International Journal of Computer Vision

, Volume 2, Issue 2, pp 125–151 | Cite as

A framework for object recognition in a visually complex environment and its application to locating address blocks on mail pieces

  • Ching-Huei Wang
  • Sargur N. Srihari


A computational framework for recognizing an object of interest in a complex visual environment is described. Arising from the problem of finding the destination address block on a mail piece, a general framework for coordinating a collection of specialized image-analysis tools is described. The resulting system is capable of dealing with a wide range of environments—from those having a high degree of global spatial structure (e.g., letter mail envelopes that conform to specifications) to those with no structure (e.g., magazines with randomly pasted address labels). The problem-solving architecture accounts for uncertainty in the imaging environment by using the blackboard model. This paper discusses systematic derivation of a set of object recognition heuristics (knowledge base), specialized image analysis tools for extracting those features that are called for by the heuristics, and a control structure for integrating evidence and managing tools. Experimental results with a database of difficult cases demonstrating the promise of the methodology are presented.


Object Recognition Complex Environment Difficult Case Specialized Image Computational Framework 
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.
    D.H., Ballard, C.M., Brown, and J.A., Feldman, “An approach to knowledge-directed image analysis”. In Computer Vision Systems, A., Hanson and E., Riseman (eds.), Academic Press: New York, pp. 271–281, 1978.Google Scholar
  2. 2.
    J.A. Barnett, “Computational methods for a mathematical theory of evidence”, Proc. 7th Int. Joint Conf. Artif. Intell., Vancouver, pp. 868–875, 1981.Google Scholar
  3. 3.
    T.O., Binford, “Survey of model-based image analysis systems”. Int. J. Robotics Res., 1(1), pp. 18–62, 1982.Google Scholar
  4. 4.
    R.A., Brooks, Model-Based Computer Vision, UMI Research Press: Ann Arbor, MI, 1984.Google Scholar
  5. 5.
    R.A., Brooks, “Symbolic reasoning among 3-D models and 2-D images”, Artifical Intelligence 17, pp. 285–348, August 1981.Google Scholar
  6. 6.
    M. Caviglione, G. Musso, and B. Ortolani, “An advanced approach to the address block finding problem”, Proc. USPS Advanc. Technology Conf., Washington DC, pp. 85–103, October 1986.Google Scholar
  7. 7.
    L.D., Erman, F., Hayes-Roth, V.R., Lesser, and D.R., Reddy, “The Hearsay-II Speech-Understanding System: Integrating knowledge to resolve uncertainty”, Computing Surveys 12(2), pp. 213–253, 1980.Google Scholar
  8. 8.
    C.L. Forgy, OPS5 User's Manual, Dept. of Computer Science, Carnegie-Mellon University, 1981.Google Scholar
  9. 9.
    GTRI, Automated Processing of Irregular Parcel Post: IPP, Letter, and Flat Statistical Database, Electronics and Computer Systems Lab. Georgia Tech Res. Inst., 1985–1986.Google Scholar
  10. 10.
    T.D. Garvey, J.D. Lowrence, and M.A. Fischler, “A inference technique for integrating knowledge from disparate sources”, Proc. 7th Int. Joint Conf. Artif. Intell., Vancouver, pp. 319–325, 1981.Google Scholar
  11. 11.
    A.R., Hanson and E.M., Riseman, “VISIONS: A computer system for interpreting scenes”. In Computer Vision Systems, A., Hanson and E., Riseman (eds.), Academic Press: New York, pp. 303–333, 1978.Google Scholar
  12. 12.
    J.J. Hull, G. Krishnan, P. Palumbo, and S.N. Srihari, “Optical character recognition techniques in mail sorting: A review of algorithms”. Tech. Rept. 214, Dept. of Computer Science, State Univ. of New York at Buffalo, June 1984.Google Scholar
