COARSE CLASSIFICATION OF ONLINE CHINESE CHARACTERS VIA STRUCTURE FEATURE-BASED METHOD

In this paper, we will propose a structure feature-based coarse classi fication mechanism to classify the on-line handwritten Chinese charact ers. The main purpose of coarse classification is to classify on-line Chinese characters into one of the six structure types and divide them into separated parts accordingly, if they can be divided. Our propose d coarse classification mechanism can be used to classify the followin g three writing style categories: square writing characters, partial c onnected characters, and script characters. Two structure classificati on methods for coarse classification are proposed in this paper. One i s the line segment order method, and another is the projection method. Fourteen databases of 5400 frequently used Chinese characters are tes ted in our experiment. The average classification rates of square writ ing characters, partial connected characters, and full connected chara cters are 96.7%, 92.8%, and 91.7%, respectively. The experimental resu lts reveal the feasibility and promise of our proposed approach.