Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Recognition, Resolution, and Complexity of Objects Subject to Affine Transformations

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

The problem of recognizing objects subject to affine transformation in images is examined from a physical perspective using the theory of statistical estimation. Focusing first on objects that occlude zero-mean scenes with additive noise, we derive the Cramer-Rao lower bound on the mean-square error in an estimate of the six-dimensional parameter vector that describes an object subject to affine transformation and so generalize the bound on one-dimensional position error previously obtained in radar and sonar pattern recognition. We then derive two useful descriptors from the object's Fisher information that are independent of noise level. The first is a generalized coherence scale that has great practical value because it corresponds to the width of the object's autocorrelation peak under affine transformation and so provides a physical measure of the extent to which an object can be resolved under affine parameterization. The second is a scalar measure of an object's complexity that is invariant under affine transformation and can be used to quantitatively describe the ambiguity level of a general 6-dimensional affine recognition problem. This measure of complexity has a strong inverse relationship to the level of recognition ambiguity. We then develop a method for recognizing objects subject to affine transformation imaged in thousands of complex real-world scenes. Our method exploits the resolution gain made available by the brightness contrast between the object perimeter and the scene it partially occludes. The level of recognition ambiguity is shown to decrease exponentially with increasing object and scene complexity. Ambiguity is then avoided by conditioning the permissible range of template complexity above a priori thresholds. Our method is statistically optimal for recognizing objects that occlude scenes with zero-mean background.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • Ballard, D.H. and Brown, C.M. 1982. Computer Vision. Prentice-Hall: Englewood Cliffs, NJ.

    Google Scholar 

  • Betke, M. and Gurvits, L. 1997. Mobile robot localization using landmarks. IEEE Trans. Robotics and Automation, 13:251-263.

    Google Scholar 

  • Betke, M. and Makris, N.C. 1995. Fast object recognition in noisy images using simulated annealing. In Proceedings of the Fifth International Conference on Computer Vision, Cambridge, MA, June 1995. IEEE Computer Society: Los Alamitos, CA, pp. 523-530.

    Google Scholar 

  • Betke, M. and Makris, N.C. 1997. Information-conserving object recognition. Technical Report CAR-TR-858, CS-TR-3799, University of Maryland.

  • Betke, M. and Makris, N.C. 1998. Information-conserving object recognition. In Proceedings of the Sixth International Conference on Computer Vision, Mumbai, India, January 1998. IEEE Computer Society: Los Alamitos, CA, pp. 145-152.

    Google Scholar 

  • Cernuschi-Frias, B., Cooper, D.B., Hung, Y.-P., and Belhumeur, P.N. 1989. Toward a model-based Bayesian theory for estimating and recognizing parameterized 3-D objects using two or more images taken from different positions. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11:540-564.

    Google Scholar 

  • Chin, R.T. and Dyer, C.R. 1986. Model-based recognition in robot vision. Computing Surveys, 18(1):67-108.

    Article  Google Scholar 

  • Difranco, J.V. and Rubin, W.L. 1968. Radar Detection. Prentice-Hall: Englewood Cliffs, NJ.

    Google Scholar 

  • Downie, J.D. and Walkup, J.F. 1994. Optimal correlation filters for images with signal-dependent noise. Journal of the Optical Society of America A 11:1599-1609.

    Google Scholar 

  • Friedland, N.S. and Rosenfeld, A. 1991. Lobed object delineation using a multipolar representation. Technical Report 2779, University of Maryland.

  • Gabor, D. 1946. Theory of communication. J. Inst. Electri. Eng., 93:429-457.

    Google Scholar 

  • Goodman, J.W. 1965. Some effects of target induced scintillation on optical radar performance. In Proceedings of the IEEE, 53:1688-1700.

    Google Scholar 

  • Goodman, J.W. 1985. Statistical Optics. Wiley: New York.

    Google Scholar 

  • Horn, B.K.P. 1986. Robot Vision. MIT Press: Cambridge, MA.

    Google Scholar 

  • Jain, R., Kasturi, R., and Schunk, B. 1995. Machine Vision. McGraw Hill: New York.

