt. Anal. and Mach. Intell., vol. 18, no. 7., pp. 746–751.CrossRefGoogle Scholar
  5. [5]
    Horn B.K.P., 1986, Robot Vision. MIT Press, Cambridge.Google Scholar
  6. [6]
    Roth, S.D., 1989, Vision System for Distinguishing Touching Parts. U.S. Patent #4, 876, 728.Google Scholar
  7. [7]
    Silver W.M., 1987, Normalized Correlation Search in Alignment, Gauging, and Inspection. Proc. SPIE, vol. 755, pp. 23–34.CrossRefGoogle Scholar
  8. [8]
    Silver W.M., R.A. Wolff, R.E. Dynneson, 1990, Digital Image Processing System. U.S. Patent #4, 972, 359.Google Scholar
  9. [9]
    McGarry J., 1991, Acumen 900 Series News Release. October 22, 1991.Google Scholar
  10. [10]
    Hough P.V.C., 1962, Method and means for recognizing complex patterns. U.S. Patent #3,069,654.Google Scholar
  11. [11]
    Ballard D.H., C.M. Brown, 1982, Computer Vision. Prentice-Hall, Englewood Cliffs, N.J.Google Scholar
  12. [12]
    Lubofsky E., 1999, Machine Vision Streamlines Robotic Handling of Engine Parts. Robotics World, March/April 1999, pp. 20–25.Google Scholar
  13. [13]
    Staff Writer, 1999, Vision Tech. Improves Robotic Part Loading. Manufacturing Engineering, March 1999, pp. 154–156.Google Scholar
  14. [14]
    Machine Design, March 11, 1999, p. 176.Google Scholar
  15. [15]
    ABB Flexible Automation, 1998, FlexPicker IRB 340 Industrial Robot product brochure.Google Scholar
  16. [16]
    Staff Writer, 1999, Ford automates engine block loading process with machine vision. Automotive Engineering International, February.Google Scholar
  17. [17]
    Quality, April 1999, pp. 120–121.Google Scholar
  18. [18]
    Staff Writer, 1999, Rim Shot. Manufacuring Automation, March/April.Google Scholar
  19. [19]
    Murphy W.B., 1999, Tire Tread Recognition. Proc. 1999 International Robots & Vision Conference, Automated Imaging Association.Google Scholar

Copyright information

© Springer-Verlag London 2000

Authors and Affiliations

  • William Silver
    • 1
  1. 1.One Vision DriveCognex CorporationNatickUSA

Personalised recommendations