An application of support vector machines to chinese character classification problem

Recently, it becomes known that support vector machines have high classification performance in a wide variety of applications. This paper applies support vector machines to Chinese character classification problem. Since it is difficult to apply support vector machines into Chinese character classification problem, this paper divides classification process into three stages; rough classification with Euclidean distance, resembling character classification with support vector machines, and fine classification for a small number of resembling characters. The effectiveness of the method is shown through computer experiments.