Abstract
Thinning or skeletonization can contribute tremendously to efficient feature extraction and classification. This paper describes a novel thinning procedure which decomposes a polygonal approximation of the inner and outer boundaries of a word image into a set of triangles. These triangles are classified into three types and replaced either by three lines at branches or by single lines to form a completely connected skeleton which is one pixel wide. The procedure also automatically generates a graph representation of the skeleton for use by subsequent analysis steps. The procedure has been tested on a variety of Arabic and English handwritten words and found to produce very few spurious features. The speed of this method does not depend strongly on the resolution of the digital image unlike commonly used thinning methods which iteratively remove layers from the boundary of words. In addition, it can be used for thinning any line-like patterns such as fingerprints, chromosomes and line drawings.
Preview
Unable to display preview. Download preview PDF.
References
Amin A., Al-Sadoun H., and Fischer S. Hand-printed Arabic character recognition system using an artificial network, Pattern Recognition 29(4), 663–675 (1996).
Fitz A. and Green R. Fingerprint pre-processing on a hexagonal grid, Proceedings of the 1995 European Convention on Security and Detection, pp. 257–260, Brighton, UK (May 1995).
DiezHiguera J., DiazPernas F. and LopezCoronado J. Neural network architecture for automatic chromosome analysis, Proceedings of SPIE — Applications of Artificial Neural Networks in Image Processing, pp. 85–94, CA, USA (February 1996).
Ye Q. and Danielsson P. Inspection of printed circuits boards by connectivity preserving shrinking, IEEE Trans. Pattern Anal. and Mach. Intell. 10(5), 737–743 (1988).
Blum H. “A transformation for extracting new descriptors of shape” in Models for the perception of speech and visual fonn, Wathen-Dune, W., ed., MIT Press, Cambridge, Mass (1967).
Lam L., Lee S., and Suen C.Y. Thinning methodologies-a comprehensive Survey, IEEE Trans. Pattern Anal. and Mach. Intell. 14, 869–885 (1992).
Datta A. and Parui S. A robust parallel thinning algorithm for binary images, Pattern Recognition 27 (9), 1181–1192 (1994).
Altwaijri M., Ayoubi R. and Bayoumi M. Skeletonization of Arabic characters using a neural network mapped on Maspar, World Congress on Neural Networks-International Neural Network Society Annual Meeting, 2, pp. 653–658 (1994).
Niblack C.W., Gibbons P.B. and Capson D.W. Generating skeletons and centerlines from the distance transform, CVGIP: Graphical Models and Image Processing 54 (5), 420–437 (1992).
Shih F.Y. and Pu C.C. A skeletonization algorithm by maxima tracking on Euclidean distance transform, Pattern Recognition 28 (3), 331–341 (1995).
Tarjan R. and Wyk V. An O(n log log n)-time algorithm for triangulating a simple polygon, SIAM J. Comput. 17,143–178 (Feb. 1988).
Yuan J. and Suen C.Y. An optimal O(n) algorithm for identifying line segments from a sequence of chain codes, Pattern Recognition 28 (5), 635–646 (1995).
O'Rourke J. “Computational geometry in C”, Cambridge University Press.
Melhi M.H., Ipson S.S. and Booth W. A database for research in Arabic handwriting recognition, Dept. of E & EE, Internal Report 595, University of Bradford, UK (1997)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ipson, S.S., Melhi, M., Booth, W. (1997). A novel triangulation procedure for thinning cursive text. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1351. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63930-6_119
Download citation
DOI: https://doi.org/10.1007/3-540-63930-6_119
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63930-5
Online ISBN: 978-3-540-69669-8
eBook Packages: Springer Book Archive