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

PLoS One. 2013;8(3):e57928. doi: 10.1371/journal.pone.0057928. Epub 2013 Mar 11.

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.

MeSH terms

  • Algorithms
  • China
  • Humans
  • Image Processing, Computer-Assisted
  • Language
  • Pattern Recognition, Automated / methods*
  • Semantics
  • Support Vector Machine*
  • Writing*

Grants and funding

The authors have no support or funding to report.