Abstract
Size functions are integer valued functions of two real variables which have been recently proposed for the representation and recognition of shape. A main limitation of the theory of size functions appeared to be the fragility of the produced representation with respect to edge fragmentation. In this paper it is shown that size functions can actually be defined without making assumptions on the topological structure of the viewed shape. Consequently, size functions can be profitably used even in the presence of fragmented edge maps. In order to demonstrate the potential of size functions for computer vision, a system for shape recognition is described and tested on two different domains. The very good performances of the system indicate that size functions are extremely effective for the analysis of shapes for which geometric models might be difficult to obtain.
Similar content being viewed by others
References
Ayache, N. and Faugeras, O. D. 1986. HYPER: A new approach for the recognition and positioning of two-dimensional objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(1):44-54.
Forsyth, D. A., Mundy, J. L., Zisserman, A., Coelho, C., Heller, A., and Rothwell, C. A. 1991. Invariant descriptors for 3D object recognition and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(10):971-991.
Frosini, P. 1990. A distance for similarity classes of submanifolds of a euclidean space. Bull Austral Math Soc., 42:407-416.
Frosini, P. 1991. Measuring shapes by size functions. Proc. of SPIE on Intelligent Robotic Systems, Boston, vol. 1607, pp. 122- 133.
Frosini, P. 1992. Discrete computation of size functions. Journal of Combinatorics and Information System Science, 17(3-4):232- 250.
Grimson, W. E. L. and Lozano-Perez, T. 1984. Model-based recognition and localization from sparse range and tactile data. International Journal of Robotics Research, 3(3):3-35.
Grimson, W. E. L. and Lozano-Perez, T. 1987. Localizing overlapping parts by searching the interpretation tree. IEEE Transactions on Pattern Analysis and Machine Intelligence, 9(4):469- 482.
Huttenlocher, D. P. 1989. Three-dimensional recognition of solid objects from a two-dimensional image. A. I. Memo No. 1045, AI Lab, MIT.
Huttenlocher, D. P., Klanderman, G. A., and Rucklidge, W. J. 1993. Comparing images using the hausdorff distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(9):850-863.
Lowe, D. G. 1987. Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence, 31(3):355-395.
Teague, M. R. 1980. Image analysis via the general theory of moments. J. Opt. Soc. Am., 70(8):920-930.
Ullman, S. 1987. An approach to object recognition: Aligning pictorial descriptions. A. I. Memo No. 931, AI Lab, MIT.
Uras, C. and Verri, A. 1994a. Studying shape through size functions. In Shape in Picture, Y. O., A. Toet, D. Foster, H. Heijmans, and P. Meer (Eds.), NATO ASI Series F, vol. 126, Springer-Verlag, Berlin Heidelberg, pp. 81-90.
Uras, C. and Verri, A. 1994b. On the recognition of the alphabet of the sign language through size functions. Proc. Intl. Conf. on Pattern Recognition, Jerusalem, vol. II, pp. 334-338.
Verri, A., Uras, C., Frosini, P., and Ferri, M. 1993. On the use of size functions for shape analysis. Biological Cybernetics, 70(2):99- 107.
Verri, A. and Uras, C. 1994. Invariant size functions. In Applications of Invariance in Computer Vision, J. L. Mundy, A. Zisserman, and D. Forsyth (Eds.), Lecture Notes in Computer Science 825, Springer Verlag, Berlin Heidelberg, pp. 215-234.
Verri, A. and Uras, C. 1996. A metric-topological approach to shape representation and recognition (submitted to Image and Vision Computing, 14:189-207).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Uras, C., Verri, A. Computing Size Functions from Edge Maps. International Journal of Computer Vision 23, 169–183 (1997). https://doi.org/10.1023/A:1007910913691
Issue Date:
DOI: https://doi.org/10.1023/A:1007910913691