    Google Scholar 

  • Kashioka, S., Ejiri, M., and Sakamoto, Y. 1976. A transistor wire-bonding system utilizing multiple local pattern matching techniques. IEEE Transactions on Systems, Man and Cybernetics, 6(8):562-569.

    Google Scholar 

  • Kay, S.M. 1993. Statistical Signal Processing. Prentice Hall: Englewood Cliffs.

    Google Scholar 

  • Kelley, R.B., Martins, H.A.S., Birk, J.R., and Dessimoz, J.-D. 1983. Three vision algorithms for acquiring workpieces from bins. Proceedings of the IEEE, 71(7):803-820.

    Google Scholar 

  • Kirkpatrick, S., Gelatt, C.D., and Vecchi, M.P. 1983. Optimization by simulated annealing. Science, 220:671-680.

    Google Scholar 

  • Levanon, N. 1988. Radar Principles. John Wiley and Sons: New York.

    Google Scholar 

  • Makris, N.C. 1995. A foundation for logarithmic measures of fluctuating intensity in pattern recognition. Optics Letters,20:2012-2014.

    Google Scholar 

  • Makris, N.C. 1996. The effect of saturated transmission scintillation on ocean acoustic intensity measurements. Journal of the Acoustical Society of America, 100(2):769-783.

    Google Scholar 

  • Makris, N.C., Avelino, L.Z., and Menis, R. 1995. Deterministic reverberation from ocean ridges. Journal of the Acoustical Society of America, 97(6):3546-3574.

    Google Scholar 

  • Metropolis, N., Rosenbluth, A.W., Rosenbluth, M.N., Teller, A.H., and Teller, E. 1953. Equations of state calculations by fast computing machines. 1953. J. Chem. Physics, C-21:734-738.

    Google Scholar 

  • Poynton, C. 1993. “Gamma” and its disguises: The nonlinear mappings of intensity in perception, CRTs, film and video. J. SMPTE, 102:1099-1108.

    Google Scholar 

  • Rao, C.R. 1973. Linear Statistical Inference and its Applications, 2nd ed. Wiley and Sons: New York.

    Google Scholar 

  • Rosenfeld, A. and Kak, A.C. 1982. Digital Picture Processing, 2nd ed. Academic Press: New York, Vol. 2.

    Google Scholar 

  • Strang, G. 1976. Linear Algebra and its Applications. Academic Press: San Diego.

    Google Scholar 

  • Strenski, P.N. and Kirkpatrick, S. 1991. Analysis of finite length annealing schedules. Algorithmica, 6:346-366.

    Google Scholar 

  • Szu, H. and Hartley, R. 1987. Fast simulated annealing. Physics Letters A, 122:157-162.

    Google Scholar 

  • Trucco, E. and Verri, A. 1998. Introductory Techniques for 3-D Computer Vision. Prentice Hall: New York.

    Google Scholar 

  • Umbaugh, S. 1998. Computer Vision and Image Processing. Prentice Hall: Englewood Cliffs, NJ.

    Google Scholar 

  • Van, H.L. Trees. 1968. Detection, Estimation, and Modulation Theory, Part I. Wiley: New York.

    Google Scholar 

  • Yoshimura, S. and Kanade, T. 1994. Fast template matching based on the normalized correlation by using multiresolution eigenimages. In Proceedings of the International Conference on Intelligent Robots and Systems, Munich, Germany, September 1994.

  • Zadeh, L.A. and Ragazzini, J.R. 1952. Optimum filters for the detection of signals in noise. In Proc. IRE, 40:1123-1131.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Boston University, Boston, MA, 02215

    Margrit Betke

  2. Massachusetts Institute of Technology, Cambridge, MA, 02139

    Nicholas C. Makris

Authors
  1. Margrit Betke
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nicholas C. Makris
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Betke, M., Makris, N.C. Recognition, Resolution, and Complexity of Objects Subject to Affine Transformations. International Journal of Computer Vision 44, 5–40 (2001). https://doi.org/10.1023/A:1011168302294

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1011168302294

Search

Navigation