Format

Send to

Choose Destination
See comment in PubMed Commons below
PLoS One. 2013;8(3):e57928. doi: 10.1371/journal.pone.0057928. Epub 2013 Mar 11.

A method of neighbor classes based SVM classification for optical printed Chinese character recognition.

Author information

1
Image Information Institute, School of Electronics and Information Engineering, Sichuan University, Chengdu, China.

Erratum in

  • PLoS One. 2013;8(5). doi:10.1371/annotation/f089122e-03d9-4715-9d92-c284f8d8b416.

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.

PMID:
23536777
PMCID:
PMC3594215
DOI:
10.1371/journal.pone.0057928
[Indexed for MEDLINE]
Free PMC Article
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Public Library of Science Icon for PubMed Central
    Loading ...
    Support Center