A machine vision system with learning capabilities

  • D. R. Skinner
  • K. K. Benke
Vision And Robotics
Part of the Lecture Notes in Computer Science book series (LNCS, volume 406)


We describe a new approach to machine vision which employs local operators with coefficients optimized by a learning process. Any desired performance index may be used and determination of coefficients is achieved on the basis of training images. Experimental results are presented for target discrimination, automatic visual inspection, and the identification of surface defects on materials.

Keywords and phrases

machine vision texture discrimination texture segmentation automatic visual inspection target detection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

7. References

  1. Benke, K.K. "Rapid Texture Discrimination Using Local Operators", Australian Computer Sci. Comm., Vol 10, No.1(February, 1988), pp. 334–345. Paper presented at 11th Australian Computer Sci. Conf., Univ. of Queensland, St. Lucia, 3–5 February, 1988.Google Scholar
  2. Benke, K.K. and Skinner, D.R. "Segmentation of Visually Similar Textures by Convolution Filtering", Australian Computer J., Vol 19, No.3 (August, 1987), pp. 134–139.Google Scholar
  3. Benke, K.K., Skinner, D.R. and Woodruff, C.J. "Convolution Operators as a Basis for Objective Correlates for Texture Perception", IEEE Trans. Syst. Man and Cybern., Vol SMC-18, No. 1 (January/February 1988), pp. 158–163.Google Scholar
  4. Besl, P.J., Delp, E.J. and Jain, R. "Automatic Visual Solder Joint Inspection", IEEE J. Robot. Autom., Vol RA-1, No. 1 (March 1985), pp. 42–56.Google Scholar
  5. Brodatz, P. (1967) Textures, Dover, New York.Google Scholar
  6. Casasent, D. and Vinod, S. "Fourier Transform Feature-Space Studies", Proc. SPIE Vol 449, Third International Conference on Robot Vision and Sensory Controls, Cambridge, Massachusetts (1983), pp. 2–8.Google Scholar
  7. Chung, M.C. "Detection of Fuze Defects by Image Processing Methods", Rept. MRL-R-1109, Materials Res. Lab., Ascot Vale, Vic. (March, 1988)Google Scholar
  8. Cornsweet, T.N. (1970) Visual Perception, Academic Press, New York, USA.Google Scholar
  9. Haralick, R.M., Shanmugam, K. and Dinstein, I. (1973). "Textural Features for Image Classification", IEEE Trans. Syst. Man and Cybern., Vol SMC-3, No. 6, pp.610–621.Google Scholar
  10. Laws, K.I. "Textured Image Segmentation", USCIPI Rept. 940, Univ. of Southern California (January, 1980)Google Scholar
  11. Marr, D. (1982) Vision, Freeman, San Francisco, USA.Google Scholar
  12. Pratt, W.K. (1978) Digital Image Processing, Wiley, New York, USA.Google Scholar
  13. Skinner, D.R. and Benke, K.K. "The Adaptive Convolution Operator in Image Analysis", presented at Australian Bicentenary Congr. of Physicists, Univ. of New South Wales, Sydney, 25–29 January, 1988.Google Scholar
  14. Weir, A.F. "Computer Vision for Real Time Industrial Applications", Proc. Computer Image Processing Symp., Chisholm Inst. of Techn., Melbourne, 16–18 July, 1985, pp. D-4.2 to D-4.7.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • D. R. Skinner
    • 1
  • K. K. Benke
    • 1
  1. 1.Department of DefenceMaterials Research LaboratoryAscot ValeAustralia

Personalised recommendations