Character Recognition Based On Maximum Membership Principle

DOI

10.2991/icsecs-13.2013.62How to use a DOI?

Keywords

Character recognition; fuzzy sets; feature extraction; maximum membership principle

Abstract

Text recognition is one of the key technologies in an intelligent system. By means of highly effective extraction of the 7 typical features of characters, we dramatically shorten the time spent on feature extraction in this research. Then we built a membership function based on multidimensional normal distribution by utilizing normalized eigenvalue; and finally, we applied maximum membership principle (MMP)-based recognition technology to character recognition. The result indicates that this approach has evidently reduced the time and complexity of calculation while it was still able to maintain high accuracy of recognition.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yu Liao
PY  - 2013/09
DA  - 2013/09
TI  - Character Recognition Based On Maximum Membership Principle
BT  - Proceedings of the 2013 International Conference on Software Engineering and Computer Science
PB  - Atlantis Press
SP  - 283
EP  - 285
SN  - 1951-6851
UR  - https://doi.org/10.2991/icsecs-13.2013.62
DO  - 10.2991/icsecs-13.2013.62
ID  - Liao2013/09
ER  -