Classification of Chinese Characters Using Pseudo Skeleton Features

In this paper we present a novel method to classify machine printed Chinese characters by matching the code strings generated from pseudo skeleton features. In our approach, the pseudo skeletons of Chinese characters are extracted rather than using skeletons extracted by traditional thinning algorithms. The features of the pseudo skeletons of both input and template characters are then encoded into two code strings. Finally, the edit-distance algorithm is employed to compute the similarity between the two characters based on their corresponding encoded strings. The main contribution of this paper is to effectively classify multi-fonts Chinese characters using a single-font reference database. Experiments were conducted on 5401 daily-used Chinese characters of various fonts and sizes. Experimental results demonstrate the validity and efficiency of our proposed method for classifying Chinese characters.