Correction: A Method of Neighbor Classes Based SVM Classification for Optical Printed Chinese Character Recognition
Jie Zhang, Xiaohong Wu, Yanmei Yu, Daisheng Luo · PLoS ONE · 2013
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.