Abstract
A new method for the fast recognition of two-dimensional wire-shapes is presented. Both the rigid and the non-rigid case are explored. The proposed approach is based on a characterization of the skeleton of the shape in terms of a set of two topological robust features: terminal points (TPs), i.e. points with just one neighbor and three-edge-points (TEPs), i.e points with only three neighbors. The number of TPs and TEPs in the skeleton are used as inputs to look up the object's database for the fast recognition of the shape. The proposed technique profits the advantages of the Fast Distance Transformation (FDT) to obtain rapidly the skeleton. These two characteristics make of the proposed approach a fast and simple method for the fast recognition of 2D binary objects, which is desired for real time applications.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This research was supported by the National Council of Science and Technology of México and the Mexican Institute of Communications.
Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
J. L. Díaz-de-León S. Skeletonization algorithms for binary images. Master's thesis, CINVESTAV — IPN, Depto. de Ing. Eléctrica, Secc. de Control Automático, August 1993. In Spanish.
J. L. Díaz-de-León S. and J. H. Sossa. On the computation of the euler number of a binary object. Pattern Recognition, 29(3):471–476, 1996.
J. Boyce and W. Hossack. Moment invariants for pattern recognition. Pattern Recognition Letters, 1:451–456, 1983.
M. Hu. Visual pattern recognition by moment invariant. IRE Transaction on Information Theory, 12:179–187, 1962.
T. Knoll and R. Jain. Recognizing partially visible objects using feature indexed hypothesesoccluded parts. IEEE J. of Robotics and Automation, 2(1):3–13, 1986.
Z. Mingfa and S. Hasani, S. Bhattarai, and H. Sing. Pattren recognition with moment invariants on a machine vision system. Pattern Recognition Letters, 9:175–180, 1989.
E. Persoon and K. S. Fu. Shape discrimination using fourier descriptors. IEEE Trans. Syst. Man, Cybern., 7:170–179, 1977.
A. Rosenfeld and A. Kak. Digital Picture Processing. Academic Press, New York, 1976.
D. Rutovitz. Pattern recognition. I. Royal Statist. Soc., 129:504–530, 1966.
H. Tamura. A comparison of line thinning algorithms from a digital geometry viewpoint. In 4th. Int. Conf. on Patt. Recog., pages 715–719, 1978.
J. Turney, T. Mudge, and R. Voltz. Recognizing partially occluded parts. IEEE Trans. Patt. Anal. and Mach. Intell., 7:410–421, 1985.
H. Yang and S. Sengupta. Intelligent shape recognition for complex industrial tasks. IEEE Control Systems Magazine, 23–29, June 1988.
S. Yokoi, J. Toriwaki, and T. Fukumura. An analysis of topological properties in digitized binary pictures. CGIP, 4:63–73, 1975.
C. Zhan and R. Roskies. Fourier descriptors for plane closed curves. IEEE Transaction on Computers, 21:269–280, 1972.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sossa, J.H.A., Díaz-de-León, J.S.L. (1996). Recognizing 2-D rigid and non-rigid wire-shapes. In: Perner, P., Wang, P., Rosenfeld, A. (eds) Advances in Structural and Syntactical Pattern Recognition. SSPR 1996. Lecture Notes in Computer Science, vol 1121. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61577-6_31
Download citation
DOI: https://doi.org/10.1007/3-540-61577-6_31
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61577-4
Online ISBN: 978-3-540-70631-1
eBook Packages: Springer Book Archive