Back to Search
Start Over
A Method of Neighbor Classes Based SVM Classification for Optical Printed Chinese Character Recognition.
- Source :
- PLoS ONE; Mar2013, Vol. 8 Issue 3, p1-7, 7p
- Publication Year :
- 2013
-
Abstract
- In optical printed Chinese character recognition (OPCCR), many classifiers have been proposed for the recognition. Among the classifiers, support vector machine (SVM) might be the best classifier. However, SVM is a classifier for two classes. When it is used for multi-classes in OPCCR, its computation is time-consuming. Thus, we propose a neighbor classes based SVM (NC-SVM) to reduce the computation consumption of SVM. Experiments of NC-SVM classification for OPCCR have been done. The results of the experiments have shown that the NC-SVM we proposed can effectively reduce the computation time in OPCCR. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 8
- Issue :
- 3
- Database :
- Complementary Index
- Journal :
- PLoS ONE
- Publication Type :
- Academic Journal
- Accession number :
- 87680017
- Full Text :
- https://doi.org/10.1371/journal.pone.0057928