Share Email Print
cover

Proceedings Paper

Detecting and eliminating false strokes in skeletons by geometric analysis
Author(s): Si Wei Lu; He Xu; Cao An Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Skeletonization is a process by which a binary pattern of a character is transformed into another binary pattern consisting of its skeleton in order to reduce and extract information for further transmission or recognition. It is very important to preserve the shape of the original pre-thinned pattern in order to keep the necessary information for further processing. However, skeletonizing transformation generally results in distorted representation of the original pattern, and usually affects the possibility of correct recognition in the corresponding character. In this paper, a systematical algorithm is applied to detect and correct the distorted part of the skeleton by geometrical analysis. Hence, a more accurate stroke segmentation can be achieved to tell how the lines (strokes) cross (overlap) each other. Our method significantly reduces the rejection rate and substitution rate for character recognition.

Paper Details

Date Published: 9 April 1993
PDF: 12 pages
Proc. SPIE 1832, Vision Geometry, (9 April 1993); doi: 10.1117/12.142180
Show Author Affiliations
Si Wei Lu, Memorial Univ. of Newfoundland (Canada)
He Xu, Memorial Univ. of Newfoundland (Canada)
Cao An Wang, Memorial Univ. of Newfoundland (Canada)


Published in SPIE Proceedings Vol. 1832:
Vision Geometry
Robert A. Melter; Angela Y. Wu, Editor(s)

© SPIE. Terms of Use
Back to Top