Abstract
Methods for the recognition ofplanar shapes from arbitrary viewpoints are described. The adopted model of projection is orthographic. The invariant descriptions derived for this group are one-dimensional shape signatures comparable to the well-known curvature as a function of arc length description of Euclidean geometry. Since the use of such differential invariants in the affine case would lead to unacceptably high orders of derivatives, affine invariant descriptions based onsemi-differential invariants are proposed as an alternative. A systematic discussion of different types of these invariants is given. The usefulness and viability of this methodology is demonstrated on a database containing more than 40 objects.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bartels, H., Beatty, C., and Barsky, A. 1987.An introduction to splines for use in computer graphics and geometric modeling, Morgan Kaufmann: Los Altos, CA.
Bruckstein, A., and Netravali, A. 1990. On differential invariants of planar curves and recognizing partially occluded planar shapes, AT&T Technical Report.
Costa, M., Haralick, R., Phillips, T., and Shapiro, L. 1989. Optimal affine-invariant point matching, SPIE Vol. 1095,Applications of Artificial Intelligence VII, pp. 515–530.
Cyganski, D., Orr, J., Cott, T., and Dodson, R. 1987. Development, implementation, testing and application of an affine transform invariant curvature function. InProc. 1st Int. Conf. on Computer Vision, pp. 496–500.
Huttenlocher, D.P., and Ullman, S. 1987.Object recognition using Allignment. In:Proc. 1st Int. Conf. on Computer Vision, pp. 102–111.
Kempenaers, P., Van Gool, L., and Oosterlinck, A. 1991. Shape recognition under affine distortion. In: C. Arcelli, L. Cordelia, G. Sanniti di Baja, (eds.) Visual Form. Plenum: New York, pp. 323–332.
Lamdan, Y., Schwartz, J., and Wolfson, H. 1988. On recognition of 3-D ojects from 2-D images, InProc. IEEE Int. Conf. on Robotics and Automation, pp. 1407–1413.
Mannaert, H., and Oosterlinck, A. 1990. A Recursive Self-Organizing Network for Object Recognition. InProc. Int. Joint Conf. on Neural Networks, pp. II 405–408.
Moons, T., Pauwels, E.J., Van Gool, L.J., and Oosterlinck, A. 1995. “Foundations of Semi-differential Invariants,”Int. J. of Computer Vision, vol. 14, no. 1, pp. 49–65.
Olver, P.J. 1986.Applications of Lie groups to Differential Equations, Graduate Texts in Mathematics, Vol. 107, Springer-Verlag: Berlin/Heidelberg/New York/Tokyo.
Pauwels, E.J., Moons, T., Van Gool, L.J., Kempenaers, P., and Oosterlinck, A. Jan 1994. Recognition of Planar Shapes under Affine Distortion. Technical Report: KUL/ESAT/MI2/9405, ESAT, Kath. Univ. Leuven.
Rothwell, C.A., Zisserman, A., Forsyth, D.A., and Mundy, J.L. 1991. Using projective invariants for constant time library indexing in model based vision.Proc. BMVC91, pp. 62–70.
Sagle, A.A., and Walde, R.E. 1973. Introduction to Lie Groups and Lie Algebras. Pure and Applied Mathematics, Vol. 51. Academic Press: New York.
Van Gool, L., Kempenaers, P., and Oosterlinck, A. 1991. Recognition and semi-differential invariants. In IEEE Conf. on Computer Vision and Pattern Recognition, pp. 454–460.
Van Gool, L., Brill, M., Barrett, E., Moons, T., and Pauwels, E.J. 1992. Semi-differential invariants for nonplanar curves. In: J. Mundy and A. Zisserman, (eds.) Geometric Invariance in Computer Vision. MIT Press: Cambridge, Massachusetts/London, England Chapter 15: pp. 293–309.
Author information
Authors and Affiliations
Additional information
Post-doctoral Research Fellow of the Belgian National Fund for Scientific Research (N.F.W.O.).
Rights and permissions
About this article
Cite this article
Pauwels, E.J., Moons, T., Van Gool, L.J. et al. Recognition of planar shapes under affine distortion. Int J Comput Vision 14, 49–65 (1995). https://doi.org/10.1007/BF01421488
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01421488