Automatic Recognition of Complex Three-Dimensional Objects from Optical Images

  • Robert B. McGhee


The possibility of duplicating in a machine the ability of animals and man to interpret visual information has intrigued many investigators. While this problem has been treated with considerable success relative to automatic classification of two-dimensional objects, especially with regard to recognition of printed characters, comparatively little has been achieved in automatic identification of three-dimensional objects. Generally speaking, such successes as have been attained in the latter area can be grouped under two broad headings: 1) scene analysis in which various specialized procedures are used to determine spatial relationships between simple objects such as solid polyhedra, cylinders, cones, etc., and 2) statistical pattern recognition in which certain numerical features of an image of an unknown object are used to classify it and perhaps to estimate its position and orientation [1]. This paper is addressed entirely to the second approach and is concerned with recognition of complex man- made objects rather than natural objects or simple solids.


Optical Image Recognition Accuracy Character Recognition Bend Function Automatic Recognition 
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.
    Duda, R.O., and Hart, P.E., Pattern Classification and Scene Analysis, John Wiley & Sons, New York, 1973.Google Scholar
  2. 2.
    Cosgriff, R.L., Identification of Shape, Report No. 820–11, The Ohio State University Research Foundation, Columbus, Ohio, ASTIA AD-254 792, December 1960.Google Scholar
  3. 3.
    Pugh, A., Heginbotham, W.B., and Kitchin, P.W., “Visual Feedback Applied to Programmable Assembly Machines,” Proceedings of 2nd International Symposium on Industrial Robots, Chicago, Ill., May, 1972, pp. 77–88.Google Scholar
  4. 4.
    Rosenfeld, A., Picture Processing by Computer, Academic Press, New York, 1969.Google Scholar
  5. 5.
    Hall, E.L., et al., “A Survey of Preprocessing and Feature Extraction Techniques for Radiographic Images,” IEEE Trans. on Computers, Vol. C-20, No. 9, pp. 1032–1044, September 1971.CrossRefGoogle Scholar
  6. 6.
    Sklansky, J., and Davidson, G.A., “Recognizing Three-Dimensional Objects by Their Silhouettes,” J. Soc. Photo-Opt. Instrum. Eng., Vol. 10, pp. 10–17, October 1971.Google Scholar
  7. 7.
    Levine, M.D., “Feature Extraction: A Survey,” Proc. of the IEEE, Vol. 50, No. 8, pp. 1391–1407, August 1969.CrossRefGoogle Scholar
  8. 8.
    Nagy, G., “State of the Art in Pattern Recognition,” Proc. of IEEE, Vol. 26, No. 5, May 1968.Google Scholar
  9. 9.
    Watanabe, S., Frontiers of Pattern Recognition, Academic Press, New York, 1972.Google Scholar
  10. 10.
    Brill, E.L., “Character Recognition via Fourier Descriptors,” in Qualitative Pattern Recognition Through Image Shaping, preprints of WESCON Session 25, Los Angeles, August 1968.Google Scholar
  11. 11.
    Zahn, C.T., and Roskies, R.Z., “Fourier Descriptors for Plane Closed Curves,” IEEE Trans, on Computers, Vol. C-21, No. 3, pp. 269–281, March 1972.CrossRefGoogle Scholar
  12. 12.
    Dudani, S.A., Moment Methods for the Identification of Three- Dimensional Objects from Optical Images, M.S. thesis, The Ohio State University, Columbus, Ohio, August 1971.Google Scholar
  13. 13.
    Pio, R.L., “Euler Angle Transformations,” IEEE Trans, on Automatic Control, Vol. AC-11, No. 4, pp. 707–715, Oct. 1966.CrossRefGoogle Scholar
  14. 14.
    Cosgriff, R.L., An Investigation of Techniques for Recognition of Script Numeric Characters, Research Proposal No. 67–14, The Ohio State University Research Foundation, Columbus, Ohio, July 1966.Google Scholar
  15. Richard, C.W., and Hemami, H., “Identification of Three-Dimensional Objects using Fourier Descriptors of the Boundary Curve,” Proc. of 1972 Symposium on Computer Image Processing and Recognition, Vol. 2, University of Missouri at Columbia, August 1972, pp. 15–2–1 to 15–2–13.Google Scholar
  16. 16.
    Sutherland, I.E., “Computer Displays,” Scientific American, June 1970, pp. 57–81.Google Scholar
  17. 17.
    Advani, J.G., Computer Recognition of Three-Dimensional Objects from Optical Images, Ph.D. dissertation, The Ohio State University, Columbus, Ohio, August 1971.Google Scholar
  18. 18.
    Hemami, H., McGhee, R.B., and Gardner, S.R., “Towards a Generalized Template Matching Algorithm for Pictorial Pattern Recognition,” Proc. of the 1970 IEEE Symposium on Adaptive Processes, Dec. 1970.Google Scholar
  19. 19.
    Sklansky, J., and Nahin, P.J., “A Parallel Mechanism for Describing Silhouettes,” IEEE Trans, on Computers, Vol. C-21, No. 11, pp. 1233–1239, November 1972.CrossRefGoogle Scholar
  20. 20.
    Davidson, G.A., Johnson, V.M., and Sklansky, J., Optical Feature Extraction Technique, Report AFAL-TR-70–133, Aerojet- General Corporation, Azusa, Calif., July 1970.Google Scholar
  21. 21.
    Hu, M.K., “Visual Pattern Recognition by Moment Invariants,” IRE Trans, on Information Theory, Vol. IT-8, pp. 179–187, February 1962.Google Scholar
  22. 22.
    Dudani, S.A., An Experimental Study of Moment Methods for Automatic Identification of Three-Dimensional Objects from Television Images, Ph.D. dissertation, The Ohio State University, Columbus, Ohio, August 1973.Google Scholar
  23. 23.
    Breeding, K.J., and Miller, P.E., A Symmetrical Rectangular Array Processor and Its Simulation, Technical Note No. 15, Communication and Control Systems Laboratory, The Ohio State University, Columbus, Ohio, October 1973.Google Scholar

Copyright information

© Plenum Press, New York 1974

Authors and Affiliations

  • Robert B. McGhee
    • 1
  1. 1.Ohio State UniversityColumbusUSA

Personalised recommendations