On-line recognition of handwritten Renqun shorthand for fast mobile Chinese text entry

Abstract

There is a wish to be able to enter Chinese text into mobile computing devices in real-time at the speed of speech. Handwritten shorthand schemes offer the potential to achieve this data recording rate. A new overall solution to the segmentation and classification of phonetic features in Renqun shorthand, which records Chinese characters phonetically, is proposed in this paper. A new writing rule is introduced to improve the machine readability of Renqun shorthand. Evaluation results show that the introduction of the new rule has a positive effect on the recognition performance. The recognition accuracies for vocalized outlines and shortforms following the new rule achieve 83% and 84.07%, respectively.