Computing Irregular Component Spacing of Digital Ink Chinese Characters Handwritten by Junior International Students

There are many irregular component problems in digital ink Chinese characters handwritten by junior international students. The irregular component spacing is one of them. It is necessary to compute the irregularity based on reference characters. This paper presents one quantitative computing approach based on the database of reference Chinese characters' component spacing. The database provides heuristic information for component extraction of digital ink Chinese characters, rule selection for component spacing calculation, and reference data for computing irregularity. Digital ink is used to collect handwritten Chinese characters because of its natural writing and rich information. The automatic extraction of digital ink Chinese character components is realized by reading the heuristic information from the database, and the interactive correction is also provided. Taking the components as a whole, the boundary distances between each component are calculated. Based on the information of reference Chinese character component spacing, the difference and ratio of the component spacing between digital ink characters and reference ones are calculated. This not only provides correction data, but also indicates the severity of the irregularity. The experimental data includes six categories of Chinese character structures, and each structure includes six examples. The calculation results can be used for statistical analysis and rule discovery, which provides data support for the study of Chinese character acquisition.