Abstract
An algorithm for the recognition of planar shapes under affine distortion is presented. Shape description is based on the use of semi-differential invariants, combining coordinates and derivatives of contour points. The philosophy behind the use of these invariants is to find a tradeoff between two extreme strategies currently used in the literature: (invariant) feature extraction methods, involving high order derivatives, and invariant coordinate descriptions, leading to the correspondence problem of reference points. Accuracy is obtained due to the use of B-spline approximations for the descriptions of coordinates and derivatives of the contours. The recognition results on a set of 12 different objects are given.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
H. Bartels, C. Beatty, and A. Barsky, An introduction to splines for use in computer graphics and geometric modeling, Morgan Kaufmann, Los Altos, CA, 1987.
M. Costa, R. Haralick, T. Phillips, and L. Shapiro, Optimal affine-invariant point matching, SPIE Vol. 1095, Applications of Artificial Intelligence VII, pp.515–530, 1989.
D. Cyganski, J. Orr, T. Cott, and R. Dodson, Development, implementation, testing, and application of an affine transform invariant curvature function, Proc. 1st Int. Conf. on Computer Vision, pp.496-500, 1987.
H. Guggenheimer, Differential Geometry, Dover, NY, 1977.
Y. Lamdan, J. Schwartz, and H. Wolfson, On recognition of 3-D ojects from 2-D images, Proc. IEEE Internat. Conf. on Robotics and Automation, 1407-1413, 1988.
H. Mannaert, and A. Oosterlinck, A Recursive Self-Organizing Network for Object Recognition, Proc. Int. Joint Conf. on Neural Networks, pp. II 405-408, 1990.
S. Ullman, Aligning pictorial descriptions: an approach to object recognition, Cognition 32, pp. 193–254, 1989.
L. Van Gool, P. Kempenaers, and A. Oosterlinck, Recognition and semi-differential invariants, Proc. IEEE Internat. Conf. on Computer Vision and Pattern Recognition, Hawaï, 1991.
L. Van Gool, T. Moons, E. Pauwels, and A. Oosterlinck, Semi-differential invariants, DARPA/ESPRIT Workshop on Applications of Invariants in Computer Vision, pp. 359-386, 1991.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer Science+Business Media New York
About this chapter
Cite this chapter
Kempenaers, P., Van Gool, L., Oosterlinck, A. (1992). Shape Recognition Under Affine Distortions. In: Arcelli, C., Cordella, L.P., di Baja, G.S. (eds) Visual Form. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-0715-8_32
Download citation
DOI: https://doi.org/10.1007/978-1-4899-0715-8_32
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-0717-2
Online ISBN: 978-1-4899-0715-8
eBook Packages: Springer Book Archive