Integrating iconic and structured matching

  • R. B. Fisher
  • A. MacKirdy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1407)


Several investigations [11,16,19–21] have recently been undertaken into object recognition based on matching image intensity neighborhoods rather than geometric matching of features extracted from the images. These projects have used small subwindows or complete image regions and matching has been based on the similarity of extracted descriptors to previously stored descriptors. One characteristic common to these approaches is the representation of objects as a whole, rather than as a structured ensemble. This paper describes an extension to these approaches wherein a set of related features recognized at an earlier iteration also contribute to the complete object recognition. The paper describes an iconic, or image-based, matching approach that incorporates an element of geometric matching and shows that use of the subfeatures improves matching efficiency, position accuracy and completeness.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    DH Ballard and CM Brown. Computer Vision, Prentice-Hall, New Jersey, 1982.Google Scholar
  2. 2.
    J Ben-Arie and Z Wang. Pictorial recognition using affine-invariant spectral signatures. Proc. Int Conf on Comp. Vis. and Pat. Rec, pp 35–39, San Jose, Puerto Rico, 1997.Google Scholar
  3. 3.
    I Biederman. Recognition-by-components: A theory of human image understanding. Psychological Review. vol 4, pp 115–147, 1987.CrossRefGoogle Scholar
  4. 4.
    RA Brooks. Symbolic reasoning among 3D models and 2-D images. Artificial Intelligence Journal, vol 17, pp 285–348, 1981.CrossRefGoogle Scholar
  5. 5.
    JA Feldman. Four frames suffice: a provisional model of vision and space. Behavioral Brain Sciences Vol 8, pp 265–313, 1985.CrossRefGoogle Scholar
  6. 6.
    RB Fisher. From Surfaces to objects: Computer Vision and Three Dimensional Scene Analysis. John Wiley, UK, 1989.Google Scholar
  7. 7.
    RB Fisher. Hierarchical Matching Beats The Non-Wildcard and Interpretation Tree Model Matching Algorithms. Proc. 1993 British Machine Vision Association Conf., pp 589–598, Surrey, 1993.Google Scholar
  8. 8.
    D. A. Forsyth and M. M. Fleck. Identifying nude pictures. In IEEE Workshop on the Applic. of Comp. Vis. pp 103–108, 1996.Google Scholar
  9. 9.
    W. E. L. Grimson. Object Recognition By Computer: The Role of Geometric Constraints. MIT Press, 1990.Google Scholar
  10. 10.
    TD Grove. Attention directed iconic object matching. M.Sc. dissertation, Dept. of Artificial Intelligence, University of Edinburgh, 1995.Google Scholar
  11. 11.
    TD Grove, RB Fisher. Attention in Iconic Object Matching. Proc. British Machine Vision Conference BMVC96, Edinburgh, pp 293–302, September 1996.Google Scholar
  12. 12.
    A MacKirdy. Full Subcomponent Evidence and Further Parallelism in an Iconic Object Recognition System. BSc Honours Dissertation, Dept. of Artificial Intelligence, Univ. of Edinburgh, 1997.Google Scholar
  13. 13.
    D Marr. Vision. W.H. Freeman and Company, 1980.Google Scholar
  14. 14.
    K Messer, J Kittler, M Kraaijveld. Selecting features for neural networks to aid an iconic search through an image database. Proc. IEE 6th Int. Conf. on Image Proc and Its Applic, pp 428–432, 1997.Google Scholar
  15. 15.
    J Mundy, A Liu, N Pillow, A Zisserman, S Abdallah, S Utcke, S Nayar and C Rothwell. An experimental comparison of appearance and geometric model based recognition. in Proc. Int Workshop on Object Representations in Comp. Vis, 1996. In assoc. with ECCV 1996.Google Scholar
  16. 16.
    RPN Rao and DH Ballard. Object indexing using an iconic sparse distributed memory. Technical Report TR 559, Computer Science Dept., U. Rochester, 1995.Google Scholar
  17. 17.
    LG Roberts. Machine Perception of Three-Dimensional Solids, in Tippett, J.T. (ed.), Optical and Electro-Optical Information Processing, MIT Press, Ch. 9, Cambridge, Massachusetts, pp 159–197, 1965.Google Scholar
  18. 18.
    G Sandini and M Tistarelli. Vision and Space-Variant Sensing. In (ed. H. Wechsler), Neural Networks for Perception, Vol 1: Human and Machine Perception, Academic Press, Ch II.9, pp 398–425, 1992.Google Scholar
  19. 19.
    B Schiele and JL Crowley. Object Recognition Using Multidimensional Receptive Field Histograms. Proc. 1996 Eur. Conf. on Comp. Vision, Vol 2, pp 610–619, 1996.Google Scholar
  20. 20.
    M Seibert and AM Waxman. Learning and Recognizing 3D Objects from Multiple Views in a Neural System. in (ed. H. Wechsler), Neural Networks for Perception, Vol 1: Human and Machine Perception, Academic Press, Ch II.12, pp 426–444, 1992.Google Scholar
  21. 21.
    JP Siebert and I Eising. Scale-space recognition based on the retino-cortical transform. Proc. IEE Conf on Image Processing and its Applications, Edinburgh, 1995.Google Scholar
  22. 22.
    J van der Spiegel, G Kreider, C Claeys, I Debusschere, G Sandini, P Dario, F Fantini, P Belluti, and G Soncini. A foveated retina-like sensor using CCD technology. In C. Mead and M. Ismail, editors, Analog VLSI Implementation of Neural Systems, Ch 8. pp 189–212. Kluwer Academic Publishers, Boston, 1989.Google Scholar
  23. 23.
    M Tistarelli. Active/Space-Variant Object Recognition. Image and Vision Computing, Vol. 13. No 3, pp 215–226, 1995.CrossRefGoogle Scholar
  24. 24.
    MA Turk and AP Pentland. Eigenfaces for Recognition. J. Cognitive Neuroscience, vol 3 no 1, pp 71–86, 1991.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • R. B. Fisher
    • 1
  • A. MacKirdy
    • 1
  1. 1.Department of Artificial IntelligenceEdinburgh UniversityEdinburghScotland, UK

Personalised recommendations