  13. 13.
    A.F. Lehar, “The automatic detection and ranking of address blocks in unconstrained mail”, Proc. USPS Advanc. Technology Conf., Washington DC, pp. 132–146, October 1986.Google Scholar
  14. 14.
    M.D., Levine and S.I., Shaheen, “A modular computer vision system for picture segmentation and interpretation”, IEEE Trans. PAMI-3, 5, pp. 540–556, September 1981.Google Scholar
  15. 15.
    A. Litcher, S. Antoy, P.S. Yeh, and A. Rosenfeld, “A rulebased based system for address recognition”. Proc. USPS Advanc. Technology Conf., Washington DC, pp. 66–84, October 1986.Google Scholar
  16. 16.
    T. Matsuyama and V. Hwang, “SIGMA: A framework for image understanding—Integration of bottom-up and topdown analysis”, Proc. Int. Joint Conf. Artific. Intell., Los Angeles, pp. 908–915, August 1985.Google Scholar
  17. 17.
    D.M.J., McKeown, W.A., Harvey, and J., McDermott, “Rule-based interpretation of aerial imagery”. IEEE Trans. PAMI-7, 5, pp. 570–585, September 1985.Google Scholar
  18. 18.
    P.G. Mulgaonkar and A. Bergman, “Address block location: The SRI approach”, Proc. USPS Advanc. Technology Conf., Washington DC, pp. 161–178, October 1986.Google Scholar
  19. 19.
    M., Nagao and T., Matsuyama, A Structural Analysis of Complex Aerial Photographs. Plenum Press: New York, 1980.Google Scholar
  20. 20.
    H.P., Nii, “Part One, Blackboard systems: The blackboard model of problem solving and the evolution of black-board architectures”. AI Magazine 7(2), pp. 38–53, Summer 1986.Google Scholar
  21. 21.
    Y., Ohta, Knowledge-Based Interpretation of Outdoor Natural Scenes. Pitman Publishing: Marshfield MA, 1985.Google Scholar
  22. 22.
    J.E. Orrock, J. Jelinek, and K. Schaper, “A system for automatic address block location”, Proc. USPS Advanc. Technology Conf., Washington DC, pp. 104–115, October 1986.Google Scholar
  23. 23.
    G. Shafer, A Mathematical Theory of Evidence. Princeton University Press, 1976.Google Scholar
  24. 24.
    L.G. Shapiro, “The role of AI in computer vision”, Proc. 2nd IEEE Computer Soc. Conf. Artif. Intell. Applications, Miami Beach, FL, pp. 76–81, December 1985.Google Scholar
  25. 25.
    S.N., Srihari, C.H., Wang, P.W., Palumbo, and J.J., Hull, “Recognizing address blocks on mail pleces: Specialized tools and problem solving architecture”. AI magazine 8(4), pp. 25–40, Winter 1987.Google Scholar
  26. 26.
    S.N. Srihari, J.J. Hull, P.W. Palumbo, and C.H. Wang, “Address block location: Evaluation of image and statistical database”, Tech. Rept. 86-09, Dept. of Computer Science, SUNY at Buffalo, April 1986.Google Scholar
  27. 27.
    USPS, Engineering Report on OCR Readability Guidelines, June 1984.Google Scholar
  28. 28.
    C.H. Wang and S.N. Srihari, “Object recognition in structured andrandom environments:Locating address blocks on mail pieces”, Proc. 5th AAAI Nat. Conf., Philadephia, pp. 1133–1137, August 1986.Google Scholar
  29. 29.
    L.P. Wesley and A.R. Hanson, “The use of an evidential-based model for representing knowledge and reasoning about images in the visions system”. Proc. of the Workshop on Computer Vision: Representation and Control, Rindge, New Hampshire, pp. 14–25, August 1982.Google Scholar
  30. 30.
    P.S., Yeh, S., Antoy, A., Litcher, and A., Rosenfeld, “Address location on envelopes”, Pattern Recognition 20(2), pp. 213–217, 1987.Google Scholar

Copyright information

© Kluwer Academic Publishers 1988

Authors and Affiliations

  • Ching-Huei Wang
    • 1
  • Sargur N. Srihari
    • 1
  1. 1.Department of Computer ScienceState University of New York at BuffaloBuffalo

Personalised recommendations