Detecting and eliminating false strokes in skeletons by geometric analysis

Si Wei Lu; He Xu; Cao An Wang

doi:10.1117/12.142180

9 April 1993 Detecting and eliminating false strokes in skeletons by geometric analysis

Si Wei Lu, He Xu, Cao An Wang

Proceedings Volume 1832, Vision Geometry; (1993) https://doi.org/10.1117/12.142180
Event: Applications in Optical Science and Engineering, 1992, Boston, MA, United States

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.

Citation Download Citation

Si Wei Lu, He Xu, and Cao An Wang "Detecting and eliminating false strokes in skeletons by geometric analysis", Proc. SPIE 1832, Vision Geometry, (9 April 1993); https://doi.org/10.1117/12.142180

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available