A Method of Neighbor Classes Based SVM Classification for Optical Printed Chinese Character Recognition |
| |
Authors: | Jie Zhang Xiaohong Wu Yanmei Yu Daisheng Luo |
| |
Institution: | Image Information Institute, School of Electronics and Information Engineering, Sichuan University, Chengdu, China.; University of Adelaide, Australia, |
| |
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. |
| |
Keywords: | |
|
|