Online Handwritten New Tai Lue Character Recognition Using SVM

The character recognition technology has been widely developed during these years, but the character recognition study for the new Tai Lue has been lagged. As a result, the digital processes of new Tai Lue have been in troubles. To solve this problem, this paper proposed an online handwritten character recognition method of new Tai Lue based on SVM. Firstly, the handwritten new Tai Lue characters are preprocessed, and then the features of these characters are extracted. Furthermore, the feature set is optimized by Sequential floating backward selection to get a new feature set with small size. Finally, SVM is used to train and test the handwritten new Tai Lue characters with the optimal parameters which obtained by Cross-Validation method. The experimental results whose Top-5 recognition rate reaches 98.86% show that SVM is effective in online handwritten character recognition for new Tai Lue.