Recognition of similar handwritten Chinese characters based on support vector machines and partial space method

Jun Feng; Yang Yang; Xianmei Wang; Zhijun Chen

doi:10.1117/12.522326

2 September 2003 Recognition of similar handwritten Chinese characters based on support vector machines and partial space method

Jun Feng, Yang Yang, Xianmei Wang, Zhijun Chen

Author Affiliations +

Proceedings Volume 5253, Fifth International Symposium on Instrumentation and Control Technology; (2003) https://doi.org/10.1117/12.522326
Event: Fifth International Symposium on Instrumentation and Control Technology, 2003, Beijing, China

Abstract

This paper presents a recognition approach for handwritten similar Chinese characters based on wavelet transform and elastic meshing technique, partial space method and support vector machines (SVM) theory. The technique of combining wavelet transform with elastic meshing is employed for a given handwritten character to extract its feature. In addition, partial space method is adopted to select some components of the feature vector showing the main difference among similar Chinese characters. Finally, SVM classifier based on the Gaussian kernel function is exploited to obtain the recognition result. The experiment results confirm the effectiveness and practicality of the approach.

Citation Download Citation

Jun Feng, Yang Yang, Xianmei Wang, and Zhijun Chen "Recognition of similar handwritten Chinese characters based on support vector machines and partial space method", Proc. SPIE 5253, Fifth International Symposium on Instrumentation and Control Technology, (2 September 2003); https://doi.org/10.1117/12.522326

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