Multiple Peripheral Segment Features for Coarse Classification of On-Line Chinese Handwritten Character Recognition

In this paper, a simple and efficient method for coarse classification of Chinese characters is presented. In the new approach, a Chinese character is characterized with its outmost and second-peripheral segment features, each of which is expressed as four string vectors. The outmost and second-peripheral segment features of a Chinese word describe the structure of segments in top, bottom, left and right directions respectively. In addition, A scoring-based coarse classification scheme is devised in forming candidate set. Ten sets of Chinese characters are tested and the average number of characters in candidate sets is 100 and error rate is about 2%. Experimental results show that the approach is feasible in coarse classification of Chinese characters.