Abstract
Size functions are integer valued functions of two real variables which represent metric and topological properties of visual shape. In this paper size functions invariant for transformations of increasing generality are presented and discussed. Experiments on synthetically generated and real images show that by means of size functions invariant for Euclidean, affine, or projective transformations it is possible to identify similar shapes and distinguish between different shapes independently of the observer viewpoint. Since size functions are inherently robust against small qualitative and quantitative changes in the apparent shape of the viewed objects, it is concluded that size functions can be useful for viewpoint invariant recognition of natural shapes.
This work has been partially funded by the EEC B.R.A. project VIVA.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Carlsson, S.: Projectively invariant decomposition and recognition of planar shapes. Proc. of the 4th Int. Conf. Comput. Vision. Berlin, Germany, (1993) 471–475.
Forsyth, D.A., Mundy, J.L., Zisserman, A., Coelho, C., Heller, A., Rothwell, C.A.: Invariant descriptors for 3D object recognition and pose. PAMI-13 10 (1991) 971–991.
Frosini, P.: A distance for similarity classes of submanifolds of a Euclidean space. Bull. Austral. Math. Soc. 42 (1990) 407–416.
Frosini, P.: Discrete computation of size functions. Journal of Combinatorics, Information and System Sciences, in press (1993)
Frosini, P.: Metric homotopies. Submitted for publication (1994).
Rothwell, C.A., Forsyth, D.A., Zisserman, A., Mundy, J.L.: Extracting projective structure from single perspective views of 3D point sets. Proc. of the 4th Int. Conf. Comput. Vision. Berlin, Germany, (1993) 573–582.
Uras, C., Verri, A.: Studying shape through size functions. In: O, Y., Toet, A., Foster, D., Heijmans, H., Meer, P. (eds.), Shape in Picture, NATO ASI Series F Vol. 126, Springer-Verlag, Berlin Heidelberg, (1994) pp. 81–90.
Uras, C., Verri, A.: On the recognition of the alphabet of the sign language through Size Functions. Submitted for publication (1994).
Van Gol, L.J., Moons, T., Pauwels, E.J., Oosterlinck, A.: Semi-differential invariants. In: Mundy, J., Zisserman, A. (eds.), Geometric Invariants in Computer Vision, MIT Press, Cambridge, Massachusetts, (1992) pp. 193–214.
Verri, A., Uras, C., Frosini, P., Ferri, M.: On the use of size functions for shape analysis. Biol. Cybern. 70 (1993) 99–107.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Verri, A., Uras, C. (1994). Invariant size functions. In: Mundy, J.L., Zisserman, A., Forsyth, D. (eds) Applications of Invariance in Computer Vision. AICV 1993. Lecture Notes in Computer Science, vol 825. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58240-1_12
Download citation
DOI: https://doi.org/10.1007/3-540-58240-1_12
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58240-3
Online ISBN: 978-3-540-48583-4
eBook Packages: Springer Book Archive