Skip to main content
Log in

Similarity-invariant signatures for partially occluded planar shapes

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

Abstract

A methodology is described for associating local invariant signature functions to smooth planar curves in order to enable their translation, rotation, and scale-invariant recognition from arbitrarily clipped portions. The suggested framework incorporates previous approaches, based on locating inflections, curvature extrema, breakpoints, and other singular points on planar object boundaries, and provides a systematic way of deriving novel invariant signature functions based on curvature or cumulative turn angle of curves. These new signatures allow the specification of arbitrarily dense feature points on smooth curves, whose locations are invariant under similarity transformations. The results are useful for detecting and recognizing partially occluded planar objects, a key task in low-level robot vision.

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

Access this article

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

Instant access to the full article PDF.

Similar content being viewed by others

References

  • Asada, H., and Brady, M. 1986. The curvature primal sketch. IEEE Trans. Patt. Anal. Mach. Intell., PAMI 8: 2–14.

    Google Scholar 

  • Ballard, D.H. 1981. Generalizing the Hough transform to detect arbitrary shapes. Patt. Recog., 13(2): 111–122.

    Google Scholar 

  • Barrett, E.B., Payton, P., and Brill, M.H. 1991. Contributions to the theory of projective invariants for curves in two and three dimensions. Proc. DARPA/ESPRIT Workshop on Invariants in Vision, Reykjavik, Iceland, March.

  • Bruckstein, A.M., Holt, R.J., Netravali, A.N., and Richardson, T.J. 1991. Invariant signatures for planar shape recognition under partial occlusion, AT&T Bell Labs Tech. Memo, Murray Hill, NJ, October.

    Google Scholar 

  • Bruckstein, A.M., and Netravali, A.N. 1990. On differential invariants of planar curves and recognizing partially occluded planar shapes. AT&T Bell Laboratories Tech. Memo, Murray-Hill, NJ, July; also in Proc. Workshop on Visual Form, Capri, May, 1991.

    Google Scholar 

  • Cyganski, D., Orr, J.A., Cott, T.A., and Dodson, R.J. 1987. An affine transform invariant curvature function. Proc. Ist Intern. Conf. Comput. Vis., London, pp. 496–500.

  • Fischler, M.A., and Bolles, R.C. 1986. Perceptual organization and curve partitioning, IEEE Trans. Patt. Anal. Mach. Intell., PAMI 8: 100–105.

    Google Scholar 

  • Guggenheimer, H.W. (1963). Differential Geometry. McGraw Hill, New York; Dover: New York.

    Google Scholar 

  • Gottschalk, P.G., Turney, J.L., and Mudge, T.N.. 1989. Effeient recognition of partially visible objects using a logarithmic complexity matching technique. Intern. J. Robotics Res., 8(6): 110–131.

    Google Scholar 

  • Gottschalk, P.G., and Mudge, T.N. 1988. Efficient encoding of local shape. Proc. SPIE, Intell. Robots Comput. Vis., 7: 46–56.

    Google Scholar 

  • Hu, M.K., 1962. Visual pattern recognition by moment invariants. IRE Trans. Inform. Theory, IT 8: 179–187.

    Google Scholar 

  • Huttenlocher, D.P., and Ullman, S. 1987. Object recognition using alignment. Proc. lst Intern. Conf. Comput. Vis., London, pp. 102–111.

  • Hong, J., and Wolfson, H. 1988. An improved model-based matching method using footprints. Proc. Intern. Conf. Patt. Recog., Rome, pp. 72–78.

  • Koenderink, J.J. 1990. Solid Shape. MIT Press: Cambridge, MA.

    Google Scholar 

  • Katzir, N., Lindenbaum, M., and Porat, M. 1990. Planar curve segmentation for recognition of partially occluded shapes. Proc. 10th Intern. Conf. Patt. Recog., Atlantic City.

  • Kalvin, A., Schonberg, E., Schwartz, J.T. and Sharir, M. 1986. Two-dimensional model-based boundary matching using footprints. Intern. J. Robotics Res., 5(4): 38–55.

    Google Scholar 

  • Lamdan, Y., and Wolfson, H.J. 1988. Geometric hashing: A general and efficient model-based recognition scheme. Proc. 2nd Intern. Conf. Comput. Vis., Tarpon Springs, Florida, pp. 238–249.

  • Ray, K.S., and Majumder, D. Dutta. 1989. Application of differential geometry to recognize and locate partially occluded objects. Patt. Recog. Lett., 9: 351–360.

    Google Scholar 

  • Turney, J.L., Mudge, T.N., and Volz, R.A. 1985. Recognizing partially occluded parts. IEEE Trans. Patt. Anal. Mach. Intell., PAMI (7)4: 410–421.

    Google Scholar 

  • Vaz, R.F., and Cyganski, D. 1990. Generation of affine invariant local contour feature data. Patt. Recog. Lett., 11: 479–483, July.

    Google Scholar 

  • VanGool, L., Kempenaers, P., and Oosterlinck, A. 1991. Recognition and semi-differential invariants. Intern. Conf. Patt. Recog., Maui, Hawaii, June.

  • VanGool, L., Moons, T., Pauwels, R., and Oosterlinck, A. 1991. Semi-differential invariants. DARPA/ESPRIT Workshop on Invariants in Vision, Reykjavik, Iceland, March.

  • Weiss, I. 1988. Projective invariants of shapes, CAR Tech. Rept. TR-339, University of Maryland, January.

  • Weiss, I. 1991. Noise resistant invariants of curves. CAR Tech. Rept. TR-537, February; also Proc. DARPA/ESPRIT Workshop on Invariants in Vision, Reykjavik, Iceland, March 1991.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bruckstein, A.M., Katzir, N., Lindenbaum, M. et al. Similarity-invariant signatures for partially occluded planar shapes. Int J Comput Vision 7, 271–285 (1992). https://doi.org/10.1007/BF00126396

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00126396

Keywords

Navigation